From dcard at andrew.cmu.edu Fri Feb 13 11:25:38 2015 From: dcard at andrew.cmu.edu (Dallas Card) Date: Fri, 13 Feb 2015 11:25:38 -0500 Subject: [CL+NLP Lunch] CL+NLP Lunch, Ankur Parikh, Tuesday February 17th @ 12:00pm Message-ID: <5b8a9cb629c267f94742fcd29766f214.squirrel@webmail.andrew.cmu.edu> Please join us for the next CL+NLP lunch at noon on Tuesday February 17th, where Ankur Parikh will be speaking about language modeling with power low rank ensembles. Lunch will be provided! --- CL+NLP lunch Tuesday, February 17th at 12:00pm GHC 4405 Speaker: Ankur Parikh, Machine Learning Department TITLE: Language Modeling with Power Low Rank Ensembles ABSTRACT: Language modeling, the task of estimating the probability of sequences of words, is an important component in many applications such as speech recognition and machine translation. While seemingly simple, the large vocabulary space and power law nature of language lead to a severe data sparsity problem, making parameter estimation challenging. The predominant approach to language modeling is the n-gram model where n-grams of various orders are interpolated via different smoothing techniques to produce robust estimates of rare sequences. In this work, I present power low rank ensembles (PLRE), a framework for language modeling that consists of collections of low rank matrices and tensors. Our method can be understood as a generalization of n-gram modeling to non-integer n, and includes standard techniques such as absolute discounting, deleted-interpolation, and Kneser Ney smoothing as special cases. Our approach consistently outperforms state-of-the-art modified Kneser Ney baselines while preserving the computational advantages of n-gram models. In particular, unlike other recent advances such as neural language models, our method does not have any partition functions, thus enabling fast evaluation at test time. This work received the best paper runner up award at EMNLP 2014 and is joint work with Avneesh Saluja, Chris Dyer, and Eric Xing. Bio: Ankur Parikh is a PhD candidate at Carnegie Mellon University advised by Professor Eric Xing. He is passionate about research in machine learning, natural language processing (NLP), and computational biology. In particular, his thesis explores probabilistic modeling from the perspective of linear algebra and applications of these insights to design effective solutions for NLP tasks. Ankur has received a best paper runner up award at EMNLP 2014, a best paper in translational bioinformatics at ISMB 2011, and an NSF Graduate Fellowship in 2011. He previously graduated from Princeton University in 2009 with highest honors. http://www.cs.cmu.edu/~apparikh/ From dcard at andrew.cmu.edu Mon Feb 16 22:32:22 2015 From: dcard at andrew.cmu.edu (Dallas Card) Date: Mon, 16 Feb 2015 22:32:22 -0500 Subject: [CL+NLP Lunch] Reminder: CL+NLP Lunch, Ankur Parikh, Tuesday February 17th @ 12:00pm Message-ID: <3f7060e50749a949c398fa6aa345b7b0.squirrel@webmail.andrew.cmu.edu> Please join us for the next CL+NLP lunch at noon on Tuesday February 17th, where Ankur Parikh will be speaking about language modeling with power low rank ensembles. Lunch will be provided! --- CL+NLP lunch Tuesday, February 17th at 12:00pm GHC 4405 Speaker: Ankur Parikh, Machine Learning Department TITLE: Language Modeling with Power Low Rank Ensembles ABSTRACT: Language modeling, the task of estimating the probability of sequences of words, is an important component in many applications such as speech recognition and machine translation. While seemingly simple, the large vocabulary space and power law nature of language lead to a severe data sparsity problem, making parameter estimation challenging. The predominant approach to language modeling is the n-gram model where n-grams of various orders are interpolated via different smoothing techniques to produce robust estimates of rare sequences. In this work, I present power low rank ensembles (PLRE), a framework for language modeling that consists of collections of low rank matrices and tensors. Our method can be understood as a generalization of n-gram modeling to non-integer n, and includes standard techniques such as absolute discounting, deleted-interpolation, and Kneser Ney smoothing as special cases. Our approach consistently outperforms state-of-the-art modified Kneser Ney baselines while preserving the computational advantages of n-gram models. In particular, unlike other recent advances such as neural language models, our method does not have any partition functions, thus enabling fast evaluation at test time. This work received the best paper runner up award at EMNLP 2014 and is joint work with Avneesh Saluja, Chris Dyer, and Eric Xing. Bio: Ankur Parikh is a PhD candidate at Carnegie Mellon University advised by Professor Eric Xing. He is passionate about research in machine learning, natural language processing (NLP), and computational biology. In particular, his thesis explores probabilistic modeling from the perspective of linear algebra and applications of these insights to design effective solutions for NLP tasks. Ankur has received a best paper runner up award at EMNLP 2014, a best paper in translational bioinformatics at ISMB 2011, and an NSF Graduate Fellowship in 2011. He previously graduated from Princeton University in 2009 with highest honors. http://www.cs.cmu.edu/~apparikh/ From dcard at andrew.cmu.edu Tue Feb 24 09:27:53 2015 From: dcard at andrew.cmu.edu (Dallas Card) Date: Tue, 24 Feb 2015 09:27:53 -0500 Subject: [CL+NLP Lunch] CL+NLP Lunch, Fei Liu, Thursday February 26th @ 12:30pm Message-ID: Please join us for the next CL+NLP lunch at 12:30 on Thursday February 26th, where Fei Liu will be speaking about summarization. Lunch will be provided! --- CL+NLP lunch Thursday, February 26th at 12:30pm GHC 4405 Speaker: Fei Liu, LTI Title: Summarizing Information in Big Data: Algorithms and Applications Abstract: Information floods the lives of modern people, and we find it overwhelming. Summarization systems that identify salient pieces of information and present it concisely can help. In this talk, I will discuss both the algorithmic and application perspectives of summarization. Algorithm-wise, I will describe keyword extraction, sentence extraction, and summary generation, including a range of techniques from information extraction to semantic representation of data sources; application-wise, I focus on summarizing human conversations, social media contents, and news articles. The data sources span low-quality speech recognizer outputs and social media chats to high-quality content produced by professional writers. A special focus of my work is exploring multiple information sources. In addition to better integration across sources, this allows abstraction to shared research challenges for broader impact. Finally, I try to identify the missing links in cross-genre summarization studies and discuss future research directions. Speaker Bio: Fei Liu is a postdoctoral fellow at Carnegie Mellon University, member of Noah's ARK. Fei's research interests are in the areas of natural language processing, machine learning, and data mining, with special emphasis on automatic summarization and social media. From 2011 to 2013, Fei worked as a Senior Research Scientist at Bosch Research, Palo Alto, California, one of the largest German companies providing intelligent car systems and home appliances. Fei received her Ph.D. in Computer Science from the University of Texas at Dallas in 2011, supported by an Erik Jonsson Distinguished Research Fellowship. Prior to that, she obtained her Bachelors and Masters degrees in Computer Science from Fudan University, Shanghai, China. Fei has published over twenty peer reviewed articles, and she serves as a referee for leading journals and conferences. -- Dallas Card Machine Learning Department Carnegie Mellon University From dcard at andrew.cmu.edu Thu Feb 26 11:58:28 2015 From: dcard at andrew.cmu.edu (Dallas Card) Date: Thu, 26 Feb 2015 11:58:28 -0500 Subject: [CL+NLP Lunch] Reminder: CL+NLP Lunch, Fei Liu, Today @ 12:30pm in GHC 4405 Message-ID: Please join us for the next CL+NLP lunch at 12:30 on Thursday February 26th, where Fei Liu will be speaking about summarization. Lunch will be provided! --- CL+NLP lunch Thursday, February 26th at 12:30pm GHC 4405 Speaker: Fei Liu, LTI Title: Summarizing Information in Big Data: Algorithms and Applications Abstract: Information floods the lives of modern people, and we find it overwhelming. Summarization systems that identify salient pieces of information and present it concisely can help. In this talk, I will discuss both the algorithmic and application perspectives of summarization. Algorithm-wise, I will describe keyword extraction, sentence extraction, and summary generation, including a range of techniques from information extraction to semantic representation of data sources; application-wise, I focus on summarizing human conversations, social media contents, and news articles. The data sources span low-quality speech recognizer outputs and social media chats to high-quality content produced by professional writers. A special focus of my work is exploring multiple information sources. In addition to better integration across sources, this allows abstraction to shared research challenges for broader impact. Finally, I try to identify the missing links in cross-genre summarization studies and discuss future research directions. Speaker Bio: Fei Liu is a postdoctoral fellow at Carnegie Mellon University, member of Noah's ARK. Fei's research interests are in the areas of natural language processing, machine learning, and data mining, with special emphasis on automatic summarization and social media. From 2011 to 2013, Fei worked as a Senior Research Scientist at Bosch Research, Palo Alto, California, one of the largest German companies providing intelligent car systems and home appliances. Fei received her Ph.D. in Computer Science from the University of Texas at Dallas in 2011, supported by an Erik Jonsson Distinguished Research Fellowship. Prior to that, she obtained her Bachelors and Masters degrees in Computer Science from Fudan University, Shanghai, China. Fei has published over twenty peer reviewed articles, and she serves as a referee for leading journals and conferences. -- Dallas Card Machine Learning Department Carnegie Mellon University From dcard at andrew.cmu.edu Mon Mar 30 15:04:14 2015 From: dcard at andrew.cmu.edu (Dallas Card) Date: Mon, 30 Mar 2015 15:04:14 -0400 Subject: [CL+NLP Lunch] CL+NLP Lunch, Pengtao Xie, Thursday April 2nd @ 12:00pm Message-ID: Please join us for the next CL+NLP lunch at 12:00pm on Thursday April 2nd, where Pengtao Xie will be speaking about incorporating word correlation knowledge into topic models. Lunch will be provided! --- CL+NLP lunch Thursday, April 2nd at 12:00pm GHC 6501 Speaker: Pengtao Xie, LTI Title: Incorporating Word Correlation Knowledge into Topic Modeling Abstract: This work studies how to incorporate external word correlation knowledge to improve the coherence of topic modeling. Existing topic models assume words are generated independently and lack the mechanism to utilize the rich similarity relationships among words to learn coherent topics. To solve this problem, we build a Markov Random Field (MRF) regularized Latent Dirichlet Allocation (LDA) model, which defines a MRF on the latent topic layer of LDA to encourage words labeled as similar to share the same topic label. Under our model, the topic assignment of each word is not independent, but rather affected by the topic labels of its correlated words. Similar words have a better chance to be put into the same topic due to the regularization of the MRF, hence the coherence of topics can be boosted. In addition, our model can accommodate the subtlety, in that whether two words are similar depends on which topic they appear in, which allows words with multiple senses to be properly put into different topics. We derive a variational inference method to infer the posterior probabilities and learn model parameters, and present techniques to deal with the hard-to-compute partition function in the MRF. Experiments on two datasets demonstrate the effectiveness of our model. Speaker Bio: Pengtao Xie is a graduate student in the Language Technologies Institute, working with Professor Eric Xing. His primary research interests lie in latent variable models and large scale distributed machine learning. He received a M.E. from Tsinghua University in 2013 and a B.E. from Sichuan University in 2010. He is the recipient of Siebel Scholarship, Goldman Sachs Global Leader Scholarship and National Scholarship of China. -- Dallas Card Machine Learning Department Carnegie Mellon University From dcard at andrew.cmu.edu Wed Apr 1 14:06:50 2015 From: dcard at andrew.cmu.edu (Dallas Card) Date: Wed, 1 Apr 2015 14:06:50 -0400 Subject: [CL+NLP Lunch] Reminder: CL+NLP Lunch, Pengtao Xie, Thursday April 2nd @ 12:00pm Message-ID: <11bcfb470106a681a25347c05d4450b2.squirrel@webmail.andrew.cmu.edu> Please join us for the next CL+NLP lunch at 12:00pm on Thursday April 2nd, where Pengtao Xie will be speaking about incorporating word correlation knowledge into topic models. Lunch will be provided! --- CL+NLP lunch Thursday, April 2nd at 12:00pm GHC 6501 Speaker: Pengtao Xie, LTI Title: Incorporating Word Correlation Knowledge into Topic Modeling Abstract: This work studies how to incorporate external word correlation knowledge to improve the coherence of topic modeling. Existing topic models assume words are generated independently and lack the mechanism to utilize the rich similarity relationships among words to learn coherent topics. To solve this problem, we build a Markov Random Field (MRF) regularized Latent Dirichlet Allocation (LDA) model, which defines a MRF on the latent topic layer of LDA to encourage words labeled as similar to share the same topic label. Under our model, the topic assignment of each word is not independent, but rather affected by the topic labels of its correlated words. Similar words have a better chance to be put into the same topic due to the regularization of the MRF, hence the coherence of topics can be boosted. In addition, our model can accommodate the subtlety, in that whether two words are similar depends on which topic they appear in, which allows words with multiple senses to be properly put into different topics. We derive a variational inference method to infer the posterior probabilities and learn model parameters, and present techniques to deal with the hard-to-compute partition function in the MRF. Experiments on two datasets demonstrate the effectiveness of our model. Speaker Bio: Pengtao Xie is a graduate student in the Language Technologies Institute, working with Professor Eric Xing. His primary research interests lie in latent variable models and large scale distributed machine learning. He received a M.E. from Tsinghua University in 2013 and a B.E. from Sichuan University in 2010. He is the recipient of Siebel Scholarship, Goldman Sachs Global Leader Scholarship and National Scholarship of China. -- Dallas Card Machine Learning Department Carnegie Mellon University From kkawakam at andrew.cmu.edu Fri Oct 23 16:30:05 2015 From: kkawakam at andrew.cmu.edu (Kazuya Kawakami) Date: Fri, 23 Oct 2015 16:30:05 -0400 Subject: [CL+NLP Lunch] [SHORT NOICE] CL+NLP lunch, Oct.26 Monday Message-ID: Hi All Please join us for the next CL+NLP lunch at noon on Monday Oct 26th, where Jiang Guo will be speaking about Cross-lingual Transfer Parsing. Lunch will be provided! To arrange meetings with Jiang, please see the following document. ( https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit ) ----------------------------------------- ML+NLP lunch Monday, Oct 26th at 11:00am GHC 7101 Speaker: Jiang Guo, Johns Hopkins University [TITLE] Representation Learning for Cross-lingual Transfer Parsing [ABSTRACT] Cross-lingual model transfer has been a promising approach for inducing dependency parsers for low-resource languages where annotated treebanks are not available. The major obstacles for the model transfer approach are two-fold: 1. Lexical features are not directly transferable across languages. 2. Target language-specific syntactic structures are difficult to be recovered. In this talk, I will provide a representation learning framework to address these challenges. By evaluating on the Google universal dependency treebanks (v2.0), our best models yield an absolute improvement of 6.53% in averaged labeled attachment score, as compared with delexicalized multi-source transfer models. We also significantly outperform the state-of-the-art transfer system proposed most recently. [SHORT BIO] Jiang Guo is a joint Ph.D student at Johns Hopkins University and at Harbin Institute of Technology. His research interests are in the areas of natural language processing, machine learning, with special interests on distributed representation learning and its applications on NLP tasks (mostly structure prediction problems). His long-term goal is developing efficient and effective algorithms and softwares for NLP and machine learning applications. ----------------------------------------- Up comming talk will be on 17th Nov. 12:00-13:00 by Ndapa Nakashole. Best regards, Kazuya -------------- next part -------------- An HTML attachment was scrubbed... URL: From wammar at cs.cmu.edu Fri Oct 23 16:43:18 2015 From: wammar at cs.cmu.edu (waleed ammar) Date: Fri, 23 Oct 2015 16:43:18 -0400 Subject: [CL+NLP Lunch] [SHORT NOICE] CL+NLP lunch, Oct.26 Monday In-Reply-To: References: Message-ID: *Clarification: this talk will be held* *11am on Monday (CL+NLP lunch),* *followed by Leonid's talk at noon (ML lunch). We get to have lunch twice this Monday.* On Fri, Oct 23, 2015 at 4:30 PM, Kazuya Kawakami wrote: > Hi All > > Please join us for the next CL+NLP lunch at noon on Monday Oct 26th, > where Jiang Guo will be speaking about Cross-lingual Transfer Parsing. > Lunch will be provided! > > To arrange meetings with Jiang, please see the following document. > ( > https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit > ) > > > ----------------------------------------- > ML+NLP lunch > Monday, Oct 26th at 11:00am > GHC 7101 > > Speaker: Jiang Guo, Johns Hopkins University > > [TITLE] > Representation Learning for Cross-lingual Transfer Parsing > > [ABSTRACT] > Cross-lingual model transfer has been a promising approach for inducing > dependency parsers for low-resource languages where annotated treebanks are > not available. The major obstacles for the model transfer approach are > two-fold: > > 1. Lexical features are not directly transferable across languages. > > 2. Target language-specific syntactic structures are difficult to be > recovered. > > In this talk, I will provide a representation learning framework to > address these challenges. By evaluating on the Google universal dependency > treebanks (v2.0), our best models yield an absolute improvement of 6.53% in > averaged labeled attachment score, as compared with delexicalized > multi-source transfer models. We also significantly outperform the > state-of-the-art transfer system proposed most recently. > > > [SHORT BIO] > Jiang Guo is a joint Ph.D student at Johns Hopkins University and at > Harbin Institute of Technology. His research interests are in the areas of > natural language processing, machine learning, with special interests on > distributed representation learning and its applications on NLP tasks > (mostly structure prediction problems). His long-term goal is developing > efficient and effective algorithms and softwares for NLP and machine > learning applications. > > ----------------------------------------- > > > Up comming talk will be on 17th Nov. 12:00-13:00 by Ndapa Nakashole. > > Best regards, > Kazuya > -- Waleed Ammar Carnegie Mellon University http://www.cs.cmu.edu/~wammar/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From www.kazuya.kawakami at gmail.com Fri Oct 23 16:45:52 2015 From: www.kazuya.kawakami at gmail.com (Kazuya Kawakami) Date: Fri, 23 Oct 2015 16:45:52 -0400 Subject: [CL+NLP Lunch] [SHORT NOTICE] CL+NLP lunch, '11am' Oct.26 Monday Message-ID: Hi All The time should be *11am*. We will have ML lunch talk by Leonid's talk at noon. Sorry. >> Please join us for the next CL+NLP lunch at *11am on Monday Oct 26th at 7101*, where Jiang Guo will be speaking about Cross-lingual Transfer Parsing. Lunch will be provided! To arrange meetings with Jiang, please see the following document. ( https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit ) ----------------------------------------- ML+NLP lunch *Monday, Oct 26th at 11:00amGHC 7101* Speaker: Jiang Guo, Johns Hopkins University [TITLE] Representation Learning for Cross-lingual Transfer Parsing [ABSTRACT] Cross-lingual model transfer has been a promising approach for inducing dependency parsers for low-resource languages where annotated treebanks are not available. The major obstacles for the model transfer approach are two-fold: 1. Lexical features are not directly transferable across languages. 2. Target language-specific syntactic structures are difficult to be recovered. In this talk, I will provide a representation learning framework to address these challenges. By evaluating on the Google universal dependency treebanks (v2.0), our best models yield an absolute improvement of 6.53% in averaged labeled attachment score, as compared with delexicalized multi-source transfer models. We also significantly outperform the state-of-the-art transfer system proposed most recently. [SHORT BIO] Jiang Guo is a joint Ph.D student at Johns Hopkins University and at Harbin Institute of Technology. His research interests are in the areas of natural language processing, machine learning, with special interests on distributed representation learning and its applications on NLP tasks (mostly structure prediction problems). His long-term goal is developing efficient and effective algorithms and softwares for NLP and machine learning applications. ----------------------------------------- Up comming talk will be on 17th Nov. 12:00-13:00 by Ndapa Nakashole. Best regards, Kazuya On Fri, Oct 23, 2015 at 4:39 PM, Kazuya Kawakami < www.kazuya.kawakami at gmail.com> wrote: > Hi Dallas, > > Actually it's a sudden talk. We scheduled it last night ;) > I have never used cs.cmu.edu, but it should be kkawakam. > > Best regards, > Kazuya > > On Fri, Oct 23, 2015 at 4:36 PM, Dallas Card > wrote: > >> Hey Kazuya, >> >> Thanks for organizing this! I just tried adding you as an administrator >> for this list. Is your cs.cmu.edu address also kkawakam? >> >> Thanks, >> Dallas >> >> On Fri, Oct 23, 2015 at 4:30 PM, Kazuya Kawakami > > wrote: >> >>> Hi All >>> >>> Please join us for the next CL+NLP lunch at noon on Monday Oct 26th, >>> where Jiang Guo will be speaking about Cross-lingual Transfer Parsing. >>> Lunch will be provided! >>> >>> To arrange meetings with Jiang, please see the following document. >>> ( >>> https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit >>> ) >>> >>> >>> ----------------------------------------- >>> ML+NLP lunch >>> Monday, Oct 26th at 11:00am >>> GHC 7101 >>> >>> Speaker: Jiang Guo, Johns Hopkins University >>> >>> [TITLE] >>> Representation Learning for Cross-lingual Transfer Parsing >>> >>> [ABSTRACT] >>> Cross-lingual model transfer has been a promising approach for inducing >>> dependency parsers for low-resource languages where annotated treebanks are >>> not available. The major obstacles for the model transfer approach are >>> two-fold: >>> >>> 1. Lexical features are not directly transferable across languages. >>> >>> 2. Target language-specific syntactic structures are difficult to be >>> recovered. >>> >>> In this talk, I will provide a representation learning framework to >>> address these challenges. By evaluating on the Google universal dependency >>> treebanks (v2.0), our best models yield an absolute improvement of 6.53% in >>> averaged labeled attachment score, as compared with delexicalized >>> multi-source transfer models. We also significantly outperform the >>> state-of-the-art transfer system proposed most recently. >>> >>> >>> [SHORT BIO] >>> Jiang Guo is a joint Ph.D student at Johns Hopkins University and at >>> Harbin Institute of Technology. His research interests are in the areas of >>> natural language processing, machine learning, with special interests on >>> distributed representation learning and its applications on NLP tasks >>> (mostly structure prediction problems). His long-term goal is developing >>> efficient and effective algorithms and softwares for NLP and machine >>> learning applications. >>> >>> ----------------------------------------- >>> >>> >>> Up comming talk will be on 17th Nov. 12:00-13:00 by Ndapa Nakashole. >>> >>> Best regards, >>> Kazuya >>> >> >> > -------------- next part -------------- An HTML attachment was scrubbed... URL: From wammar at cs.cmu.edu Mon Oct 26 10:32:30 2015 From: wammar at cs.cmu.edu (waleed ammar) Date: Mon, 26 Oct 2015 10:32:30 -0400 Subject: [CL+NLP Lunch] [SHORT NOTICE] CL+NLP lunch, '11am' Oct.26 Monday In-Reply-To: References: Message-ID: talk starts in half an hour at GHC-7101. waleed > Please join us for the next CL+NLP lunch at *11am on Monday Oct 26th at > 7101*, > where Jiang Guo will be speaking about Cross-lingual Transfer Parsing. > Lunch will be provided! > > To arrange meetings with Jiang, please see the following document. > ( > https://docs.google.com/document/d/1i4s181AWQGY1SJup76BZGgsjpquAH2ZrVe7tHWISPYc/edit > ) > > > ----------------------------------------- > ML+NLP lunch > > *Monday, Oct 26th at 11:00amGHC 7101* > > Speaker: Jiang Guo, Johns Hopkins University > > [TITLE] > Representation Learning for Cross-lingual Transfer Parsing > > [ABSTRACT] > Cross-lingual model transfer has been a promising approach for inducing > dependency parsers for low-resource languages where annotated treebanks are > not available. The major obstacles for the model transfer approach are > two-fold: > > 1. Lexical features are not directly transferable across languages. > > 2. Target language-specific syntactic structures are difficult to be > recovered. > > In this talk, I will provide a representation learning framework to > address these challenges. By evaluating on the Google universal dependency > treebanks (v2.0), our best models yield an absolute improvement of 6.53% in > averaged labeled attachment score, as compared with delexicalized > multi-source transfer models. We also significantly outperform the > state-of-the-art transfer system proposed most recently. > > > [SHORT BIO] > Jiang Guo is a joint Ph.D student at Johns Hopkins University and at > Harbin Institute of Technology. His research interests are in the areas of > natural language processing, machine learning, with special interests on > distributed representation learning and its applications on NLP tasks > (mostly structure prediction problems). His long-term goal is developing > efficient and effective algorithms and softwares for NLP and machine > learning applications. > > ----------------------------------------- > > > Up comming talk will be on 17th Nov. 12:00-13:00 by Ndapa Nakashole. > > Best regards, > Kazuya > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From kkawakam at andrew.cmu.edu Thu Nov 12 17:28:05 2015 From: kkawakam at andrew.cmu.edu (Kazuya Kawakami) Date: Thu, 12 Nov 2015 17:28:05 -0500 Subject: [CL+NLP Lunch] CL+NLP lunch at 13am on Nov 17th at 8102 Message-ID: Please join us for the next CL+NLP lunch at *13am on **Nov* *17th** at * *8102*, where Ndapa Nakashole will be speaking about Knowledge Graph. Lunch will be provided! ----------------------------------------- ML+NLP lunch *Tuesday Nov 17th at 13:00 - 14:00**GHC 8102* The Knowledge Graph Extraction Virtuous Circle Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large amounts of beliefs about real world entities using machine reading methods. Current machine readers have been successful at populating such knowledge graphs by means of pattern detection ? a shallow way of machine reading which leverages the redundancy of large corpora to capture language patterns. However, machine readers still lack the ability to fully understand language. In the pursuit of the much harder goal of language comprehension, knowledge graphs present an opportunity for a virtuous circle: the accumulated knowledge can be used to improve machine readers; in turn, advanced reading methods can be used to populate knowledge graphs with beliefs expressed using complex and potentially ambiguous language. In this talk, I will elaborate on this virtuous circle, starting with methods for building knowledge graphs, followed by results on using them for machine reading. Bio: Ndapa Nakashole is a postdoctoral fellow in the Machine Learning Department at Carnegie Mellon University. She holds a B.Sc and an M.Sc from the University of Cape Town, South Africa and a PhD from the Max Planck Institute for Informatics and Saarland University, Germany. ----------------------------------------- Up comming talk will be on Monday, Nov.23, by Chu-Ren Huang. Best regards, Kazuya -------------- next part -------------- An HTML attachment was scrubbed... URL: From kkawakam at andrew.cmu.edu Mon Nov 16 11:03:12 2015 From: kkawakam at andrew.cmu.edu (Kazuya Kawakami) Date: Mon, 16 Nov 2015 11:03:12 -0500 Subject: [CL+NLP Lunch] [Tomorrow] CL+NLP lunch at 13am on Nov 17th at 8102 Message-ID: This is a reminder for NLP lunh talk tomorrow. Please join us for the next CL+NLP lunch at *13am on **Nov* *17th** at * *8102*, where Ndapa Nakashole will be speaking about Knowledge Graph. Lunch will be provided! ----------------------------------------- ML+NLP lunch *Tuesday Nov 17th at 13:00 - 14:00**GHC 8102* The Knowledge Graph Extraction Virtuous Circle Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large amounts of beliefs about real world entities using machine reading methods. Current machine readers have been successful at populating such knowledge graphs by means of pattern detection ? a shallow way of machine reading which leverages the redundancy of large corpora to capture language patterns. However, machine readers still lack the ability to fully understand language. In the pursuit of the much harder goal of language comprehension, knowledge graphs present an opportunity for a virtuous circle: the accumulated knowledge can be used to improve machine readers; in turn, advanced reading methods can be used to populate knowledge graphs with beliefs expressed using complex and potentially ambiguous language. In this talk, I will elaborate on this virtuous circle, starting with methods for building knowledge graphs, followed by results on using them for machine reading. Bio: Ndapa Nakashole is a postdoctoral fellow in the Machine Learning Department at Carnegie Mellon University. She holds a B.Sc and an M.Sc from the University of Cape Town, South Africa and a PhD from the Max Planck Institute for Informatics and Saarland University, Germany. ----------------------------------------- Up comming talk will be on Monday, Nov.23, by Chu-Ren Huang. Best regards, Kazuya On Mon, Nov 16, 2015 at 11:00 AM, Kazuya Kawakami < www.kazuya.kawakami at gmail.com> wrote: > This is a reminder for NLP lunh talk tomorrow. > > Please join us for the next CL+NLP lunch at *13am on **Nov* *17th** at * > *8102*, > where Ndapa Nakashole will be speaking about Knowledge Graph. > Lunch will be provided! > > ----------------------------------------- > ML+NLP lunch > > *Tuesday Nov 17th at 13:00 - 14:00**GHC 8102* > > The Knowledge Graph Extraction Virtuous Circle > > Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large > amounts of beliefs about real world entities using machine reading methods. > Current machine readers have been successful at populating such knowledge > graphs by means of pattern detection ? a shallow way of machine reading > which leverages the redundancy of large corpora to capture language > patterns. However, machine readers still lack the ability to fully > understand language. > In the pursuit of the much harder goal of language comprehension, > knowledge graphs present an opportunity for a virtuous circle: the > accumulated knowledge > can be used to improve machine readers; in turn, advanced reading methods > can be used to populate knowledge graphs with beliefs expressed using > complex and potentially ambiguous language. In this talk, I will elaborate > on this virtuous circle, starting with methods for building knowledge > graphs, followed by results on using them for machine reading. > > > Bio: > Ndapa Nakashole is a postdoctoral fellow in the Machine Learning > Department at Carnegie Mellon University. > She holds a B.Sc and an M.Sc from the University of Cape Town, South > Africa and a PhD from the Max Planck Institute for Informatics and Saarland > University, Germany. > ----------------------------------------- > > Up comming talk will be on Monday, Nov.23, by Chu-Ren Huang. > > Best regards, > Kazuya > -------------- next part -------------- An HTML attachment was scrubbed... URL: From www.kazuya.kawakami at gmail.com Tue Nov 17 11:52:27 2015 From: www.kazuya.kawakami at gmail.com (Kazuya Kawakami) Date: Tue, 17 Nov 2015 11:52:27 -0500 Subject: [CL+NLP Lunch] [Today] CL+NLP lunch at 13am at 8102 Message-ID: This is a reminder for NLP lunh talk today! Please join us for the next CL+NLP lunch at *13am **at **8102*, where Ndapa Nakashole will be speaking about Knowledge Graph. Lunch will be provided. We got some requests for recording, but unfortunately we cannot record the talk this time. Let me figure out how to share the talk to students in conferences and in SV campus. ----------------------------------------- ML+NLP lunch *Tuesday Nov 17th at 13:00 - 14:00**GHC 8102* The Knowledge Graph Extraction Virtuous Circle Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large amounts of beliefs about real world entities using machine reading methods. Current machine readers have been successful at populating such knowledge graphs by means of pattern detection ? a shallow way of machine reading which leverages the redundancy of large corpora to capture language patterns. However, machine readers still lack the ability to fully understand language. In the pursuit of the much harder goal of language comprehension, knowledge graphs present an opportunity for a virtuous circle: the accumulated knowledge can be used to improve machine readers; in turn, advanced reading methods can be used to populate knowledge graphs with beliefs expressed using complex and potentially ambiguous language. In this talk, I will elaborate on this virtuous circle, starting with methods for building knowledge graphs, followed by results on using them for machine reading. Bio: Ndapa Nakashole is a postdoctoral fellow in the Machine Learning Department at Carnegie Mellon University. She holds a B.Sc and an M.Sc from the University of Cape Town, South Africa and a PhD from the Max Planck Institute for Informatics and Saarland University, Germany. ----------------------------------------- Best regards, Kazuya On Mon, Nov 16, 2015 at 11:03 AM, Kazuya Kawakami wrote: > This is a reminder for NLP lunh talk tomorrow. > > Please join us for the next CL+NLP lunch at *13am on **Nov* *17th** at * > *8102*, > where Ndapa Nakashole will be speaking about Knowledge Graph. > Lunch will be provided! > > ----------------------------------------- > ML+NLP lunch > > *Tuesday Nov 17th at 13:00 - 14:00**GHC 8102* > > The Knowledge Graph Extraction Virtuous Circle > > Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large > amounts of beliefs about real world entities using machine reading methods. > Current machine readers have been successful at populating such knowledge > graphs by means of pattern detection ? a shallow way of machine reading > which leverages the redundancy of large corpora to capture language > patterns. However, machine readers still lack the ability to fully > understand language. > In the pursuit of the much harder goal of language comprehension, > knowledge graphs present an opportunity for a virtuous circle: the > accumulated knowledge > can be used to improve machine readers; in turn, advanced reading methods > can be used to populate knowledge graphs with beliefs expressed using > complex and potentially ambiguous language. In this talk, I will elaborate > on this virtuous circle, starting with methods for building knowledge > graphs, followed by results on using them for machine reading. > > > Bio: > Ndapa Nakashole is a postdoctoral fellow in the Machine Learning > Department at Carnegie Mellon University. > She holds a B.Sc and an M.Sc from the University of Cape Town, South > Africa and a PhD from the Max Planck Institute for Informatics and Saarland > University, Germany. > ----------------------------------------- > > Up comming talk will be on Monday, Nov.23, by Chu-Ren Huang. > > Best regards, > Kazuya > > On Mon, Nov 16, 2015 at 11:00 AM, Kazuya Kawakami < > www.kazuya.kawakami at gmail.com> wrote: > >> This is a reminder for NLP lunh talk tomorrow. >> >> Please join us for the next CL+NLP lunch at *13am on **Nov* *17th** at * >> *8102*, >> where Ndapa Nakashole will be speaking about Knowledge Graph. >> Lunch will be provided! >> >> ----------------------------------------- >> ML+NLP lunch >> >> *Tuesday Nov 17th at 13:00 - 14:00**GHC 8102* >> >> The Knowledge Graph Extraction Virtuous Circle >> >> Knowledge graphs such a NELL, Freebase, and YAGO have accumulated large >> amounts of beliefs about real world entities using machine reading methods. >> Current machine readers have been successful at populating such knowledge >> graphs by means of pattern detection ? a shallow way of machine reading >> which leverages the redundancy of large corpora to capture language >> patterns. However, machine readers still lack the ability to fully >> understand language. >> In the pursuit of the much harder goal of language comprehension, >> knowledge graphs present an opportunity for a virtuous circle: the >> accumulated knowledge >> can be used to improve machine readers; in turn, advanced reading methods >> can be used to populate knowledge graphs with beliefs expressed using >> complex and potentially ambiguous language. In this talk, I will elaborate >> on this virtuous circle, starting with methods for building knowledge >> graphs, followed by results on using them for machine reading. >> >> >> Bio: >> Ndapa Nakashole is a postdoctoral fellow in the Machine Learning >> Department at Carnegie Mellon University. >> She holds a B.Sc and an M.Sc from the University of Cape Town, South >> Africa and a PhD from the Max Planck Institute for Informatics and Saarland >> University, Germany. >> ----------------------------------------- >> >> Up comming talk will be on Monday, Nov.23, by Chu-Ren Huang. >> >> Best regards, >> Kazuya >> > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From www.kazuya.kawakami at gmail.com Fri Nov 20 11:59:38 2015 From: www.kazuya.kawakami at gmail.com (Kazuya Kawakami) Date: Fri, 20 Nov 2015 11:59:38 -0500 Subject: [CL+NLP Lunch] CL+NLP lunch at 12:00 on Nov 23th at 8102 Message-ID: Please join us for the next CL+NLP lunch at *12:00 on **Nov** 23**th** at * *8102*, where Chu-Ren Huang will be speaking about Chinese Language Processing. Lunch will be provided! ----------------------------------------- ML+NLP lunch *Tuesday Nov 23th at 12:00* *GHC 8102* What You Need to Know about Chinese for Chinese Language Processing In this talk, I will introduce essential knowledge of Chinese linguistics encompassing both the fundamental knowledge of the linguistic structure of Chinese as well as explanations regarding how such knowledge of the language can be explored in Chinese language processing. The perspective will be synergetic, aiming to provide comprehensive knowledge of the linguistic characteristics of the Chinese language along with insights and case studies explaining how such knowledge can help language technology. The talk will be organized according to the structure of linguistic knowledge of Chinese, starting from the basic building block to the use of Chinese in context. The first part deals with characters (?) as the basic linguistic unit of Chinese in terms of phonology, orthography, and basic concepts. An ontological view of how the Chinese writing system organizes meaningful content as well as how this onomasiological decision affects Chinese text processing will also be discussed. The second part deals with words (?) and presents basic issues involving the definition and identification of words in Chinese, especially given the lack of conventional marks of word boundaries. The third part will focus on lemmatization and parts of speech (??), underlining the unique challenges Chinese poses for lemmatization, as well as distributional properties of Chinese PoS and tagging systems. The fourth part deals with sentence and structure, focusing on how to identify grammatical relations in Chinese as well as a few Chinese-specific constructions. In each topic, an empirical foundation of linguistics facts are clearly explicated with a robust generalization, and the linguistic generalization is then accounted for in terms of its function in the knowledge representation system. Lastly this knowledge representation role is then exploited in terms of the aims of specific language technology tasks. In terms of references, in addition to language resources and various relevant papers, the tutorial will make reference to Huang and Shi?s (2016) reference grammar for linguistic description of Chinese. Bio: Chu-Ren Huang, ???, is a Chair Professor of Applied Chinese Language Studies, The Hong Kong Polytechnic University. He is a President of Hong Kong Academy of the Humanities and a Permanent Member, International Committee on Computational Linguistics. ----------------------------------------- Best regards, Kazuya -------------- next part -------------- An HTML attachment was scrubbed... URL: From www.kazuya.kawakami at gmail.com Fri Nov 20 12:19:36 2015 From: www.kazuya.kawakami at gmail.com (Kazuya Kawakami) Date: Fri, 20 Nov 2015 12:19:36 -0500 Subject: [CL+NLP Lunch] CL+NLP lunch at 12:00 on Nov 23th at 8102 In-Reply-To: References: Message-ID: Sorry it was on 12:00 on Monday, Nov. 23th at 8102. Please join us for the next CL+NLP lunch at *12:00 on **Nov** 23**th** at * *8102*, where Chu-Ren Huang will be speaking about Chinese Language Processing. Lunch will be provided! ----------------------------------------- ML+NLP lunch *Monday Nov 23th at 12:00* *GHC 8102* What You Need to Know about Chinese for Chinese Language Processing In this talk, I will introduce essential knowledge of Chinese linguistics encompassing both the fundamental knowledge of the linguistic structure of Chinese as well as explanations regarding how such knowledge of the language can be explored in Chinese language processing. The perspective will be synergetic, aiming to provide comprehensive knowledge of the linguistic characteristics of the Chinese language along with insights and case studies explaining how such knowledge can help language technology. The talk will be organized according to the structure of linguistic knowledge of Chinese, starting from the basic building block to the use of Chinese in context. The first part deals with characters (?) as the basic linguistic unit of Chinese in terms of phonology, orthography, and basic concepts. An ontological view of how the Chinese writing system organizes meaningful content as well as how this onomasiological decision affects Chinese text processing will also be discussed. The second part deals with words (?) and presents basic issues involving the definition and identification of words in Chinese, especially given the lack of conventional marks of word boundaries. The third part will focus on lemmatization and parts of speech (??), underlining the unique challenges Chinese poses for lemmatization, as well as distributional properties of Chinese PoS and tagging systems. The fourth part deals with sentence and structure, focusing on how to identify grammatical relations in Chinese as well as a few Chinese-specific constructions. In each topic, an empirical foundation of linguistics facts are clearly explicated with a robust generalization, and the linguistic generalization is then accounted for in terms of its function in the knowledge representation system. Lastly this knowledge representation role is then exploited in terms of the aims of specific language technology tasks. In terms of references, in addition to language resources and various relevant papers, the tutorial will make reference to Huang and Shi?s (2016) reference grammar for linguistic description of Chinese. Bio: Chu-Ren Huang, ???, is a Chair Professor of Applied Chinese Language Studies, The Hong Kong Polytechnic University. He is a President of Hong Kong Academy of the Humanities and a Permanent Member, International Committee on Computational Linguistics. ----------------------------------------- Best regards, Kazuya On Fri, Nov 20, 2015 at 11:59 AM, Kazuya Kawakami < www.kazuya.kawakami at gmail.com> wrote: > Please join us for the next CL+NLP lunch at *12:00 on **Nov** 23**th* > * at **8102*, > where Chu-Ren Huang will be speaking about Chinese Language Processing. > Lunch will be provided! > > ----------------------------------------- > ML+NLP lunch > *Tuesday Nov 23th at 12:00* > *GHC 8102* > > What You Need to Know about Chinese for Chinese Language Processing > > > In this talk, I will introduce essential knowledge of Chinese linguistics encompassing both the fundamental knowledge of the linguistic structure of Chinese as well as explanations regarding how such knowledge of the language can be explored in Chinese language processing. The perspective will be synergetic, aiming to provide comprehensive knowledge of the linguistic characteristics of the Chinese language along with insights and case studies explaining how such knowledge can help language technology. > > > The talk will be organized according to the structure of linguistic knowledge of Chinese, starting from the basic building block to the use of Chinese in context. The first part deals with characters (?) as the basic linguistic unit of Chinese in terms of phonology, orthography, and basic concepts. An ontological view of how the Chinese writing system organizes meaningful content as well as how this onomasiological decision affects Chinese text processing will also be discussed. The second part deals with words (?) and presents basic issues involving the definition and identification of words in Chinese, especially given the lack of conventional marks of word boundaries. The third part will focus on lemmatization and parts of speech (??), underlining the unique challenges Chinese poses for lemmatization, as well as distributional properties of Chinese PoS and tagging systems. The fourth part deals with sentence and structure, focusing on how to identify grammatical relations in Chinese as well as a few Chinese-specific constructions. In each topic, an empirical foundation of linguistics facts are clearly explicated with a robust generalization, and the linguistic generalization is then accounted for in terms of its function in the knowledge representation system. Lastly this knowledge representation role is then exploited in terms of the aims of specific language technology tasks. In terms of references, in addition to language resources and various relevant papers, the tutorial will make reference to Huang and Shi?s (2016) reference grammar for linguistic description of Chinese. > > Bio: > Chu-Ren Huang, ???, is a Chair Professor of Applied Chinese Language > Studies, The Hong Kong Polytechnic University. > He is a President of Hong Kong Academy of the Humanities and a > Permanent Member, International Committee on Computational Linguistics. > ----------------------------------------- > > Best regards, > Kazuya > -------------- next part -------------- An HTML attachment was scrubbed... URL: From www.kazuya.kawakami at gmail.com Mon Nov 23 10:16:22 2015 From: www.kazuya.kawakami at gmail.com (Kazuya Kawakami) Date: Mon, 23 Nov 2015 10:16:22 -0500 Subject: [CL+NLP Lunch] [TODAY] CL+NLP lunch at 12:00 on Nov 23th at 8102 Message-ID: This is a reminder for nlp-lunch talk today!! Please join us for the next CL+NLP lunch at *12:00 on **Nov** 23**th** at * *8102*, where Chu-Ren Huang will be speaking about Chinese Language Processing. Lunch will be provided! ----------------------------------------- ML+NLP lunch *Monday Nov 23th at 12:00* *GHC 8102* What You Need to Know about Chinese for Chinese Language Processing In this talk, I will introduce essential knowledge of Chinese linguistics encompassing both the fundamental knowledge of the linguistic structure of Chinese as well as explanations regarding how such knowledge of the language can be explored in Chinese language processing. The perspective will be synergetic, aiming to provide comprehensive knowledge of the linguistic characteristics of the Chinese language along with insights and case studies explaining how such knowledge can help language technology. The talk will be organized according to the structure of linguistic knowledge of Chinese, starting from the basic building block to the use of Chinese in context. The first part deals with characters (?) as the basic linguistic unit of Chinese in terms of phonology, orthography, and basic concepts. An ontological view of how the Chinese writing system organizes meaningful content as well as how this onomasiological decision affects Chinese text processing will also be discussed. The second part deals with words (?) and presents basic issues involving the definition and identification of words in Chinese, especially given the lack of conventional marks of word boundaries. The third part will focus on lemmatization and parts of speech (??), underlining the unique challenges Chinese poses for lemmatization, as well as distributional properties of Chinese PoS and tagging systems. The fourth part deals with sentence and structure, focusing on how to identify grammatical relations in Chinese as well as a few Chinese-specific constructions. In each topic, an empirical foundation of linguistics facts are clearly explicated with a robust generalization, and the linguistic generalization is then accounted for in terms of its function in the knowledge representation system. Lastly this knowledge representation role is then exploited in terms of the aims of specific language technology tasks. In terms of references, in addition to language resources and various relevant papers, the tutorial will make reference to Huang and Shi?s (2016) reference grammar for linguistic description of Chinese. Bio: Chu-Ren Huang, ???, is a Chair Professor of Applied Chinese Language Studies, The Hong Kong Polytechnic University. He is a President of Hong Kong Academy of the Humanities and a Permanent Member, International Committee on Computational Linguistics. ----------------------------------------- Best regards, Kazuya On Fri, Nov 20, 2015 at 12:19 PM, Kazuya Kawakami < www.kazuya.kawakami at gmail.com> wrote: > Sorry it was on 12:00 on Monday, Nov. 23th at 8102. > > Please join us for the next CL+NLP lunch at *12:00 on **Nov** 23**th* > * at **8102*, > where Chu-Ren Huang will be speaking about Chinese Language Processing. > Lunch will be provided! > > ----------------------------------------- > ML+NLP lunch > *Monday Nov 23th at 12:00* > *GHC 8102* > > What You Need to Know about Chinese for Chinese Language Processing > > > In this talk, I will introduce essential knowledge of Chinese linguistics encompassing both the fundamental knowledge of the linguistic structure of Chinese as well as explanations regarding how such knowledge of the language can be explored in Chinese language processing. The perspective will be synergetic, aiming to provide comprehensive knowledge of the linguistic characteristics of the Chinese language along with insights and case studies explaining how such knowledge can help language technology. > > > The talk will be organized according to the structure of linguistic knowledge of Chinese, starting from the basic building block to the use of Chinese in context. The first part deals with characters (?) as the basic linguistic unit of Chinese in terms of phonology, orthography, and basic concepts. An ontological view of how the Chinese writing system organizes meaningful content as well as how this onomasiological decision affects Chinese text processing will also be discussed. The second part deals with words (?) and presents basic issues involving the definition and identification of words in Chinese, especially given the lack of conventional marks of word boundaries. The third part will focus on lemmatization and parts of speech (??), underlining the unique challenges Chinese poses for lemmatization, as well as distributional properties of Chinese PoS and tagging systems. The fourth part deals with sentence and structure, focusing on how to identify grammatical relations in Chinese as well as a few Chinese-specific constructions. In each topic, an empirical foundation of linguistics facts are clearly explicated with a robust generalization, and the linguistic generalization is then accounted for in terms of its function in the knowledge representation system. Lastly this knowledge representation role is then exploited in terms of the aims of specific language technology tasks. In terms of references, in addition to language resources and various relevant papers, the tutorial will make reference to Huang and Shi?s (2016) reference grammar for linguistic description of Chinese. > > Bio: > Chu-Ren Huang, ???, is a Chair Professor of Applied Chinese Language > Studies, The Hong Kong Polytechnic University. > He is a President of Hong Kong Academy of the Humanities and a > Permanent Member, International Committee on Computational Linguistics. > ----------------------------------------- > > Best regards, > Kazuya > > On Fri, Nov 20, 2015 at 11:59 AM, Kazuya Kawakami < > www.kazuya.kawakami at gmail.com> wrote: > >> Please join us for the next CL+NLP lunch at *12:00 on **Nov** 23**th* >> * at **8102*, >> where Chu-Ren Huang will be speaking about Chinese Language Processing. >> Lunch will be provided! >> >> ----------------------------------------- >> ML+NLP lunch >> *Tuesday Nov 23th at 12:00* >> *GHC 8102* >> >> What You Need to Know about Chinese for Chinese Language Processing >> >> >> In this talk, I will introduce essential knowledge of Chinese linguistics encompassing both the fundamental knowledge of the linguistic structure of Chinese as well as explanations regarding how such knowledge of the language can be explored in Chinese language processing. The perspective will be synergetic, aiming to provide comprehensive knowledge of the linguistic characteristics of the Chinese language along with insights and case studies explaining how such knowledge can help language technology. >> >> >> The talk will be organized according to the structure of linguistic knowledge of Chinese, starting from the basic building block to the use of Chinese in context. The first part deals with characters (?) as the basic linguistic unit of Chinese in terms of phonology, orthography, and basic concepts. An ontological view of how the Chinese writing system organizes meaningful content as well as how this onomasiological decision affects Chinese text processing will also be discussed. The second part deals with words (?) and presents basic issues involving the definition and identification of words in Chinese, especially given the lack of conventional marks of word boundaries. The third part will focus on lemmatization and parts of speech (??), underlining the unique challenges Chinese poses for lemmatization, as well as distributional properties of Chinese PoS and tagging systems. The fourth part deals with sentence and structure, focusing on how to identify grammatical relations in Chinese as well as a few Chinese-specific constructions. In each topic, an empirical foundation of linguistics facts are clearly explicated with a robust generalization, and the linguistic generalization is then accounted for in terms of its function in the knowledge representation system. Lastly this knowledge representation role is then exploited in terms of the aims of specific language technology tasks. In terms of references, in addition to language resources and various relevant papers, the tutorial will make reference to Huang and Shi?s (2016) reference grammar for linguistic description of Chinese. >> >> Bio: >> Chu-Ren Huang, ???, is a Chair Professor of Applied Chinese Language >> Studies, The Hong Kong Polytechnic University. >> He is a President of Hong Kong Academy of the Humanities and a >> Permanent Member, International Committee on Computational Linguistics. >> ----------------------------------------- >> >> Best regards, >> Kazuya >> > > -------------- next part -------------- An HTML attachment was scrubbed... URL: