From www.kazuya.kawakami at gmail.com Fri Apr 22 15:56:29 2016 From: www.kazuya.kawakami at gmail.com (Kawakami Kazuya) Date: Fri, 22 Apr 2016 15:56:29 -0400 Subject: [CL+NLP Lunch] NLP Lunch & Speaking Skills Talk at 12:00 on Apr 29th at GHC6115 Message-ID: Hi all, Please join us for the next CL+NLP lunch at *12:00 on Apr** 29**th** at 6115*, where I will talk about "Multilingual and Multimodal word representation". Lunch will be provided. *Title: *Multilingual and Multimodal word representation *Time*: Apr 29th, 12:00 - 13:00 *Location*: GHC 6115 *Abstract:* Learned word representations are used as features in models of natural language in place of hand-engineered features. Traditionally, type-level representations are learned by aggregating and summarizing word-word concurrence statistics in large corpora. In this talk, I will present two methods for learning word representations using multilingual or multimodal supervision. The first learns representations of words-in-context (rather than context-agnostic word types) using cross-lingual supervision. The motivating hypothesis is that a good representation of a word in context will be one that is sufficient for selecting the correct translation into a second language. These context-sensitive word representations are suitable for, e.g., distinguishing different word senses and other context-modulated variations in meaning. In the second part, I will talk about a method for projecting words into three-dimensional color spaces. Using color-name pairs obtained from an online color design forum, we evaluate our model on a ?color Turing test? and find that, given a name, the color predicted by our model is often considered by human judges to be no worse than the color that actually inspired the name. This model enables the analysis of words and documents in terms of the colors associated with the words they contain, finding for example that recipes are more evocative of colors than poems or news reports. +++++++ After the series of faculty candidate talks, I would like to continue NLP Lunch. Please suggest next speaker to me. I will find a room and lunch. Best regards, Kazuya Kawakami -------------- next part -------------- An HTML attachment was scrubbed... URL: From www.kazuya.kawakami at gmail.com Fri Apr 29 11:34:52 2016 From: www.kazuya.kawakami at gmail.com (Kawakami Kazuya) Date: Fri, 29 Apr 2016 11:34:52 -0400 Subject: [CL+NLP Lunch] NLP Lunch & Speaking Skills Talk at 12:00 on Apr 29th at GHC6115 In-Reply-To: References: Message-ID: Hi all, NLP Lunch will happen in 30 mins. >>>>>>>>>>>>>>>>>>>>>>>>>>>>> Please join us for the next CL+NLP lunch at *12:00 on Apr** 29**th** at 6115*, where I will talk about "Multilingual and Multimodal word representation". Lunch will be provided. *Title: *Multilingual and Multimodal word representation *Time*: Apr 29th, 12:00 - 13:00 *Location*: GHC 6115 *Abstract:* Learned word representations are used as features in models of natural language in place of hand-engineered features. Traditionally, type-level representations are learned by aggregating and summarizing word-word concurrence statistics in large corpora. In this talk, I will present two methods for learning word representations using multilingual or multimodal supervision. The first learns representations of words-in-context (rather than context-agnostic word types) using cross-lingual supervision. The motivating hypothesis is that a good representation of a word in context will be one that is sufficient for selecting the correct translation into a second language. These context-sensitive word representations are suitable for, e.g., distinguishing different word senses and other context-modulated variations in meaning. In the second part, I will talk about a method for projecting words into three-dimensional color spaces. Using color-name pairs obtained from an online color design forum, we evaluate our model on a ?color Turing test? and find that, given a name, the color predicted by our model is often considered by human judges to be no worse than the color that actually inspired the name. This model enables the analysis of words and documents in terms of the colors associated with the words they contain, finding for example that recipes are more evocative of colors than poems or news reports. +++++++ After the series of faculty candidate talks, I would like to continue NLP Lunch. Please suggest next speaker to me. I will find a room and lunch. Best regards, Kazuya Kawakami 2016-04-22 15:56 GMT-04:00 Kawakami Kazuya : > Hi all, > > Please join us for the next CL+NLP lunch at *12:00 on Apr** 29**th** at > 6115*, > where I will talk about "Multilingual and Multimodal word representation" > . > Lunch will be provided. > > *Title: *Multilingual and Multimodal word representation > *Time*: Apr 29th, 12:00 - 13:00 > *Location*: GHC 6115 > *Abstract:* > Learned word representations are used as features in models of natural > language in place of hand-engineered features. Traditionally, type-level > representations are learned by aggregating and summarizing word-word > concurrence statistics in large corpora. In this talk, I will present two > methods for learning word representations using multilingual or multimodal > supervision. The first learns representations of words-in-context (rather > than context-agnostic word types) using cross-lingual supervision. The > motivating hypothesis is that a good representation of a word in context > will be one that is sufficient for selecting the correct translation into a > second language. These context-sensitive word representations are suitable > for, e.g., distinguishing different word senses and other context-modulated > variations in meaning. > > In the second part, I will talk about a method for projecting words into > three-dimensional color spaces. Using color-name pairs obtained from an > online color design forum, we evaluate our model on a ?color Turing test? > and find that, given a name, the color predicted by our model is often > considered by human judges to be no worse than the color that actually > inspired the name. This model enables the analysis of words and documents > in terms of the colors associated with the words they contain, finding for > example that recipes are more evocative of colors than poems or news > reports. > > +++++++ > After the series of faculty candidate talks, I would like to continue NLP > Lunch. > Please suggest next speaker to me. I will find a room and lunch. > > Best regards, > Kazuya Kawakami > -------------- next part -------------- An HTML attachment was scrubbed... URL: