From dyogatama at cs.cmu.edu  Sat Nov 10 15:00:44 2012
From: dyogatama at cs.cmu.edu (Dani Yogatama)
Date: Sat, 10 Nov 2012 15:00:44 -0500
Subject: [CL+NLP Lunch] CL+NLP Lunch Tuesday Nov 13 @ noon
Message-ID: <CAJPxrhzLnW9hqWb9WJW-cOtPdPu37BaV1fBO-XzE7AdMweyV5g@mail.gmail.com>

Hi all,

We are excited to announce that Dirk Hovy will speak to the the CL+NLP
Lunch.
Details are included below.
Lunch will be provided.

If you would like to receive announcements about future CL+NLP Lunch talks,
subscribe to the mailing list:
https://mailman.srv.cs.cmu.edu/mailman/listinfo/nlp-lunch


Thanks,
Dani

===================================================
*CL+NLP Lunch* (http://www.cs.cmu.edu/~nlp-lunch/)
*Speaker*: Dirk Hovy, University of Southern California
*Date*: Tuesday, November 13, 2012
*Time*: 12:00 noon
*Venue*: GHC 6115

*Title*:
Learning Semantic Types and Relations from Syntactic Context

*Abstract*:
Natural Language Processing (NLP) is moving towards incorporating more
semantics into its applications, such as Machine Translation (MT) or
Question Answering (QA). Most semantic frameworks depend on predefined
"external" resources, such as knowledge bases or ontologies. This requires
a lot of manual effort, but even then it is impossible to build a complete
representation of the world. Instead, we would like to learn a sufficient
representation directly from data.

One way to encode meaning is through syntactic and semantic relations
between predicates and their arguments. Relations are thus at the core of
meaning and information. Recently, several approaches have collected large
corpora of syntactically related word chains (e.g., subject, verb, object).
However, these chains are extracted at the lexical level and do not
generalize well, so their use for semantic interpretation is limited. If we
could use these lexical chains as inputs to generalize beyond the word
level, we would be able to learn semantic relations and make use of these
existing resources.

In this talk, I will present a method to learn semantic types and relations
from raw text.
I construct unsupervised models on syntactic dependency arcs, using
potential types as latent variables. The resulting models allow for quick
domain adaptation and unknown relations, and avoid data sparsity caused by
intervening words.
I show improvements over state-of-the-art systems as well as novel
approaches to fully exploit the structure contained in the data. My method
builds on existing triple stores and does not require any external
knowledge bases, manual annotation, or pre-defined predicates or arguments.

*Bio*:
Dirk Hovy is a PhD candidate in Natural Language Processing at the
University of Southern California (USC), and holds a Masters in
linguistics. He is interested in data-driven models of meaning and
understanding and has published on unsupervised learning, information
extraction, word-sense disambiguation, and temporal relation classification
(see <http://www.dirkhovy.com/portfolio/papers/index.php>).
His thesis work is concerned with how computers can learn semantic types
and relations from raw text, without recurrence to external resources.
His other interests include baking, cooking, crossfit, and medieval art and
literature.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/nlp-lunch/attachments/20121110/1a271368/attachment.html>

From dyogatama at cs.cmu.edu  Mon Nov 12 00:14:04 2012
From: dyogatama at cs.cmu.edu (Dani Yogatama)
Date: Mon, 12 Nov 2012 00:14:04 -0500
Subject: [CL+NLP Lunch] CL+NLP Lunch Tuesday Nov 13 @ noon
In-Reply-To: <CAJPxrhzLnW9hqWb9WJW-cOtPdPu37BaV1fBO-XzE7AdMweyV5g@mail.gmail.com>
References: <CAJPxrhzLnW9hqWb9WJW-cOtPdPu37BaV1fBO-XzE7AdMweyV5g@mail.gmail.com>
Message-ID: <CAJPxrhzzVXHS=+C4TFR_CNcWkGgaTtLq20gaz+A0GtfFru0=nQ@mail.gmail.com>

This talk has been canceled.
There will be *no* CL+NLP Lunch on Tuesday Nov 13.


On Sat, Nov 10, 2012 at 3:00 PM, Dani Yogatama <dyogatama at cs.cmu.edu> wrote:

> Hi all,
>
> We are excited to announce that Dirk Hovy will speak to the the CL+NLP
> Lunch.
> Details are included below.
> Lunch will be provided.
>
> If you would like to receive announcements about future CL+NLP Lunch
> talks, subscribe to the mailing list:
> https://mailman.srv.cs.cmu.edu/mailman/listinfo/nlp-lunch
>
>
> Thanks,
> Dani
>
> ===================================================
> *CL+NLP Lunch* (http://www.cs.cmu.edu/~nlp-lunch/)
> *Speaker*: Dirk Hovy, University of Southern California
> *Date*: Tuesday, November 13, 2012
> *Time*: 12:00 noon
> *Venue*: GHC 6115
>
> *Title*:
> Learning Semantic Types and Relations from Syntactic Context
>
> *Abstract*:
> Natural Language Processing (NLP) is moving towards incorporating more
> semantics into its applications, such as Machine Translation (MT) or
> Question Answering (QA). Most semantic frameworks depend on predefined
> "external" resources, such as knowledge bases or ontologies. This requires
> a lot of manual effort, but even then it is impossible to build a complete
> representation of the world. Instead, we would like to learn a sufficient
> representation directly from data.
>
> One way to encode meaning is through syntactic and semantic relations
> between predicates and their arguments. Relations are thus at the core of
> meaning and information. Recently, several approaches have collected large
> corpora of syntactically related word chains (e.g., subject, verb, object).
> However, these chains are extracted at the lexical level and do not
> generalize well, so their use for semantic interpretation is limited. If we
> could use these lexical chains as inputs to generalize beyond the word
> level, we would be able to learn semantic relations and make use of these
> existing resources.
>
> In this talk, I will present a method to learn semantic types and
> relations from raw text.
> I construct unsupervised models on syntactic dependency arcs, using
> potential types as latent variables. The resulting models allow for quick
> domain adaptation and unknown relations, and avoid data sparsity caused by
> intervening words.
>  I show improvements over state-of-the-art systems as well as novel
> approaches to fully exploit the structure contained in the data. My method
> builds on existing triple stores and does not require any external
> knowledge bases, manual annotation, or pre-defined predicates or arguments.
>
> *Bio*:
> Dirk Hovy is a PhD candidate in Natural Language Processing at the
> University of Southern California (USC), and holds a Masters in
> linguistics. He is interested in data-driven models of meaning and
> understanding and has published on unsupervised learning, information
> extraction, word-sense disambiguation, and temporal relation classification
> (see <http://www.dirkhovy.com/portfolio/papers/index.php>).
> His thesis work is concerned with how computers can learn semantic types
> and relations from raw text, without recurrence to external resources.
> His other interests include baking, cooking, crossfit, and medieval art
> and literature.
>
>
>
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/nlp-lunch/attachments/20121112/75afa085/attachment.html>

From dyogatama at cs.cmu.edu  Tue Nov 27 18:18:14 2012
From: dyogatama at cs.cmu.edu (Dani Yogatama)
Date: Tue, 27 Nov 2012 18:18:14 -0500
Subject: [CL+NLP Lunch] CL+NLP Lunch Tuesday Dec 4 @ noon
Message-ID: <CAJPxrhwKZoUiwCkvEkvy1rv6k90O9UwkDs3-AnwYnPvMHbE+8A@mail.gmail.com>

Hi all,

Dirk Hovy's talk has been rescheduled for Tuesday December 4 at
noon. Details are included below.
Lunch will be provided.


Thanks,
Dani

P.S.: You may also be interested in Nathan Schneider's thesis proposal
tomorrow at 5pm (http://calendar.cs.cmu.edu/scsEvents/demo/8238.html).

===================================================
*CL+NLP Lunch* (http://www.cs.cmu.edu/~nlp-lunch/)
*Speaker*: Dirk Hovy, University of Southern California
*Date*: Tuesday, December 4, 2012
*Time*: 12:00 noon
*Venue*: GHC 6115

*Title*:
Learning Semantic Types and Relations from Syntactic Context

*Abstract*:
Natural Language Processing (NLP) is moving towards incorporating more
semantics into its applications, such as Machine Translation (MT) or
Question Answering (QA). Most semantic frameworks depend on predefined
"external" resources, such as knowledge bases or ontologies. This requires
a lot of manual effort, but even then it is impossible to build a complete
representation of the world. Instead, we would like to learn a sufficient
representation directly from data.

One way to encode meaning is through syntactic and semantic relations
between predicates and their arguments. Relations are thus at the core of
meaning and information. Recently, several approaches have collected large
corpora of syntactically related word chains (e.g., subject, verb, object).
However, these chains are extracted at the lexical level and do not
generalize well, so their use for semantic interpretation is limited. If we
could use these lexical chains as inputs to generalize beyond the word
level, we would be able to learn semantic relations and make use of these
existing resources.

In this talk, I will present a method to learn semantic types and relations
from raw text.
I construct unsupervised models on syntactic dependency arcs, using
potential types as latent variables. The resulting models allow for quick
domain adaptation and unknown relations, and avoid data sparsity caused by
intervening words.
I show improvements over state-of-the-art systems as well as novel
approaches to fully exploit the structure contained in the data. My method
builds on existing triple stores and does not require any external
knowledge bases, manual annotation, or pre-defined predicates or arguments.

*Bio*:
Dirk Hovy is a PhD candidate in Natural Language Processing at the
University of Southern California (USC), and holds a Masters in
linguistics. He is interested in data-driven models of meaning and
understanding and has published on unsupervised learning, information
extraction, word-sense disambiguation, and temporal relation classification
(see <http://www.dirkhovy.com/portfolio/papers/index.php>).
His thesis work is concerned with how computers can learn semantic types
and relations from raw text, without recurrence to external resources.
His other interests include baking, cooking, crossfit, and medieval art and
literature.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/nlp-lunch/attachments/20121127/dbf73afd/attachment.html>

From dyogatama at cs.cmu.edu  Tue Dec  4 11:27:58 2012
From: dyogatama at cs.cmu.edu (Dani Yogatama)
Date: Tue, 4 Dec 2012 11:27:58 -0500
Subject: [CL+NLP Lunch] CL+NLP Lunch Tuesday Dec 4 @ noon
In-Reply-To: <CAJPxrhwKZoUiwCkvEkvy1rv6k90O9UwkDs3-AnwYnPvMHbE+8A@mail.gmail.com>
References: <CAJPxrhwKZoUiwCkvEkvy1rv6k90O9UwkDs3-AnwYnPvMHbE+8A@mail.gmail.com>
Message-ID: <CAJPxrhzsnhqcnzdCNkVM9XS3+4mxFzhHq8XFZKY01h7UYe0fcw@mail.gmail.com>

Reminder: today

===================================================
> *CL+NLP Lunch* (http://www.cs.cmu.edu/~nlp-lunch/)
> *Speaker*: Dirk Hovy, University of Southern California
> *Date*: Tuesday, December 4, 2012
> *Time*: 12:00 noon
> *Venue*: GHC 6115
>
> *Title*:
> Learning Semantic Types and Relations from Syntactic Context
>
> *Abstract*:
> Natural Language Processing (NLP) is moving towards incorporating more
> semantics into its applications, such as Machine Translation (MT) or
> Question Answering (QA). Most semantic frameworks depend on predefined
> "external" resources, such as knowledge bases or ontologies. This requires
> a lot of manual effort, but even then it is impossible to build a complete
> representation of the world. Instead, we would like to learn a sufficient
> representation directly from data.
>
> One way to encode meaning is through syntactic and semantic relations
> between predicates and their arguments. Relations are thus at the core of
> meaning and information. Recently, several approaches have collected large
> corpora of syntactically related word chains (e.g., subject, verb, object).
> However, these chains are extracted at the lexical level and do not
> generalize well, so their use for semantic interpretation is limited. If we
> could use these lexical chains as inputs to generalize beyond the word
> level, we would be able to learn semantic relations and make use of these
> existing resources.
>
> In this talk, I will present a method to learn semantic types and
> relations from raw text.
> I construct unsupervised models on syntactic dependency arcs, using
> potential types as latent variables. The resulting models allow for quick
> domain adaptation and unknown relations, and avoid data sparsity caused by
> intervening words.
> I show improvements over state-of-the-art systems as well as novel
> approaches to fully exploit the structure contained in the data. My method
> builds on existing triple stores and does not require any external
> knowledge bases, manual annotation, or pre-defined predicates or arguments.
>
> *Bio*:
> Dirk Hovy is a PhD candidate in Natural Language Processing at the
> University of Southern California (USC), and holds a Masters in
> linguistics. He is interested in data-driven models of meaning and
> understanding and has published on unsupervised learning, information
> extraction, word-sense disambiguation, and temporal relation classification
> (see <http://www.dirkhovy.com/portfolio/papers/index.php>).
> His thesis work is concerned with how computers can learn semantic types
> and relations from raw text, without recurrence to external resources.
> His other interests include baking, cooking, crossfit, and medieval art
> and literature.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/nlp-lunch/attachments/20121204/9c7c6ea9/attachment.html>