Difference between revisions of "Fall 2022 Schedule"
CompSemUser (talk | contribs) |
CompSemUser (talk | contribs) |
||
Line 35: | Line 35: | ||
* Assisted interviewing: DJ, Abe | * Assisted interviewing: DJ, Abe | ||
* THYME: | * THYME: | ||
− | * UMR: | + | * UMR: Martha and Jim |
|- style="border-top: 2px solid DarkGray;" | |- style="border-top: 2px solid DarkGray;" | ||
− | | 21.09.22 || | + | | 21.09.22 || lunch at the Taj |
|- style="border-top: 2px solid DarkGray;" | |- style="border-top: 2px solid DarkGray;" | ||
| 28.09.22 || James Pustejovsky | | 28.09.22 || James Pustejovsky | ||
+ | |||
+ | Dense Paraphrasing for Textual Enrichment: Question Answering and Inference | ||
+ | |||
+ | Abstract: Much of the current computational work on inference in NLP can be associated with one of two techniques: the first focuses on a specific notion of text-based question answering (QA), using large pre-trained language models (LLMs). To examine specific linguistic properties present in the model, « probing tasks » (diagnostic classifiers) have been developed to test capabilities that the LLM demonstrates on interpretable semantic inferencing tasks, such as age and object comparisons, hypernym conjunction, antonym negation, and others. The second is Knowledge Graph-based inference and QA, where triples are mined from Wikipedia, ConceptNet, WikiData, and other non-corpus resources, and then used for answering questions involving multiple components of the KG (multi-hop QA). While quite impressive with benchmarked metrics in QA, both techniques are completely confused by (a) syntactically missing semantic content, and (b) the semantics accompanying the consequences of events and actions in narratives. | ||
+ | In this talk, I discuss a model we have developed to enrich the surface form of texts, using type-based semantic operations to « textually expose » the deeper meaning of the corpus that was used to make the original embeddings in the language model. This model, Dense Paraphrasing, is a linguistically-motivated, textual enrichment strategy, that textualizes the compositional operations inherent in a semantic model, such as Generative Lexicon Theory or CCG. This involves broadly three kinds of interpretive processes: (i) recognizing the diverse variability in linguistic forms that can be associated with the same underlying semantic representation (paraphrases); (ii) identifying semantic factors or variables that accompany or are presupposed by the lexical semantics of the words present in the text, through dropped, hidden or shadow arguments; and (iii) interpreting or computing the dynamic consequences of actions and events in the text. After performing these textual enrichment algorithms, we fine-tune the LLM which allows more robust inference and QA task performance. | ||
+ | |||
+ | James Pustejovsky, Professor | ||
+ | TJX Feldberg Chair in Computer Science | ||
+ | Department of Computer Science | ||
+ | Chair of CL MS Program | ||
+ | Chair of Linguistics Program | ||
+ | |||
|- style="border-top: 2px solid DarkGray;" | |- style="border-top: 2px solid DarkGray;" | ||
| 05.10.22 || Martha, COLING keynote // Daniel poster presentation dry run | | 05.10.22 || Martha, COLING keynote // Daniel poster presentation dry run |
Revision as of 18:38, 27 September 2022
Location: Hybrid - Buchanan 126, and the zoom link below
Time: Wednesdays at 10:30am, Mountain Time
Zoom link: https://cuboulder.zoom.us/j/97014876908
Date | Title |
---|---|
24.08.22 | Planning, introductions, welcome! |
31.08.22 | PhD students present! Ongoing projects and opportunities
|
07.09.22 | PhD students continue to present!
20 minutes per project
|
14.09.22 | And more presentations from our fabulous students and colleagues!
|
21.09.22 | lunch at the Taj |
28.09.22 | James Pustejovsky
Dense Paraphrasing for Textual Enrichment: Question Answering and Inference Abstract: Much of the current computational work on inference in NLP can be associated with one of two techniques: the first focuses on a specific notion of text-based question answering (QA), using large pre-trained language models (LLMs). To examine specific linguistic properties present in the model, « probing tasks » (diagnostic classifiers) have been developed to test capabilities that the LLM demonstrates on interpretable semantic inferencing tasks, such as age and object comparisons, hypernym conjunction, antonym negation, and others. The second is Knowledge Graph-based inference and QA, where triples are mined from Wikipedia, ConceptNet, WikiData, and other non-corpus resources, and then used for answering questions involving multiple components of the KG (multi-hop QA). While quite impressive with benchmarked metrics in QA, both techniques are completely confused by (a) syntactically missing semantic content, and (b) the semantics accompanying the consequences of events and actions in narratives. In this talk, I discuss a model we have developed to enrich the surface form of texts, using type-based semantic operations to « textually expose » the deeper meaning of the corpus that was used to make the original embeddings in the language model. This model, Dense Paraphrasing, is a linguistically-motivated, textual enrichment strategy, that textualizes the compositional operations inherent in a semantic model, such as Generative Lexicon Theory or CCG. This involves broadly three kinds of interpretive processes: (i) recognizing the diverse variability in linguistic forms that can be associated with the same underlying semantic representation (paraphrases); (ii) identifying semantic factors or variables that accompany or are presupposed by the lexical semantics of the words present in the text, through dropped, hidden or shadow arguments; and (iii) interpreting or computing the dynamic consequences of actions and events in the text. After performing these textual enrichment algorithms, we fine-tune the LLM which allows more robust inference and QA task performance. James Pustejovsky, Professor TJX Feldberg Chair in Computer Science Department of Computer Science Chair of CL MS Program Chair of Linguistics Program |
05.10.22 | Martha, COLING keynote // Daniel poster presentation dry run |
12.10.22 | COLING / paper review |
19.10.22 | CLASIC Open House |
21.10.22 | FRIDAY Carolyn Rose: Dialogue and Tutoring systems (ICS talk, noon) |
26.10.22 | EMNLP practice talks? |
28.10.22 | FRIDAY Barbara diEugenio (ICS talk, noon) |
31.10.22 | MONDAY Nathan Schneider (Linguistics talk) |
02.11.22 | Ananya Ganesh, prelim |
09.11.22 | Abteen Ebrahimi, prelim |
16.11.22 | Maggie Perkoff, prelim |
23.11.22 | *** No meeting - fall break *** |
30.11.22 | Kris Stenzel? or EMNLP practice talks? |
07.12.22 | Mans: 21st century tools for indigenous languages? |
Past Schedules
- Spring 2022 Schedule
- Fall 2021 Schedule
- Spring 2021 Schedule
- Fall 2020 Schedule
- Spring 2020 Schedule
- Fall 2019 Schedule
- Spring 2019 Schedule
- Fall 2018 Schedule
- Summer 2018 Schedule
- Spring 2018 Schedule
- Fall 2017 Schedule
- Summer 2017 Schedule
- Spring 2017 Schedule
- Fall 2016 Schedule
- Spring 2016 Schedule
- Fall 2015 Schedule
- Spring 2015 Schedule
- Fall 2014 Schedule
- Spring 2014 Schedule
- Fall 2013 Schedule
- Summer 2013 Schedule
- Spring 2013 Schedule
- Fall 2012 Schedule
- Spring 2012 Schedule
- Fall 2011 Schedule
- Summer 2011 Schedule
- Spring 2011 Schedule
- Fall 2010 Schedule
- Summer 2010 Schedule
- Spring 2010 Schedule
- Fall 2009 Schedule
- Summer 2009 Schedule
- Spring 2009 Schedule
- Fall 2008 Schedule
- Summer 2008 Schedule