Frame-Semantic Parsing
Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets (i.e., content words and phrases) in their sentential contexts and predicts frame-seman...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
MIT Press
2014
|
| Online Access: | http://hdl.handle.net/1721.1/88418 https://orcid.org/0000-0003-2336-6235 |
| _version_ | 1826202062953644032 |
|---|---|
| author | Das, Dipanjan Chen, Desai Martins, André F. T. Schneider, Nathan Smith, Noah A. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Das, Dipanjan Chen, Desai Martins, André F. T. Schneider, Nathan Smith, Noah A. |
| author_sort | Das, Dipanjan |
| collection | MIT |
| description | Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets (i.e., content words and phrases) in their sentential contexts and predicts frame-semantic structures. Given a target in context, the first stage disambiguates it to a semantic frame. This model uses latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time. The second stage finds the target's locally expressed semantic arguments. At inference time, a fast exact dual decomposition algorithm collectively predicts all the arguments of a frame at once in order to respect declaratively stated linguistic constraints, resulting in qualitatively better structures than naïve local predictors. Both components are feature-based and discriminatively trained on a small set of annotated frame-semantic parses. On the SemEval 2007 benchmark data set, the approach, along with a heuristic identifier of frame-evoking targets, outperforms the prior state of the art by significant margins. Additionally, we present experiments on the much larger FrameNet 1.5 data set. We have released our frame-semantic parser as open-source software. |
| first_indexed | 2024-09-23T12:01:17Z |
| format | Article |
| id | mit-1721.1/88418 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:01:17Z |
| publishDate | 2014 |
| publisher | MIT Press |
| record_format | dspace |
| spelling | mit-1721.1/884182022-09-27T23:33:04Z Frame-Semantic Parsing Das, Dipanjan Chen, Desai Martins, André F. T. Schneider, Nathan Smith, Noah A. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Chen, Desai Frame semantics is a linguistic theory that has been instantiated for English in the FrameNet lexicon. We solve the problem of frame-semantic parsing using a two-stage statistical model that takes lexical targets (i.e., content words and phrases) in their sentential contexts and predicts frame-semantic structures. Given a target in context, the first stage disambiguates it to a semantic frame. This model uses latent variables and semi-supervised learning to improve frame disambiguation for targets unseen at training time. The second stage finds the target's locally expressed semantic arguments. At inference time, a fast exact dual decomposition algorithm collectively predicts all the arguments of a frame at once in order to respect declaratively stated linguistic constraints, resulting in qualitatively better structures than naïve local predictors. Both components are feature-based and discriminatively trained on a small set of annotated frame-semantic parses. On the SemEval 2007 benchmark data set, the approach, along with a heuristic identifier of frame-evoking targets, outperforms the prior state of the art by significant margins. Additionally, we present experiments on the much larger FrameNet 1.5 data set. We have released our frame-semantic parser as open-source software. United States. Defense Advanced Research Projects Agency (DARPA grant NBCH-1080004) National Science Foundation (U.S.) (NSF grant IIS-0836431) National Science Foundation (U.S.) (NSF grant IIS-0915187) Qatar National Research Fund (NPRP 08-485-1-083) 2014-07-17T13:28:15Z 2014-07-17T13:28:15Z 2014-03 2012-11 Article http://purl.org/eprint/type/JournalArticle 0891-2017 1530-9312 http://hdl.handle.net/1721.1/88418 Das, Dipanjan, Desai Chen, André F. T. Martins, Nathan Schneider, and Noah A. Smith. “Frame-Semantic Parsing.” Computational Linguistics 40, no. 1 (March 2014): 9–56. https://orcid.org/0000-0003-2336-6235 en_US http://dx.doi.org/10.1162/COLI_a_00163 Computational Linguistics Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf MIT Press MIT Press |
| spellingShingle | Das, Dipanjan Chen, Desai Martins, André F. T. Schneider, Nathan Smith, Noah A. Frame-Semantic Parsing |
| title | Frame-Semantic Parsing |
| title_full | Frame-Semantic Parsing |
| title_fullStr | Frame-Semantic Parsing |
| title_full_unstemmed | Frame-Semantic Parsing |
| title_short | Frame-Semantic Parsing |
| title_sort | frame semantic parsing |
| url | http://hdl.handle.net/1721.1/88418 https://orcid.org/0000-0003-2336-6235 |
| work_keys_str_mv | AT dasdipanjan framesemanticparsing AT chendesai framesemanticparsing AT martinsandreft framesemanticparsing AT schneidernathan framesemanticparsing AT smithnoaha framesemanticparsing |