Universal Discourse Representation Structure Parsing
AbstractWe consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce 𝕌niversal Discourse Repr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2021-07-01
|
| Series: | Computational Linguistics |
| Online Access: | https://direct.mit.edu/coli/article/47/2/445/98515/Universal-Discourse-Representation-Structure |
| _version_ | 1811255349293875200 |
|---|---|
| author | Jiangming Liu Shay B. Cohen Mirella Lapata Johan Bos |
| author_facet | Jiangming Liu Shay B. Cohen Mirella Lapata Johan Bos |
| author_sort | Jiangming Liu |
| collection | DOAJ |
| description |
AbstractWe consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce 𝕌niversal Discourse Representation Theory (𝕌DRT), a variant of DRT that explicitly anchors semantic representations to tokens in the linguistic input. We develop a semantic parsing framework based on the Transformer architecture and utilize it to obtain semantic resources in multiple languages following two learning schemes. The many-to-one approach translates non-English text to English, and then runs a relatively accurate English parser on the translated text, while the one-to-many approach translates gold standard English to non-English text and trains multiple parsers (one per language) on the translations. Experimental results on the Parallel Meaning Bank show that our proposal outperforms strong baselines by a wide margin and can be used to construct (silver-standard) meaning banks for 99 languages. |
| first_indexed | 2024-04-12T17:23:26Z |
| format | Article |
| id | doaj.art-55812fe849884f5ea2eab9311a7afca4 |
| institution | Directory Open Access Journal |
| issn | 0891-2017 1530-9312 |
| language | English |
| last_indexed | 2024-04-12T17:23:26Z |
| publishDate | 2021-07-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Computational Linguistics |
| spelling | doaj.art-55812fe849884f5ea2eab9311a7afca42022-12-22T03:23:24ZengThe MIT PressComputational Linguistics0891-20171530-93122021-07-0147244547610.1162/coli_a_00406Universal Discourse Representation Structure ParsingJiangming Liu0Shay B. Cohen1Mirella Lapata2Johan Bos3School of Informatics, University of Edinburgh. jiangming.liu@ed.ac.ukSchool of Informatics, University of Edinburgh. scohen@inf.ed.ac.ukSchool of Informatics, University of Edinburgh. mlap@inf.ed.ac.ukCenter for Language and Cognition, University of Groningen. johan.bos@rug.nl AbstractWe consider the task of crosslingual semantic parsing in the style of Discourse Representation Theory (DRT) where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide learning in other languages. We introduce 𝕌niversal Discourse Representation Theory (𝕌DRT), a variant of DRT that explicitly anchors semantic representations to tokens in the linguistic input. We develop a semantic parsing framework based on the Transformer architecture and utilize it to obtain semantic resources in multiple languages following two learning schemes. The many-to-one approach translates non-English text to English, and then runs a relatively accurate English parser on the translated text, while the one-to-many approach translates gold standard English to non-English text and trains multiple parsers (one per language) on the translations. Experimental results on the Parallel Meaning Bank show that our proposal outperforms strong baselines by a wide margin and can be used to construct (silver-standard) meaning banks for 99 languages.https://direct.mit.edu/coli/article/47/2/445/98515/Universal-Discourse-Representation-Structure |
| spellingShingle | Jiangming Liu Shay B. Cohen Mirella Lapata Johan Bos Universal Discourse Representation Structure Parsing Computational Linguistics |
| title | Universal Discourse Representation Structure Parsing |
| title_full | Universal Discourse Representation Structure Parsing |
| title_fullStr | Universal Discourse Representation Structure Parsing |
| title_full_unstemmed | Universal Discourse Representation Structure Parsing |
| title_short | Universal Discourse Representation Structure Parsing |
| title_sort | universal discourse representation structure parsing |
| url | https://direct.mit.edu/coli/article/47/2/445/98515/Universal-Discourse-Representation-Structure |
| work_keys_str_mv | AT jiangmingliu universaldiscourserepresentationstructureparsing AT shaybcohen universaldiscourserepresentationstructureparsing AT mirellalapata universaldiscourserepresentationstructureparsing AT johanbos universaldiscourserepresentationstructureparsing |