Learning Lexical Subspaces in a Distributional Vector Space
In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relation should hold. Our fra...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2020-07-01
|
| Series: | Transactions of the Association for Computational Linguistics |
| Online Access: | https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00316 |
| _version_ | 1818001008048996352 |
|---|---|
| author | Arora, Kushal Chakraborty, Aishik Cheung, Jackie C. K. |
| author_facet | Arora, Kushal Chakraborty, Aishik Cheung, Jackie C. K. |
| author_sort | Arora, Kushal |
| collection | DOAJ |
| description | In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relation should hold. Our framework can handle symmetric attract and repel relations (e.g., synonymy and antonymy, respectively), as well as asymmetric relations (e.g., hypernymy and meronomy). In a suite of intrinsic benchmarks, we show that our model outperforms previous approaches on relatedness tasks and on hypernymy classification and detection, while being competitive on word similarity tasks. It also outperforms previous systems on extrinsic classification tasks that benefit from exploiting lexical relational cues. We perform a series of analyses to understand the behaviors of our model. 1 Code available at https://github.com/aishikchakraborty/LexSub . |
| first_indexed | 2024-04-14T03:28:48Z |
| format | Article |
| id | doaj.art-2709f451114b4a36b52b0b406310f409 |
| institution | Directory Open Access Journal |
| issn | 2307-387X |
| language | English |
| last_indexed | 2024-04-14T03:28:48Z |
| publishDate | 2020-07-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Transactions of the Association for Computational Linguistics |
| spelling | doaj.art-2709f451114b4a36b52b0b406310f4092022-12-22T02:15:02ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2020-07-01831132910.1162/tacl_a_00316Learning Lexical Subspaces in a Distributional Vector SpaceArora, KushalChakraborty, AishikCheung, Jackie C. K.In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relation should hold. Our framework can handle symmetric attract and repel relations (e.g., synonymy and antonymy, respectively), as well as asymmetric relations (e.g., hypernymy and meronomy). In a suite of intrinsic benchmarks, we show that our model outperforms previous approaches on relatedness tasks and on hypernymy classification and detection, while being competitive on word similarity tasks. It also outperforms previous systems on extrinsic classification tasks that benefit from exploiting lexical relational cues. We perform a series of analyses to understand the behaviors of our model. 1 Code available at https://github.com/aishikchakraborty/LexSub .https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00316 |
| spellingShingle | Arora, Kushal Chakraborty, Aishik Cheung, Jackie C. K. Learning Lexical Subspaces in a Distributional Vector Space Transactions of the Association for Computational Linguistics |
| title | Learning Lexical Subspaces in a Distributional Vector Space |
| title_full | Learning Lexical Subspaces in a Distributional Vector Space |
| title_fullStr | Learning Lexical Subspaces in a Distributional Vector Space |
| title_full_unstemmed | Learning Lexical Subspaces in a Distributional Vector Space |
| title_short | Learning Lexical Subspaces in a Distributional Vector Space |
| title_sort | learning lexical subspaces in a distributional vector space |
| url | https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00316 |
| work_keys_str_mv | AT arorakushal learninglexicalsubspacesinadistributionalvectorspace AT chakrabortyaishik learninglexicalsubspacesinadistributionalvectorspace AT cheungjackieck learninglexicalsubspacesinadistributionalvectorspace |