Low-Rank Tensors for Scoring Dependency Structures
Accurate scoring of syntactic structures such as head-modifier arcs in dependency parsing typically requires rich, high-dimensional feature representations. A small subset of such features is often selected manually. This is problematic when features lack clear linguistic meaning as in embeddings o...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computational Linguistics
2015
|
| Online Access: | http://hdl.handle.net/1721.1/99745 https://orcid.org/0000-0003-3121-0185 https://orcid.org/0000-0002-2921-8201 https://orcid.org/0000-0002-2199-0379 https://orcid.org/0000-0003-4644-3088 |
| _version_ | 1826211512818073600 |
|---|---|
| author | Lei, Tao Zhang, Yuan Barzilay, Regina Jaakkola, Tommi S. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Lei, Tao Zhang, Yuan Barzilay, Regina Jaakkola, Tommi S. |
| author_sort | Lei, Tao |
| collection | MIT |
| description | Accurate scoring of syntactic structures such as head-modifier arcs in dependency parsing typically requires rich, high-dimensional feature representations. A small subset of such features is often selected manually. This is problematic when features lack clear linguistic meaning as in embeddings or when the information is blended across features. In this paper, we use tensors to map high-dimensional feature vectors into low dimensional representations. We explicitly maintain the parameters as a low-rank tensor to obtain low dimensional representations of words in their syntactic roles, and to leverage modularity in the tensor for easy training with online algorithms. Our parser consistently outperforms the Turbo and MST parsers across 14 different languages. We also obtain the best published UAS results on 5 languages. |
| first_indexed | 2024-09-23T15:07:10Z |
| format | Article |
| id | mit-1721.1/99745 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:07:10Z |
| publishDate | 2015 |
| publisher | Association for Computational Linguistics |
| record_format | dspace |
| spelling | mit-1721.1/997452022-09-29T12:46:28Z Low-Rank Tensors for Scoring Dependency Structures Lei, Tao Zhang, Yuan Barzilay, Regina Jaakkola, Tommi S. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Lei, Tao Zhang, Yuan Barzilay, Regina Jaakkola, Tommi S. Accurate scoring of syntactic structures such as head-modifier arcs in dependency parsing typically requires rich, high-dimensional feature representations. A small subset of such features is often selected manually. This is problematic when features lack clear linguistic meaning as in embeddings or when the information is blended across features. In this paper, we use tensors to map high-dimensional feature vectors into low dimensional representations. We explicitly maintain the parameters as a low-rank tensor to obtain low dimensional representations of words in their syntactic roles, and to leverage modularity in the tensor for easy training with online algorithms. Our parser consistently outperforms the Turbo and MST parsers across 14 different languages. We also obtain the best published UAS results on 5 languages. United States. Multidisciplinary University Research Initiative (W911NF-10-1-0533) United States. Defense Advanced Research Projects Agency. Broad Operational Language Translation 2015-11-09T13:31:42Z 2015-11-09T13:31:42Z 2014-06 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/99745 Lei, Tao, Yuan Zhang, Regina Barzilay, and Tommi Jaakkola. "Low-Rank Tensors for Scoring Dependency Structures." 52nd Annual Meeting of the Association for Computational Linguistics (June 2014). https://orcid.org/0000-0003-3121-0185 https://orcid.org/0000-0002-2921-8201 https://orcid.org/0000-0002-2199-0379 https://orcid.org/0000-0003-4644-3088 en_US http://acl2014.org/acl2014/P14-1/index.html Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computational Linguistics MIT web domain |
| spellingShingle | Lei, Tao Zhang, Yuan Barzilay, Regina Jaakkola, Tommi S. Low-Rank Tensors for Scoring Dependency Structures |
| title | Low-Rank Tensors for Scoring Dependency Structures |
| title_full | Low-Rank Tensors for Scoring Dependency Structures |
| title_fullStr | Low-Rank Tensors for Scoring Dependency Structures |
| title_full_unstemmed | Low-Rank Tensors for Scoring Dependency Structures |
| title_short | Low-Rank Tensors for Scoring Dependency Structures |
| title_sort | low rank tensors for scoring dependency structures |
| url | http://hdl.handle.net/1721.1/99745 https://orcid.org/0000-0003-3121-0185 https://orcid.org/0000-0002-2921-8201 https://orcid.org/0000-0002-2199-0379 https://orcid.org/0000-0003-4644-3088 |
| work_keys_str_mv | AT leitao lowranktensorsforscoringdependencystructures AT zhangyuan lowranktensorsforscoringdependencystructures AT barzilayregina lowranktensorsforscoringdependencystructures AT jaakkolatommis lowranktensorsforscoringdependencystructures |