Learning to Automatically Solve Algebra Word Problems
We present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem te...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computational Linguistics
2015
|
| Online Access: | http://hdl.handle.net/1721.1/99744 https://orcid.org/0000-0002-9254-8422 https://orcid.org/0000-0002-2921-8201 |
| _version_ | 1811091146735091712 |
|---|---|
| author | Kushman, Nate Artzi, Yoav Zettlemoyer, Luke Barzilay, Regina |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Kushman, Nate Artzi, Yoav Zettlemoyer, Luke Barzilay, Regina |
| author_sort | Kushman, Nate |
| collection | MIT |
| description | We present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem text. The learning algorithm uses varied supervision, including either full equations or just the final answers. We evaluate performance on a newly gathered corpus of algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset. This is, to our knowledge, the first learning result for this task. |
| first_indexed | 2024-09-23T14:57:44Z |
| format | Article |
| id | mit-1721.1/99744 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:57:44Z |
| publishDate | 2015 |
| publisher | Association for Computational Linguistics |
| record_format | dspace |
| spelling | mit-1721.1/997442022-09-29T11:42:58Z Learning to Automatically Solve Algebra Word Problems Kushman, Nate Artzi, Yoav Zettlemoyer, Luke Barzilay, Regina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Kushman, Nate Barzilay, Regina We present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem text. The learning algorithm uses varied supervision, including either full equations or just the final answers. We evaluate performance on a newly gathered corpus of algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset. This is, to our knowledge, the first learning result for this task. Battelle Memorial Institute (PO 300662) National Science Foundation (U.S.) (Grant IIS-0835652) 2015-11-09T13:22:15Z 2015-11-09T13:22:15Z 2014-06 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/99744 Kushman, Nate, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. "Learning to Automatically Solve Algebra Word Problems." 52nd Annual Meeting of the Association for Computational Linguistics (June 2014). https://orcid.org/0000-0002-9254-8422 https://orcid.org/0000-0002-2921-8201 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 | Kushman, Nate Artzi, Yoav Zettlemoyer, Luke Barzilay, Regina Learning to Automatically Solve Algebra Word Problems |
| title | Learning to Automatically Solve Algebra Word Problems |
| title_full | Learning to Automatically Solve Algebra Word Problems |
| title_fullStr | Learning to Automatically Solve Algebra Word Problems |
| title_full_unstemmed | Learning to Automatically Solve Algebra Word Problems |
| title_short | Learning to Automatically Solve Algebra Word Problems |
| title_sort | learning to automatically solve algebra word problems |
| url | http://hdl.handle.net/1721.1/99744 https://orcid.org/0000-0002-9254-8422 https://orcid.org/0000-0002-2921-8201 |
| work_keys_str_mv | AT kushmannate learningtoautomaticallysolvealgebrawordproblems AT artziyoav learningtoautomaticallysolvealgebrawordproblems AT zettlemoyerluke learningtoautomaticallysolvealgebrawordproblems AT barzilayregina learningtoautomaticallysolvealgebrawordproblems |