Unsupervised Learning of Morphological Forests
<jats:p> This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properti...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
MIT Press - Journals
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135066 |
| _version_ | 1811087306014064640 |
|---|---|
| author | Luo, Jiaming Narasimhan, Karthik 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 Luo, Jiaming Narasimhan, Karthik Barzilay, Regina |
| author_sort | Luo, Jiaming |
| collection | MIT |
| description | <jats:p> This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families, and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results. </jats:p> |
| first_indexed | 2024-09-23T13:43:59Z |
| format | Article |
| id | mit-1721.1/135066 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:43:59Z |
| publishDate | 2021 |
| publisher | MIT Press - Journals |
| record_format | dspace |
| spelling | mit-1721.1/1350662023-02-17T21:33:06Z Unsupervised Learning of Morphological Forests Luo, Jiaming Narasimhan, Karthik Barzilay, Regina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory <jats:p> This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families, and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results. </jats:p> 2021-10-27T20:10:34Z 2021-10-27T20:10:34Z 2017 2019-05-07T16:06:50Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/135066 en 10.1162/TACL_A_00066 Transactions of the Association for Computational Linguistics Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf MIT Press - Journals MIT Press |
| spellingShingle | Luo, Jiaming Narasimhan, Karthik Barzilay, Regina Unsupervised Learning of Morphological Forests |
| title | Unsupervised Learning of Morphological Forests |
| title_full | Unsupervised Learning of Morphological Forests |
| title_fullStr | Unsupervised Learning of Morphological Forests |
| title_full_unstemmed | Unsupervised Learning of Morphological Forests |
| title_short | Unsupervised Learning of Morphological Forests |
| title_sort | unsupervised learning of morphological forests |
| url | https://hdl.handle.net/1721.1/135066 |
| work_keys_str_mv | AT luojiaming unsupervisedlearningofmorphologicalforests AT narasimhankarthik unsupervisedlearningofmorphologicalforests AT barzilayregina unsupervisedlearningofmorphologicalforests |