Instance-Based Neural Dependency Parsing
AbstractInterpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled b...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2021-01-01
|
| Series: | Transactions of the Association for Computational Linguistics |
| Online Access: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00439/108864/Instance-Based-Neural-Dependency-Parsing |
| _version_ | 1818539221793636352 |
|---|---|
| author | Hiroki Ouchi Jun Suzuki Sosuke Kobayashi Sho Yokoi Tatsuki Kuribayashi Masashi Yoshikawa Kentaro Inui |
| author_facet | Hiroki Ouchi Jun Suzuki Sosuke Kobayashi Sho Yokoi Tatsuki Kuribayashi Masashi Yoshikawa Kentaro Inui |
| author_sort | Hiroki Ouchi |
| collection | DOAJ |
| description |
AbstractInterpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations. |
| first_indexed | 2024-12-11T21:39:11Z |
| format | Article |
| id | doaj.art-53a8dde4eecf4b1e97ab48158f11ca50 |
| institution | Directory Open Access Journal |
| issn | 2307-387X |
| language | English |
| last_indexed | 2024-12-11T21:39:11Z |
| publishDate | 2021-01-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Transactions of the Association for Computational Linguistics |
| spelling | doaj.art-53a8dde4eecf4b1e97ab48158f11ca502022-12-22T00:49:54ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2021-01-0191493150710.1162/tacl_a_00439Instance-Based Neural Dependency ParsingHiroki Ouchi0Jun Suzuki1Sosuke Kobayashi2Sho Yokoi3Tatsuki Kuribayashi4Masashi Yoshikawa5Kentaro Inui6NAIST, JapanTohoku University, JapanTohoku University, JapanTohoku University, JapanTohoku University, JapanTohoku University, JapanTohoku University, Japan AbstractInterpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00439/108864/Instance-Based-Neural-Dependency-Parsing |
| spellingShingle | Hiroki Ouchi Jun Suzuki Sosuke Kobayashi Sho Yokoi Tatsuki Kuribayashi Masashi Yoshikawa Kentaro Inui Instance-Based Neural Dependency Parsing Transactions of the Association for Computational Linguistics |
| title | Instance-Based Neural Dependency Parsing |
| title_full | Instance-Based Neural Dependency Parsing |
| title_fullStr | Instance-Based Neural Dependency Parsing |
| title_full_unstemmed | Instance-Based Neural Dependency Parsing |
| title_short | Instance-Based Neural Dependency Parsing |
| title_sort | instance based neural dependency parsing |
| url | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00439/108864/Instance-Based-Neural-Dependency-Parsing |
| work_keys_str_mv | AT hirokiouchi instancebasedneuraldependencyparsing AT junsuzuki instancebasedneuraldependencyparsing AT sosukekobayashi instancebasedneuraldependencyparsing AT shoyokoi instancebasedneuraldependencyparsing AT tatsukikuribayashi instancebasedneuraldependencyparsing AT masashiyoshikawa instancebasedneuraldependencyparsing AT kentaroinui instancebasedneuraldependencyparsing |