PWESuite: Phonetic Word Embeddings and Tasks They Facilitate
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909150323146752 |
|---|---|
| author | Zouhar, Vilém Chang, Kalvin Cui, Chenxuan Carlson, Nathaniel Robinson, Nathaniel Sachan, Mrinmaya Mortensen, David |
| author_facet | Zouhar, Vilém Chang, Kalvin Cui, Chenxuan Carlson, Nathaniel Robinson, Nathaniel Sachan, Mrinmaya Mortensen, David |
| contents | Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop three methods that use articulatory features to build phonetically informed word embeddings. To address the inconsistent evaluation of existing phonetic word embedding methods, we also contribute a task suite to fairly evaluate past, current, and future methods. We evaluate both (1) intrinsic aspects of phonetic word embeddings, such as word retrieval and correlation with sound similarity, and (2) extrinsic performance on tasks such as rhyme and cognate detection and sound analogies. We hope our task suite will promote reproducibility and inspire future phonetic embedding research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_02541 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | PWESuite: Phonetic Word Embeddings and Tasks They Facilitate Zouhar, Vilém Chang, Kalvin Cui, Chenxuan Carlson, Nathaniel Robinson, Nathaniel Sachan, Mrinmaya Mortensen, David Computation and Language Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop three methods that use articulatory features to build phonetically informed word embeddings. To address the inconsistent evaluation of existing phonetic word embedding methods, we also contribute a task suite to fairly evaluate past, current, and future methods. We evaluate both (1) intrinsic aspects of phonetic word embeddings, such as word retrieval and correlation with sound similarity, and (2) extrinsic performance on tasks such as rhyme and cognate detection and sound analogies. We hope our task suite will promote reproducibility and inspire future phonetic embedding research. |
| title | PWESuite: Phonetic Word Embeddings and Tasks They Facilitate |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2304.02541 |