Learning linear transformations between counting-based and prediction-based word embeddings.
Despite the growing interest in prediction-based word embedding learning methods, it remains unclear as to how the vector spaces learnt by the prediction-based methods differ from that of the counting-based methods, or whether one can be transformed into the other. To study the relationship between...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2017-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC5604957?pdf=render |
| _version_ | 1818000462862876672 |
|---|---|
| author | Danushka Bollegala Kohei Hayashi Ken-Ichi Kawarabayashi |
| author_facet | Danushka Bollegala Kohei Hayashi Ken-Ichi Kawarabayashi |
| author_sort | Danushka Bollegala |
| collection | DOAJ |
| description | Despite the growing interest in prediction-based word embedding learning methods, it remains unclear as to how the vector spaces learnt by the prediction-based methods differ from that of the counting-based methods, or whether one can be transformed into the other. To study the relationship between counting-based and prediction-based embeddings, we propose a method for learning a linear transformation between two given sets of word embeddings. Our proposal contributes to the word embedding learning research in three ways: (a) we propose an efficient method to learn a linear transformation between two sets of word embeddings, (b) using the transformation learnt in (a), we empirically show that it is possible to predict distributed word embeddings for novel unseen words, and |
| first_indexed | 2024-04-14T03:22:01Z |
| format | Article |
| id | doaj.art-9eae8121926f48c1836a5dbee3504e3a |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-14T03:22:01Z |
| publishDate | 2017-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-9eae8121926f48c1836a5dbee3504e3a2022-12-22T02:15:17ZengPublic Library of Science (PLoS)PLoS ONE1932-62032017-01-01129e018454410.1371/journal.pone.0184544Learning linear transformations between counting-based and prediction-based word embeddings.Danushka BollegalaKohei HayashiKen-Ichi KawarabayashiDespite the growing interest in prediction-based word embedding learning methods, it remains unclear as to how the vector spaces learnt by the prediction-based methods differ from that of the counting-based methods, or whether one can be transformed into the other. To study the relationship between counting-based and prediction-based embeddings, we propose a method for learning a linear transformation between two given sets of word embeddings. Our proposal contributes to the word embedding learning research in three ways: (a) we propose an efficient method to learn a linear transformation between two sets of word embeddings, (b) using the transformation learnt in (a), we empirically show that it is possible to predict distributed word embeddings for novel unseen words, andhttp://europepmc.org/articles/PMC5604957?pdf=render |
| spellingShingle | Danushka Bollegala Kohei Hayashi Ken-Ichi Kawarabayashi Learning linear transformations between counting-based and prediction-based word embeddings. PLoS ONE |
| title | Learning linear transformations between counting-based and prediction-based word embeddings. |
| title_full | Learning linear transformations between counting-based and prediction-based word embeddings. |
| title_fullStr | Learning linear transformations between counting-based and prediction-based word embeddings. |
| title_full_unstemmed | Learning linear transformations between counting-based and prediction-based word embeddings. |
| title_short | Learning linear transformations between counting-based and prediction-based word embeddings. |
| title_sort | learning linear transformations between counting based and prediction based word embeddings |
| url | http://europepmc.org/articles/PMC5604957?pdf=render |
| work_keys_str_mv | AT danushkabollegala learninglineartransformationsbetweencountingbasedandpredictionbasedwordembeddings AT koheihayashi learninglineartransformationsbetweencountingbasedandpredictionbasedwordembeddings AT kenichikawarabayashi learninglineartransformationsbetweencountingbasedandpredictionbasedwordembeddings |