How Lexical is Bilingual Lexicon Induction?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909162053566464 |
|---|---|
| author | Kohli, Harsh Feng, Helian Dronen, Nicholas McCarter, Calvin Moeini, Sina Kebarighotbi, Ali |
| author_facet | Kohli, Harsh Feng, Helian Dronen, Nicholas McCarter, Calvin Moeini, Sina Kebarighotbi, Ali |
| contents | In contemporary machine learning approaches to bilingual lexicon induction (BLI), a model learns a mapping between the embedding spaces of a language pair. Recently, retrieve-and-rank approach to BLI has achieved state of the art results on the task. However, the problem remains challenging in low-resource settings, due to the paucity of data. The task is complicated by factors such as lexical variation across languages. We argue that the incorporation of additional lexical information into the recent retrieve-and-rank approach should improve lexicon induction. We demonstrate the efficacy of our proposed approach on XLING, improving over the previous state of the art by an average of 2\% across all language pairs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04221 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How Lexical is Bilingual Lexicon Induction? Kohli, Harsh Feng, Helian Dronen, Nicholas McCarter, Calvin Moeini, Sina Kebarighotbi, Ali Computation and Language In contemporary machine learning approaches to bilingual lexicon induction (BLI), a model learns a mapping between the embedding spaces of a language pair. Recently, retrieve-and-rank approach to BLI has achieved state of the art results on the task. However, the problem remains challenging in low-resource settings, due to the paucity of data. The task is complicated by factors such as lexical variation across languages. We argue that the incorporation of additional lexical information into the recent retrieve-and-rank approach should improve lexicon induction. We demonstrate the efficacy of our proposed approach on XLING, improving over the previous state of the art by an average of 2\% across all language pairs. |
| title | How Lexical is Bilingual Lexicon Induction? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.04221 |