Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913367810113536 |
|---|---|
| author | Tang, Chenming Wang, Zhixiang Wu, Yunfang |
| author_facet | Tang, Chenming Wang, Zhixiang Wu, Yunfang |
| contents | In-context learning (ICL) is the trending prompting strategy in the era of large language models (LLMs), where a few examples are demonstrated to evoke LLMs' power for a given task. How to select informative examples remains an open issue. Previous works on in-context example selection for machine translation (MT) focus on superficial word-level features while ignoring deep syntax-level knowledge. In this paper, we propose a syntax-based in-context example selection method for MT, by computing the syntactic similarity between dependency trees using Polynomial Distance. In addition, we propose an ensemble strategy combining examples selected by both word-level and syntax-level criteria. Experimental results between English and 6 common languages indicate that syntax can effectively enhancing ICL for MT, obtaining the highest COMET scores on 11 out of 12 translation directions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19285 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation Tang, Chenming Wang, Zhixiang Wu, Yunfang Computation and Language In-context learning (ICL) is the trending prompting strategy in the era of large language models (LLMs), where a few examples are demonstrated to evoke LLMs' power for a given task. How to select informative examples remains an open issue. Previous works on in-context example selection for machine translation (MT) focus on superficial word-level features while ignoring deep syntax-level knowledge. In this paper, we propose a syntax-based in-context example selection method for MT, by computing the syntactic similarity between dependency trees using Polynomial Distance. In addition, we propose an ensemble strategy combining examples selected by both word-level and syntax-level criteria. Experimental results between English and 6 common languages indicate that syntax can effectively enhancing ICL for MT, obtaining the highest COMET scores on 11 out of 12 translation directions. |
| title | Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.19285 |