Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929533514416128 |
|---|---|
| author | Qian, Shenbin Orăsan, Constantin Kanojia, Diptesh Carmo, Félix do |
| author_facet | Qian, Shenbin Orăsan, Constantin Kanojia, Diptesh Carmo, Félix do |
| contents | This paper investigates whether large language models (LLMs) are state-of-the-art quality estimators for machine translation of user-generated content (UGC) that contains emotional expressions, without the use of reference translations. To achieve this, we employ an existing emotion-related dataset with human-annotated errors and calculate quality evaluation scores based on the Multi-dimensional Quality Metrics. We compare the accuracy of several LLMs with that of our fine-tuned baseline models, under in-context learning and parameter-efficient fine-tuning (PEFT) scenarios. We find that PEFT of LLMs leads to better performance in score prediction with human interpretable explanations than fine-tuned models. However, a manual analysis of LLM outputs reveals that they still have problems such as refusal to reply to a prompt and unstable output while evaluating machine translation of UGC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06338 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content? Qian, Shenbin Orăsan, Constantin Kanojia, Diptesh Carmo, Félix do Computation and Language This paper investigates whether large language models (LLMs) are state-of-the-art quality estimators for machine translation of user-generated content (UGC) that contains emotional expressions, without the use of reference translations. To achieve this, we employ an existing emotion-related dataset with human-annotated errors and calculate quality evaluation scores based on the Multi-dimensional Quality Metrics. We compare the accuracy of several LLMs with that of our fine-tuned baseline models, under in-context learning and parameter-efficient fine-tuning (PEFT) scenarios. We find that PEFT of LLMs leads to better performance in score prediction with human interpretable explanations than fine-tuned models. However, a manual analysis of LLM outputs reveals that they still have problems such as refusal to reply to a prompt and unstable output while evaluating machine translation of UGC. |
| title | Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.06338 |