Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.20083 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916338878906368 |
|---|---|
| author | Yang, Cheng Huang, Guoping Yu, Mo Zhang, Zhirui Li, Siheng Yang, Mingming Shi, Shuming Yang, Yujiu Liu, Lemao |
| author_facet | Yang, Cheng Huang, Guoping Yu, Mo Zhang, Zhirui Li, Siheng Yang, Mingming Shi, Shuming Yang, Yujiu Liu, Lemao |
| contents | Word-level AutoCompletion(WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i.e., the candidate target word is treated as a label). Since the context hidden vector itself does not take the label into account and it is projected to the label through a linear classifier, the model can not sufficiently leverage valuable information from the source sentence as verified in our experiments, which eventually hinders its overall performance. To alleviate this issue, this work proposes an energy-based model for WLAC, which enables the context hidden vector to capture crucial information from the source sentence. Unfortunately, training and inference suffer from efficiency and effectiveness challenges, thereby we employ three simple yet effective strategies to put our model into practice. Experiments on four standard benchmarks demonstrate that our reranking-based approach achieves substantial improvements (about 6.07%) over the previous state-of-the-art model. Further analyses show that each strategy of our approach contributes to the final performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20083 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation Yang, Cheng Huang, Guoping Yu, Mo Zhang, Zhirui Li, Siheng Yang, Mingming Shi, Shuming Yang, Yujiu Liu, Lemao Computation and Language Word-level AutoCompletion(WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i.e., the candidate target word is treated as a label). Since the context hidden vector itself does not take the label into account and it is projected to the label through a linear classifier, the model can not sufficiently leverage valuable information from the source sentence as verified in our experiments, which eventually hinders its overall performance. To alleviate this issue, this work proposes an energy-based model for WLAC, which enables the context hidden vector to capture crucial information from the source sentence. Unfortunately, training and inference suffer from efficiency and effectiveness challenges, thereby we employ three simple yet effective strategies to put our model into practice. Experiments on four standard benchmarks demonstrate that our reranking-based approach achieves substantial improvements (about 6.07%) over the previous state-of-the-art model. Further analyses show that each strategy of our approach contributes to the final performance. |
| title | An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.20083 |