An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation

Cheng Yang, Guoping Huang, Mo Yu, Zhirui Zhang, Siheng Li, Mingming Yang, Shuming Shi, Yujiu Yang, Lemao Liu


Abstract
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 cannot 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, therefore 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.1
Anthology ID:
2024.tacl-1.8
Volume:
Transactions of the Association for Computational Linguistics, Volume 12
Month:
Year:
2024
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
137–156
Language:
URL:
https://aclanthology.org/2024.tacl-1.8
DOI:
10.1162/tacl_a_00637
Bibkey:
Cite (ACL):
Cheng Yang, Guoping Huang, Mo Yu, Zhirui Zhang, Siheng Li, Mingming Yang, Shuming Shi, Yujiu Yang, and Lemao Liu. 2024. An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation. Transactions of the Association for Computational Linguistics, 12:137–156.
Cite (Informal):
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation (Yang et al., TACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.tacl-1.8.pdf