An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
This addresses a specific challenge in computer-aided translation tools for translators, but it is incremental as it builds on existing neural network approaches with efficiency-focused strategies.
The paper tackles the problem of word-level autocompletion in computer-aided translation by proposing an energy-based model to better leverage source sentence information, achieving a 6.07% improvement over the previous state-of-the-art on four benchmarks.
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.