Almost Free Semantic Draft for Neural Machine Translation
Translation quality can be improved by global information from the required target sentence because the decoder can understand both past and future information. However, the model needs additional cost to produce and consider such global information. In this work, to inject global information but also save cost, we present an efficient method to sample and consider a semantic draft as global information from semantic space for decoding with almost free of cost. Unlike other successful adaptations, we do not have to perform an EM-like process that repeatedly samples a possible semantic from the semantic space. Empirical experiments show that the presented method can achieve competitive performance in common language pairs with a clear advantage in inference efficiency. We will open all our source code on GitHub.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderMachine TranslationSentenceTranslationSimilar Papers 제목 키워드 기반
Self-Speculative Biased Decoding for Faster Re-Translation
Large language models achieve strong machine translation quality but incur high inference cost and latency, posing challenges for simultaneous translation. Re-translation provides a practical solution for off-the-shelf L…
Machine TranslationEnhanced Neural Machine Translation by Learning from Draft
Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left to right, without considering the right c…
Machine TranslationNMTTranslationSemantic Early-Stopping for Iterative LLM Agent Loops
Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iteration cap (max_iterations). This is a syntactic kill-switch: it is bli…
Question AnsweringTesting the Deliteralization Hypothesis in Human and Machine Translation
The recent shift from dedicated NMT systems to general-purpose LLMs has reshaped machine translation, with LLMs reported to produce more fluent, less literal output than their predecessors. We test whether this shift ext…
Machine TranslationMulti-Hop Transformer for Document-Level Machine Translation
Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of c…
Document Level Machine TranslationDocument TranslationMachine TranslationNMT+2