Incremental Segmentation and Decoding Strategies for Simultaneous Translation
نویسندگان
چکیده
Simultaneous translation is the challenging task of listening to source language speech, and at the same time, producing target language speech. Human interpreters achieve this task routinely and effortlessly, using different strategies in order to minimize the latency in producing target language. Toward modeling the human interpretation process, we propose a novel input segmentation method using the phrase alignment structure of the language pair. We compare and contrast three incremental decoding and two different input segmentation strategies, including our proposed method, for simultaneous translation. We present accuracy and latency tradeoffs for each of the decoding strategies when applied to audio lectures from the TED collection.
منابع مشابه
Incremental Segmentation and Decoding Strategies for Simultaneous Translation
Simultaneous translation is the challenging task of listening to source language speech, and at the same time, producing target language speech. Human interpreters achieve this task routinely and effortlessly, using different strategies in order to minimize the latency in producing target language. Toward modeling the human interpretation process, we propose a novel input segmentation method us...
متن کاملCan neural machine translation do simultaneous translation?
We investigate the potential of attention-based neural machine translation in simultaneous translation. We introduce a novel decoding algorithm, called simultaneous greedy decoding, that allows an existing neural machine translation model to begin translating before a full source sentence is received. This approach is unique from previous works on simultaneous translation in that segmentation a...
متن کاملIncremental Decoding for Phrase-Based Statistical Machine Translation
In this paper we focus on the incremental decoding for a statistical phrase-based machine translation system. In incremental decoding, translations are generated incrementally for every word typed by a user, instead of waiting for the entire sentence as input. We introduce a novel modification to the beam-search decoding algorithm for phrase-based MT to address this issue, aimed at efficient co...
متن کاملOptimizing Segmentation Strategies for Simultaneous Speech Translation
In this paper, we propose new algorithms for learning segmentation strategies for simultaneous speech translation. In contrast to previously proposed heuristic methods, our method finds a segmentation that directly maximizes the performance of the machine translation system. We describe two methods based on greedy search and dynamic programming that search for the optimal segmentation strategy....
متن کاملAn Exploration of Segmentation Strategies in Stream Decoding
In this paper we explore segmentation strategies for the stream decoder a method for decoding from a continuous stream of input tokens, rather than the traditional method of decoding from sentence segmented text. The behavior of the decoder is analyzed and modifications to the decoding algorithm are proposed to improve its performance. The experimental results show our proposed decoding strateg...
متن کامل