NAIST’s Machine Translation Systems for IWSLT 2020 Conversational Speech Translation Task

Proceedings of the 17th International Conference on Spoken Language Translation (IWSLT), pages 172–177 July 9-10, 2020. c⃝2020 Association for Computational Linguistics https://doi.org/10.18653/v1/P17 172 NAIST’s Machine Translation Systems for IWSLT 2020 Conversational Speech Translation Task Ryo Fukuda1, Katsuhito Sudoh1, Satoshi Nakamura1,2 1Nara Institute of Science and Technology 2AIP Center, RIKEN, Japan {fukuda.ryo.fo3, sudoh, s-nakamura}@is.naist.jp Abstract This paper describes NAIST’s NMT system submitted to the IWSLT 2020 conversational speech translation task. We focus on the translation disfluent speech transcripts that in- clude ASR errors and non-grammatical utter- ances. We tried a domain adaptation method by transferring the styles of out-of-domain data (United Nations Parallel Corpus) to be like in-domain data (Fisher transcripts). Our system results showed that the NMT model with domain adaptation outperformed a base- line. In addition, slight improvement by the style transfer was observed. 1 Introduction Neural Machine Translation (NMT) has signifi- cantly improved the quality of Machine Translation (MT) (Bahdanau et al., 2014; Sutskever et al., 2014; Luong et al., 2015). However, domain-specific translation is still difficult in low-resource scenar- ios, although high performance can be achieved in resource-rich scenarios (Chu and Wang, 2018). Another major problem is the difficulty in translat- ing noisy input sentences including filler, hesita- tion, etc. Belinkov and Bisk (2017) suggests the difficulty in learning to translate noisy sentences compared to clean ones. The translation of noisy sentences is very important for spoken language translation. In the IWSLT 2020 Conversational Speech Translation Task, we are going to tackle these two problems. The task includes speech-to-text and text- to-text translation from disfluent Spanish speeches/transcripts to fluent English text. We chose the text-to-text subtask for our challenge task participation. The data for this task consists of about 130K bilingual pairs, would not be enough to learn a highly accurate NMT (Koehn and Knowles, 2017). In such a low-resource scenario, one promising way is domain adaptation using out-of-domain parallel corpora and in-domain monolingual corpora (Wang et al., 2016; Chu et al., 2017). In domain adaptation, the “similarity” between in-domain and out-of-domain data affects the trans- lation accuracy significantly (Koehn and Knowles, 2017). A domain can be defined by any property of the training data such as topic and style. We expect that the domain similarity comes from these properties. Let us return to the task description. In the task, the inputs are conversational speech transcripts by Automatic Speech Recognition (ASR). They can include ASR errors as well as disfluent and non- grammatical utterances in spontaneous speech. In contrast, the outputs are fluent sequences. In other words, the purpose of this task is to translate disflu- ent transcripts into fluent sentences. As mentioned before, domain adaptation is a common practice in a low-resource scenario. However, it is difficult to prepare external parallel data in a disfluent source language and a fluent target language. Although fluent written parallel data are widely available, the effects of training with them are limited because the style of the input sentences differs from the in- domain data. We need a new strategy …

Content truncated to 500 words