Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
HyoJung Han, Seokchan Ahn, Yoonjung Choi, Insoo Chung, Sangha Kim, Kyunghyun Cho
Abstract
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.- Anthology ID:
- 2021.wmt-1.119
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Loic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Tom Kocmi, Andre Martins, Makoto Morishita, Christof Monz
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1110–1123
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.119
- DOI:
- Bibkey:
- Cite (ACL):
- HyoJung Han, Seokchan Ahn, Yoonjung Choi, Insoo Chung, Sangha Kim, and Kyunghyun Cho. 2021. Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement. In Proceedings of the Sixth Conference on Machine Translation, pages 1110–1123, Online. Association for Computational Linguistics.
- Cite (Informal):
- Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement (Han et al., WMT 2021)
- Copy Citation:
- PDF:
- https://aclanthology.org/2021.wmt-1.119.pdf
- Video:
- https://aclanthology.org/2021.wmt-1.119.mp4
- Data
- MTNT
Export citation
@inproceedings{han-etal-2021-monotonic, title = "Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement", author = "Han, HyoJung and Ahn, Seokchan and Choi, Yoonjung and Chung, Insoo and Kim, Sangha and Cho, Kyunghyun", editor = "Barrault, Loic and Bojar, Ondrej and Bougares, Fethi and Chatterjee, Rajen and Costa-jussa, Marta R. and Federmann, Christian and Fishel, Mark and Fraser, Alexander and Freitag, Markus and Graham, Yvette and Grundkiewicz, Roman and Guzman, Paco and Haddow, Barry and Huck, Matthias and Yepes, Antonio Jimeno and Koehn, Philipp and Kocmi, Tom and Martins, Andre and Morishita, Makoto and Monz, Christof", booktitle = "Proceedings of the Sixth Conference on Machine Translation", month = nov, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.wmt-1.119", pages = "1110--1123", abstract = "Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.", }
<?xml version="1.0" encoding="UTF-8"?> <modsCollection xmlns="http://www.loc.gov/mods/v3"> <mods ID="han-etal-2021-monotonic"> <titleInfo> <title>Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement</title> </titleInfo> <name type="personal"> <namePart type="given">HyoJung</namePart> <namePart type="family">Han</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Seokchan</namePart> <namePart type="family">Ahn</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yoonjung</namePart> <namePart type="family">Choi</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Insoo</namePart> <namePart type="family">Chung</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Sangha</namePart> <namePart type="family">Kim</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Kyunghyun</namePart> <namePart type="family">Cho</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2021-11</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the Sixth Conference on Machine Translation</title> </titleInfo> <name type="personal"> <namePart type="given">Loic</namePart> <namePart type="family">Barrault</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Ondrej</namePart> <namePart type="family">Bojar</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Fethi</namePart> <namePart type="family">Bougares</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Rajen</namePart> <namePart type="family">Chatterjee</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Marta</namePart> <namePart type="given">R</namePart> <namePart type="family">Costa-jussa</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Christian</namePart> <namePart type="family">Federmann</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Mark</namePart> <namePart type="family">Fishel</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Alexander</namePart> <namePart type="family">Fraser</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Markus</namePart> <namePart type="family">Freitag</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yvette</namePart> <namePart type="family">Graham</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Roman</namePart> <namePart type="family">Grundkiewicz</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Paco</namePart> <namePart type="family">Guzman</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Barry</namePart> <namePart type="family">Haddow</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Matthias</namePart> <namePart type="family">Huck</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Antonio</namePart> <namePart type="given">Jimeno</namePart> <namePart type="family">Yepes</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Philipp</namePart> <namePart type="family">Koehn</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Tom</namePart> <namePart type="family">Kocmi</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Andre</namePart> <namePart type="family">Martins</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Makoto</namePart> <namePart type="family">Morishita</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Christof</namePart> <namePart type="family">Monz</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Online</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.</abstract> <identifier type="citekey">han-etal-2021-monotonic</identifier> <location> <url>https://aclanthology.org/2021.wmt-1.119</url> </location> <part> <date>2021-11</date> <extent unit="page"> <start>1110</start> <end>1123</end> </extent> </part> </mods> </modsCollection>
%0 Conference Proceedings %T Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement %A Han, HyoJung %A Ahn, Seokchan %A Choi, Yoonjung %A Chung, Insoo %A Kim, Sangha %A Cho, Kyunghyun %Y Barrault, Loic %Y Bojar, Ondrej %Y Bougares, Fethi %Y Chatterjee, Rajen %Y Costa-jussa, Marta R. %Y Federmann, Christian %Y Fishel, Mark %Y Fraser, Alexander %Y Freitag, Markus %Y Graham, Yvette %Y Grundkiewicz, Roman %Y Guzman, Paco %Y Haddow, Barry %Y Huck, Matthias %Y Yepes, Antonio Jimeno %Y Koehn, Philipp %Y Kocmi, Tom %Y Martins, Andre %Y Morishita, Makoto %Y Monz, Christof %S Proceedings of the Sixth Conference on Machine Translation %D 2021 %8 November %I Association for Computational Linguistics %C Online %F han-etal-2021-monotonic %X Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences. %U https://aclanthology.org/2021.wmt-1.119 %P 1110-1123
Markdown (Informal)
[Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement](https://aclanthology.org/2021.wmt-1.119) (Han et al., WMT 2021)
- Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement (Han et al., WMT 2021)
ACL
- HyoJung Han, Seokchan Ahn, Yoonjung Choi, Insoo Chung, Sangha Kim, and Kyunghyun Cho. 2021. Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement. In Proceedings of the Sixth Conference on Machine Translation, pages 1110–1123, Online. Association for Computational Linguistics.