The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kertas kerja ini membentangkan model penyusunan semula menggunakan pokok parse sisi sumber untuk terjemahan mesin statistik berasaskan frasa. Model yang dicadangkan adalah lanjutan daripada kekangan IST-ITG (pokok sumber yang mengenakan pada tatabahasa transduksi penyongsangan). Dalam kaedah yang dicadangkan, susunan perkataan sisi sasaran diperoleh dengan memutarkan nod pokok parse sisi sumber. Kami memodelkan putaran nod, monoton atau swap, menggunakan penjajaran perkataan berdasarkan korpus selari latihan dan pokok parse sisi sumber. Model ini dengan cekap menghalang susunan perkataan sasaran yang salah, terutamanya pesanan global. Tambahan pula, kaedah yang dicadangkan menjalankan penilaian kebarangkalian penyusunan semula kata sasaran. Dalam eksperimen terjemahan Inggeris-ke-Jepun dan Inggeris-ke-Cina, kaedah yang dicadangkan menghasilkan peningkatan 0.49 mata (29.31 hingga 29.80) dan peningkatan 0.33 mata (18.60 hingga 18.93) dalam perkataan BLEU-4 berbanding dengan IST- Kekangan ITG, masing-masing. Ini menunjukkan kesahihan model penyusunan semula yang dicadangkan.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Kei HASHIMOTO, Hirofumi YAMAMOTO, Hideo OKUMA, Eiichiro SUMITA, Keiichi TOKUDA, "A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 12, pp. 2386-2393, December 2009, doi: 10.1587/transinf.E92.D.2386.
Abstract: This paper presents a reordering model using a source-side parse-tree for phrase-based statistical machine translation. The proposed model is an extension of IST-ITG (imposing source tree on inversion transduction grammar) constraints. In the proposed method, the target-side word order is obtained by rotating nodes of the source-side parse-tree. We modeled the node rotation, monotone or swap, using word alignments based on a training parallel corpus and source-side parse-trees. The model efficiently suppresses erroneous target word orderings, especially global orderings. Furthermore, the proposed method conducts a probabilistic evaluation of target word reorderings. In English-to-Japanese and English-to-Chinese translation experiments, the proposed method resulted in a 0.49-point improvement (29.31 to 29.80) and a 0.33-point improvement (18.60 to 18.93) in word BLEU-4 compared with IST-ITG constraints, respectively. This indicates the validity of the proposed reordering model.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2386/_p
Salinan
@ARTICLE{e92-d_12_2386,
author={Kei HASHIMOTO, Hirofumi YAMAMOTO, Hideo OKUMA, Eiichiro SUMITA, Keiichi TOKUDA, },
journal={IEICE TRANSACTIONS on Information},
title={A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation},
year={2009},
volume={E92-D},
number={12},
pages={2386-2393},
abstract={This paper presents a reordering model using a source-side parse-tree for phrase-based statistical machine translation. The proposed model is an extension of IST-ITG (imposing source tree on inversion transduction grammar) constraints. In the proposed method, the target-side word order is obtained by rotating nodes of the source-side parse-tree. We modeled the node rotation, monotone or swap, using word alignments based on a training parallel corpus and source-side parse-trees. The model efficiently suppresses erroneous target word orderings, especially global orderings. Furthermore, the proposed method conducts a probabilistic evaluation of target word reorderings. In English-to-Japanese and English-to-Chinese translation experiments, the proposed method resulted in a 0.49-point improvement (29.31 to 29.80) and a 0.33-point improvement (18.60 to 18.93) in word BLEU-4 compared with IST-ITG constraints, respectively. This indicates the validity of the proposed reordering model.},
keywords={},
doi={10.1587/transinf.E92.D.2386},
ISSN={1745-1361},
month={December},}
Salinan
TY - JOUR
TI - A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation
T2 - IEICE TRANSACTIONS on Information
SP - 2386
EP - 2393
AU - Kei HASHIMOTO
AU - Hirofumi YAMAMOTO
AU - Hideo OKUMA
AU - Eiichiro SUMITA
AU - Keiichi TOKUDA
PY - 2009
DO - 10.1587/transinf.E92.D.2386
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2009
AB - This paper presents a reordering model using a source-side parse-tree for phrase-based statistical machine translation. The proposed model is an extension of IST-ITG (imposing source tree on inversion transduction grammar) constraints. In the proposed method, the target-side word order is obtained by rotating nodes of the source-side parse-tree. We modeled the node rotation, monotone or swap, using word alignments based on a training parallel corpus and source-side parse-trees. The model efficiently suppresses erroneous target word orderings, especially global orderings. Furthermore, the proposed method conducts a probabilistic evaluation of target word reorderings. In English-to-Japanese and English-to-Chinese translation experiments, the proposed method resulted in a 0.49-point improvement (29.31 to 29.80) and a 0.33-point improvement (18.60 to 18.93) in word BLEU-4 compared with IST-ITG constraints, respectively. This indicates the validity of the proposed reordering model.
ER -