Filters








7,704 Hits in 5.4 sec

Guiding Neural Machine Translation with Retrieved Translation Pieces

Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig, Satoshi Nakamura
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases.  ...  sentences and aligned with words that match in the source sentences, which we call "translation pieces".  ...  Introduction Neural machine translation (NMT) (Bahdanau et al., 2014; Sennrich et al., 2016a; Wang et al., 2017b) is now the state-of-the-art in machine translation, due to its ability to be trained  ... 
doi:10.18653/v1/n18-1120 dblp:conf/naacl/ZhangUSNN18 fatcat:4wrpgdku45hr7nxtqqzf57kjcu

Guiding Neural Machine Translation with Retrieved Translation Pieces [article]

Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig, Satoshi Nakamura
2018 arXiv   pre-print
One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases.  ...  sentences and aligned with words that match in the source sentences, which we call "translation pieces".  ...  Introduction Neural machine translation (NMT) (Bahdanau et al., 2014; Sennrich et al., 2016a; Wang et al., 2017b) is now the state-of-the-art in machine translation, due to its ability to be trained  ... 
arXiv:1804.02559v1 fatcat:qwouupto6rdcxamqkvokee6hou

Learning Kernel-Smoothed Machine Translation with Retrieved Examples [article]

Qingnan Jiang, Mingxuan Wang, Jun Cao, Shanbo Cheng, Shujian Huang, Lei Li
2021 arXiv   pre-print
In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online.  ...  Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples.  ...  Guid- ing neural machine translation with retrieved transla- Matt Post. 2018. A call for clarity in reporting bleu tion pieces.  ... 
arXiv:2109.09991v2 fatcat:tkynje7j3nfo3erf5nl27osvka

Retrieval-Based Neural Code Generation

Shirley Anugrah Hayati, Raphael Olivier, Pravalika Avvaru, Pengcheng Yin, Anthony Tomasic, Graham Neubig
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
We introduce RECODE, a method based on subtree retrieval that makes it possible to explicitly reference existing code examples within a neural code generation model.  ...  Finally, we increase the probability of actions that cause the retrieved n-gram action subtree to be in the predicted code.  ...  employ a simpler and faster retrieval method to guide neural MT where translation pieces are n-grams from retrieved target sentences.  ... 
doi:10.18653/v1/d18-1111 dblp:conf/emnlp/HayatiOAYTN18 fatcat:3tiinxb6gfabzmqssilvqxlm4q

Retrieval-Based Neural Code Generation [article]

Shirley Anugrah Hayati, Raphael Olivier, Pravalika Avvaru, Pengcheng Yin, Anthony Tomasic, Graham Neubig
2018 arXiv   pre-print
We introduce ReCode, a method based on subtree retrieval that makes it possible to explicitly reference existing code examples within a neural code generation model.  ...  Finally, we increase the probability of actions that cause the retrieved n-gram action subtree to be in the predicted code.  ...  employ a simpler and faster retrieval method to guide neural MT where translation pieces are n-grams from retrieved target sentences.  ... 
arXiv:1808.10025v1 fatcat:qiwhi4igkvf5ll63wtfqu3oiky

Non-Parametric Online Learning from Human Feedback for Neural Machine Translation [article]

Dongqi Wang, Haoran Wei, Zhirui Zhang, Shujian Huang, Jun Xie, Jiajun Chen
2021 arXiv   pre-print
translations are used to improve the neural machine translation (NMT) system.  ...  We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations and then the corrected  ...  Guiding Neural Machine Translation with Retrieved Translation Pieces. In NAACL, 1325–1335. Zhang, Z.; Liu, S.; Li, M.; Zhou, M.; and Chen, E. 2018b.  ... 
arXiv:2109.11136v3 fatcat:h4s5jgfcdvendjn4fptdzfqsb4

Learning to Reuse Translations: Guiding Neural Machine Translation with Examples [article]

Qian Cao, Shaohui Kuang, Deyi Xiong
2019 arXiv   pre-print
In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction.  ...  To solve these challenges, we propose an Example-Guided NMT (EGNMT) framework with two models: (1) a noise-masked encoder model that masks out noisy words according to word alignments and encodes the noise-masked  ...  Introduction Neural machine translation [3, 27, 28, 9] captures the knowledge of the source and target language along with their correspondences as part of the encoder and decoder parameters learned  ... 
arXiv:1911.10732v2 fatcat:5dy3fpcdozf6hcigxkpf7cxdau

Scalable Cross-Lingual Transfer of Neural Sentence Embeddings [article]

Hanan Aldarmaki, Mona Diab
2019 arXiv   pre-print
and extrinsic evaluations, particularly with smaller sets of parallel data.  ...  We evaluate three alignment frameworks applied to these models: joint modeling, representation transfer learning, and sentence mapping, using parallel text to guide the alignment.  ...  (b) Neural Machine Translation objective, where the output is a translation of the input sentence from a parallel corpus.  ... 
arXiv:1904.05542v1 fatcat:cvmxdq7kvzbhphsanx5rlq6rbi

Scalable Cross-Lingual Transfer of Neural Sentence Embeddings

Hanan Aldarmaki, Mona Diab
2019 Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*  
and extrinsic evaluations, particularly with smaller sets of parallel data.  ...  We evaluate three alignment frameworks applied to these models: joint modeling, representation transfer learning, and sentence mapping, using parallel text to guide the alignment.  ...  (b) Neural Machine Translation objective, where the output is a translation of the input sentence from a parallel corpus.  ... 
doi:10.18653/v1/s19-1006 dblp:conf/starsem/AldarmakiD19 fatcat:oxgda73bpfcsphfh5vdpuhkeiy

Neural Machine Translation with Monolingual Translation Memory [article]

Deng Cai and Yan Wang and Huayang Li and Wai Lam and Lemao Liu
2021 arXiv   pre-print
Prior work has proved that Translation memory (TM) can boost the performance of Neural Machine Translation (NMT).  ...  First, the cross-lingual memory retriever allows abundant monolingual data to be TM. Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal.  ...  Memory (TM) augmented Neural Machine Translation (NMT).  ... 
arXiv:2105.11269v2 fatcat:r6e5etqtbfaetijqxurpftcmwu

Multimodal machine translation through visuals and speech

Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos, Aku Rouhe, Desmond Elliott, Lucia Specia, Jörg Tiedemann
2020 Machine Translation  
The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively.  ...  Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data.  ...  We would also like to thank Maarit Koponen for her valuable feedback and her help in establishing our discussions of machine translation evaluation.  ... 
doi:10.1007/s10590-020-09250-0 fatcat:jod3ghcsnnbipotcqp6sme4lna

Multimodal Machine Translation through Visuals and Speech

Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos, Aku Rouhe, Desmond Elliott, Lucia Specia, Jörg Tiedemann
2019 Zenodo  
The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively.  ...  Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data.  ...  We would also like to thank Maarit Koponen for her valuable feedback and her help in establishing our discussions of machine translation evaluation.  ... 
doi:10.5281/zenodo.3690791 fatcat:otdy5i33fzfsnnbb3xgb6zph6q

Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation

Hardy Hardy, Andreas Vlachos
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document.  ...  Recent work on abstractive summarization has made progress with neural encoder-decoder architectures.  ...  Acknowledgments We are thankful for Gerasimos Lampouras for his help with the manual evaluation process and all volunteers who participated in it.  ... 
doi:10.18653/v1/d18-1086 dblp:conf/emnlp/HardyV18 fatcat:pamsjtopsvcahh2mzeuc6vspva

Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation [article]

Hardy, Andreas Vlachos
2018 arXiv   pre-print
In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document.  ...  Recent work on abstractive summarization has made progress with neural encoder-decoder architectures.  ...  Acknowledgments We are thankful for Gerasimos Lampouras for his help with the manual evaluation process and all volunteers who participated in it.  ... 
arXiv:1808.09160v1 fatcat:ro5vqaisrfbhrapppqs2664aeu

Query Rewriting via Cycle-Consistent Translation for E-Commerce Search [article]

Yiming Qiu, Kang Zhang, Han Zhang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, Wen-Yun Yang
2021 arXiv   pre-print
Then we introduce a novel cyclic consistent training algorithm in conjunction with state-of-the-art machine translation models to achieve the optimal performance in terms of query rewriting accuracy.  ...  Specifically, we formulate query rewriting into a cyclic machine translation problem to leverage abundant click log data.  ...  Neural Machine Translation Neural Machine Translation (NMT) based on a neural network encoder-decoder architecture recently surpasses its precedent statistical machine translation (SMT) as state-of-theart  ... 
arXiv:2103.00800v1 fatcat:7ocr5lhcgzblpcmoca7qdpmncu
« Previous Showing results 1 — 15 out of 7,704 results