Skip to search formSkip to main contentSkip to account menu
DOI:10.1162/tacl_a_00242 - Corpus ID: 52933530
@article{Pu2018IntegratingWS, title={Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation}, author={Xiao Pu and Nikolaos Pappas and James Henderson and Andrei Popescu-Belis}, journal={Transactions of the Association for Computational Linguistics}, year={2018}, volume={6}, pages={635-649}, url={https://api.semanticscholar.org/CorpusID:52933530}}
- X. Pu, Nikolaos Pappas, Andrei Popescu-Belis
- Published in Transactions of the… 5 October 2018
- Computer Science, Linguistics
This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous…
38 Citations
4
25
7
Topics
Word Sense Disambiguation (opens in a new tab)Neural MT (opens in a new tab)Sense Vectors (opens in a new tab)Neural Machine Translation (opens in a new tab)Random Walks (opens in a new tab)Chinese Restaurant Processes (opens in a new tab)Source Context (opens in a new tab)K-means (opens in a new tab)Word Vectors (opens in a new tab)BLEU Points (opens in a new tab)
Ask This Paper
BETA
AI-Powered
Ask This Paper
BETA
AI-Powered
Unknown Error
An unexpected error occurred. Please try again.
No Answer Found
Ask another question that can be answered by this paper or rephrase your question.
We are still processing this paper
Please try again later.
Question Answering Unavailable
Please try again later.
No Response
The server took too long to answer your question. You can either rephrase your question or wait until it is less busy.
AI-Generated
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Supporting Statements
Our system tries to constrain to information found in this paper. Results quality may vary. Learn more about how we generate these answers.
Feedback?
38 Citations
- Viktor HangyaQianchu LiuDario StojanovskiAlexander M. FraserA. Korhonen
- 2021
Computer Science
WMT
This work proposes CmBT (Contextually-mined Back-Translation), an approach for improving multi-sense word translation leveraging pre-trained cross-lingual contextual word representations (CCWRs), and shows that the system improves on the translation of difficult unseen and low frequency word senses.
- 3
- PDF
- Ying SuHongming ZhangYangqiu SongTong Zhang
- 2022
Computer Science, Linguistics
COLING
This paper proposes to build knowledge and supervised based Multilingual Word Sense Disambiguation systems and address the annotation scarcity problem for MWSD by transferring annotations from rich sourced languages.
- Tommaso PasiniFederico ScozzafavaBianca Scarlini
- 2020
Computer Science, Linguistics
ACL
This paper presents CluBERT, an automatic and multilingual approach for inducing the distributions of word senses from a corpus of raw sentences that attains state-of-the-art results on the English Word Sense Disambiguation tasks and helps to improve the disambiguated performance of two off- the-shelf WSD models.
- 15
- PDF
- Sawan KumarSharmistha JatKaran SaxenaP. Talukdar
- 2019
Computer Science, Linguistics
ACL
This work proposes Extended WSD Incorporating Sense Embeddings (EWISE), a supervised model to perform WSD by predicting over a continuous sense embedding space as opposed to a discrete label space, which allows EWISE to generalize over both seen and unseen senses, thus achieving generalized zero-shot learning.
- 91
- PDF
- Elijah Matthew RippethMarine CarpuatKevin DuhMatt Post
- 2023
Computer Science
ArXiv
This work introduces a simple and scalable approach to resolve translation ambiguity by incorporating a small amount of extra-sentential context in neural neural models to translate ambiguous source words better than strong sentence- level baselines and comparable document-level baselines while reducing training costs.
- Vivek IyerPinzhen ChenAlexandra Birch
- 2023
Computer Science, Linguistics
WMT
The capabilities of LLMs to translate “ambiguous sentences” are studied, and two ways to improve their disambiguation capabilities are proposed, through a) in-context learning and b) fine-tuning on carefully curated ambiguous datasets.
- Alessandro RaganatoYves ScherrerJ. Tiedemann
- 2020
Computer Science, Linguistics
LREC
This paper presents an evaluation benchmark on WSD for machine translation for 10 language pairs, comprising training data with known sense distributions, and builds upon the wide-coverage multilingual sense inventory of BabelNet, the multilingual neural parsing pipeline TurkuNLP, and the OPUS collection of translated texts from the web.
- 10
- Highly Influenced
- PDF
- X. Pu
- 2018
Computer Science, Linguistics
This thesis proposes a method to decide whether two occurrences of the same noun in a source text should be translated consistently, and designs sense-aware MT systems that select the correct translations of ambiguous words by performing word sense disambiguation (WSD).
- PDF
- Asma DjaidriH. AlianeH. Azzoune
- 2023
Linguistics, Computer Science
ACM Trans. Asian Low Resour. Lang. Inf. Process.
This work uses contextualized word embeddings for an unsupervised Arabic WSD that is based on linguistic markers and uses sentence-BERT Transformer pre-trained models, which yields encouraging results that outperform other existing un supervised neural AWSD approaches.
- 1
- Ying SuHongming ZhangYangqiu SongTong Zhang
- 2022
Computer Science
ACL
This work investigates the statistical relation between word frequency rank and word sense number distribution and proposes a Z-reweighting method on the word level to adjust the training on the imbalanced dataset.
- 6
- PDF
...
...
48 References
- Marine CarpuatDekai Wu
- 2007
Computer Science, Linguistics
EMNLP
This paper investigates a new strategy for integrating WSD into an SMT system, that performs fully phrasal multi-word disambiguation, and provides the first known empirical evidence that lexical semantics are indeed useful for SMT, despite claims to the contrary.
- 406
- PDF
- Annette Rios GonzalesLaura MascarellRico Sennrich
- 2017
Computer Science, Linguistics
WMT
While a baseline NMT system disambiguates frequent word senses quite reliably, the annotation with both sense labels and lexical chains improves the neural models’ performance on rare word senses.
- 118
- PDF
- David VickreyLuke BiewaldM. TeyssierD. Koller
- 2005
Computer Science, Linguistics
HLT
It is shown that the word-translation system can be used to improve performance on a simplified machine-translation task and can effectively and accurately prune the set of candidate translations for a word.
- 204
- PDF
- X. PuNikolaos PappasAndrei Popescu-Belis
- 2017
Computer Science
WMT
This work demonstrates that WSD systems can be adapted to help SMT, thanks to three key achievements: it considers a larger context for WSD than SMT can afford to consider, and it adapts the number of senses per word to the ones observed in the training data.
- 7
- PDF
- Zhen YangWei ChenFeng WangBo Xu
- 2017
Computer Science
2017 International Joint Conference on Neural…
This paper validates the hypothesis and proposes a simple and flexible framework, which enables the NMT model to only focus on the relevant sense type of the input word in current context and achieves substantial improvements on every test set over competitive baselines.
- 6
- Deyi XiongMin Zhang
- 2014
Computer Science, Linguistics
ACL
A sense-based translation model to integrate word senses into statistical machine translation based on a nonparametric Bayesian topic model that automatically learns sense clusters for words in the source language is proposed.
- 34
- PDF
- Jiwei LiDan Jurafsky
- 2015
Computer Science, Linguistics
EMNLP
A multisense embedding model based on Chinese Restaurant Processes is introduced that achieves state of the art performance on matching human word similarity judgments, and a pipelined architecture for incorporating multi-sense embeddings into language understanding is proposed.
- 231 [PDF]
- Steven NealeLuís Manuel dos Santos GomesEneko AgirreOier Lopez de LacalleA. Branco
- 2016
Computer Science, Linguistics
LREC
Training on a large, open-domain corpus (Europarl) and including word senses as contextual features in maxent-based translation models yields significant improvements in machine translation from English to Portuguese.
- 28
- PDF
- Frederick LiuHan LuGraham Neubig
- 2018
Computer Science, Linguistics
NAACL
Empirical evidence is provided that existing NMT systems in fact still have significant problems in properly translating ambiguous words, and methods are described that model the context of the input word with context-aware word embeddings that help to differentiate the word sense before feeding it into the encoder.
- 55 [PDF]
- Heeyoul ChoiKyunghyun ChoYoshua Bengio
- 2017
Computer Science
Comput. Speech Lang.
- 86 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers