paper-with-me

Papers

Paying Attention to Multi-Word Expressions in Neural Machine Translation

2017-10-17 · MTSummit 2017 9 · Matīss Rikters, Ondřej Bojar

Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task. Even neural machine translation (NMT) struggles to overcome it. This paper presents results of experiments on investigating NMT attention allocation to the MWEs and improving automated translation of sentences that contain MWEs in English->Latvian and English->Czech NMT systems. Two improvement strategies were explored -(1) bilingual pairs of automatically extracted MWE candidates were added to the parallel corpus used to train the NMT system, and (2) full sentences containing the automatically extracted MWE candidates were added to the parallel corpus. Both approaches allowed to increase automated evaluation results. The best result - 0.99 BLEU point increase - has been reached with the first approach, while with the second approach minimal improvements achieved. We also provide open-source software and tools used for MWE extraction and alignment inspection.

📄 PDF Abstract BibTeX arXiv:1710.06313

Code (1)

M4t1ss/MWE-Tools 공식 구현

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Head2Head: Video-based Neural Head Synthesis

2020-05-22 · Mohammad Rami Koujan, Michail Christos Doukas, Anastasios Roussos, Stefanos Zafeiriou

In this paper, we propose a novel machine learning architecture for facial reenactment. In particular, contrary to the model-based approaches or recent frame-based methods that use Deep Convolutional Neural Networks (DCN…

BIG-bench Machine Learning

MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language

2024-06-19 · Shun Wang, Ge Zhang, Han Wu, Tyler Loakman 외

Machine Translation (MT) has developed rapidly since the release of Large Language Models and current MT evaluation is performed through comparison with reference human translations or by predicting quality scores from h…

Machine TranslationTranslation

Do Context-Aware Translation Models Pay the Right Attention?

2021-05-14 · ACL 2021 5 · Kayo Yin, Patrick Fernandes, Danish Pruthi, Aditi Chaudhary 외

Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolu…

Machine TranslationTranslation

How Does Selective Mechanism Improve Self-Attention Networks?

2020-05-03 · ACL 2020 6 · Xinwei Geng, Long-Yue Wang, Xing Wang, Bing Qin 외

Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words. However, the underlying reasons for their strong performance…

Machine TranslationNatural Language InferenceSentenceTranslation

Orthogonality Constrained Multi-Head Attention For Keyword Spotting

2019-10-10 · Mingu Lee, Jinkyu Lee, Hye Jin Jang, Byeonggeun Kim 외

Multi-head attention mechanism is capable of learning various representations from sequential data while paying attention to different subsequences, e.g., word-pieces or syllables in a spoken word. From the subsequences,…

Keyword Spotting