paper-with-me

Papers

Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings

2017-07-01 · ACL 2017 7 · Benjamin Marie, Atsushi Fujita

We propose a new method for extracting pseudo-parallel sentences from a pair of large monolingual corpora, without relying on any document-level information. Our method first exploits word embeddings in order to efficiently evaluate trillions of candidate sentence pairs and then a classifier to find the most reliable ones. We report significant improvements in domain adaptation for statistical machine translation when using a translation model trained on the sentence pairs extracted from in-domain monolingual corpora.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationInformation RetrievalMachine TranslationSentenceTranslationWord Embeddings

Similar Papers 제목 키워드 기반

Large-scale Hierarchical Alignment for Data-driven Text Rewriting

2018-10-18 · RANLP 2019 9 · Nikola I. Nikolov, Richard H. R. Hahnloser

We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our appr…

ArticlesSentenceStyle TransferText Simplification

D-Terminer: Online Demo for Monolingual and Bilingual Automatic Term Extraction

2022-06-01 · TERM (LREC) 2022 6 · Ayla Rigouts Terryn, Veronique Hoste, Els Lefever

This contribution presents D-Terminer: an open access, online demo for monolingual and multilingual automatic term extraction from parallel corpora. The monolingual term extraction is based on a recurrent neural network,…

Term ExtractionTranslation

Domain Adaptation of Neural Machine Translation by Lexicon Induction

2019-06-02 · ACL 2019 7 · Junjie Hu, Mengzhou Xia, Graham Neubig, Jaime Carbonell

It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for s…

Domain AdaptationMachine TranslationNMTTranslation

Filtering Back-Translated Data in Unsupervised Neural Machine Translation

2020-12-01 · COLING 2020 8 · Jyotsana Khatri, Pushpak Bhattacharyya

Unsupervised neural machine translation (NMT) utilizes only monolingual data for training. The quality of back-translated data plays an important role in the performance of NMT systems. In back-translation, all generated…

Domain AdaptationMachine TranslationNMTSentence+1

Unsupervised Extraction of Partial Translations for Neural Machine Translation

2019-06-01 · NAACL 2019 6 · Benjamin Marie, Atsushi Fujita

In neural machine translation (NMT), monolingual data are usually exploited through a so-called back-translation: sentences in the target language are translated into the source language to synthesize new parallel data. …

Machine TranslationNMTTranslation