paper-with-me

홈 › Papers

BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis

2018-09-05 · Pamela Shapiro, Kevin Duh

Neural Machine Translation (NMT) in low-resource settings and of morphologically rich languages is made difficult in part by data sparsity of vocabulary words. Several methods have been used to help reduce this sparsity, notably Byte-Pair Encoding (BPE) and a character-based CNN layer (charCNN). However, the charCNN has largely been neglected, possibly because it has only been compared to BPE rather than combined with it. We argue for a reconsideration of the charCNN, based on cross-lingual improvements on low-resource data. We translate from 8 languages into English, using a multi-way parallel collection of TED transcripts. We find that in most cases, using both BPE and a charCNN performs best, while in Hebrew, using a charCNN over words is best.

📄 PDF Abstract BibTeX arXiv:1809.01301

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation

2018-06-18 · COLING 2018 8 · Surafel M. Lakew, Mauro Cettolo, Marcello Federico

Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bi…

Machine TranslationNMTTransfer LearningTranslation

Slovene SuperGLUE Benchmark: Translation and Evaluation

2022-02-10 · LREC 2022 6 · Aleš Žagar, Marko Robnik-Šikonja

We present a Slovene combined machine-human translated SuperGLUE benchmark. We describe the translation process and problems arising due to differences in morphology and grammar. We evaluate the translated datasets in se…

Translation

Morphologically Aware Word-Level Translation

2020-11-15 · COLING 2020 8 · Paula Czarnowska, Sebastian Ruder, Ryan Cotterell, Ann Copestake

We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic…

Bilingual Lexicon InductionTranslation

MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction

2019-07-01 · ACL 2019 7 · Pengcheng Yang, Fuli Luo, Peng Chen, Tianyu Liu 외

The task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages. Previous work has shown that morphological variation is an intractable challenge for…

Bilingual Lexicon InductionDenoisingLanguage ModelingLanguage Modelling+1

Cross-lingual Name Tagging and Linking for 282 Languages

2017-07-01 · ACL 2017 7 · Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman 외

The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify na…

TranslationWord Translation