paper-with-me

Papers

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English

2020-11-06 · COLING 2020 8 · Gongbo Tang, Rico Sennrich, Joakim Nivre

Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this paper, we conduct an investigation into pure character-based models in the case of translating Finnish into English, including exploring the ability to learn word senses and morphological inflections and the attention mechanism. We demonstrate that word-level information is distributed over the entire character sequence rather than over a single character, and characters at different positions play different roles in learning linguistic knowledge. In addition, character-based models need more layers to encode word senses which explains why only deeper models outperform subword-based models. The attention distribution pattern shows that separators attract a lot of attention and we explore a sparse word-level attention to enforce character hidden states to capture the full word-level information. Experimental results show that the word-level attention with a single head results in 1.2 BLEU points drop.

📄 PDF Abstract BibTeX arXiv:2011.03469

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

On the Effectiveness of Quasi Character-Level Models for Machine Translation

2022-09-01 · AMTA 2022 9 · Salvador Carrión-Ponz, Francisco Casacuberta

Neural Machine Translation (NMT) models often use subword-level vocabularies to deal with rare or unknown words. Although some studies have shown the effectiveness of purely character-based models, these approaches have …

Machine TranslationNMTTranslation

On the Effectiveness of Quasi Character-Level Models for Machine Translation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Neural Machine Translation (NMT) models often use subword-level vocabularies to deal with rare or unknown words. Although some studies have shown the effectiveness of purely character-based models, these approaches have …

Low Resource NMTMachine TranslationNMTTranslation

Neural Machine Translation with Byte-Level Subwords

2019-09-07 · Changhan Wang, Kyunghyun Cho, Jiatao Gu

Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese how…

Machine TranslationTranslation

On the Effectiveness of Quasi Character-Level Models for Machine Translation

2021-09-29 · Salvador Carrión Ponz, Francisco Casacuberta Nolla

Neural Machine Translation (NMT) models often use subword-level vocabularies to deal with rare or unknown words. Although some studies have shown the effectiveness of purely character-based models, these approaches have …

Low Resource NMTMachine TranslationNMTTranslation

Man vs. Machine: Extracting Character Networks from Human and Machine Translations

2022-10-01 · LaTeCHCLfL (COLING) 2022 10 · Aleksandra Konovalova, Antonio Toral

Most of the work on Character Networks to date is limited to monolingual texts. Conversely, in this paper we apply and analyze Character Networks on both source texts (English novels) and their Finnish translations (both…