paper-with-me

Papers Document Level Machine Translation

“Document Level Machine Translation” 태그가 달린 논문 58편 · 필터 해제

Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation

2022-09-28 · Hongyuan Lu, Haoyang Huang, Shuming Ma, Dongdong Zhang 외

Despite the fact that multilingual agreement (MA) has shown its importance for multilingual neural machine translation (MNMT), current methodologies in the field have two shortages: (i) require parallel data between mult…

Document Level Machine TranslationDocument TranslationMachine TranslationTranslation

DELA Project: Document-level Machine Translation Evaluation

2022-06-01 · EAMT 2022 6 · Sheila Castilho

This paper presents the results of the DELA Project. We describe the testing of context span for document-level evaluation, construction of a document-level corpus, and context position, as well as the latest development…

Document Level Machine TranslationMachine TranslationPositionTranslation

TANDO: A Corpus for Document-level Machine Translation

2022-06-01 · LREC 2022 6 · Harritxu Gete, Thierry Etchegoyhen, David Ponce, Gorka Labaka 외

Document-level Neural Machine Translation aims to increase the quality of neural translation models by taking into account contextual information. Properly modelling information beyond the sentence level can result in im…

Document Level Machine TranslationMachine TranslationSentenceTranslation

Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation

2022-05-03 · Findings (NAACL) 2022 7 · Yukun Feng, Feng Li, Ziang Song, Boyuan Zheng 외

The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the…

Document Level Machine TranslationMachine TranslationSentenceTranslation

Locality-Sensitive Hashing for Long Context Neural Machine Translation

2022-05-01 · IWSLT (ACL) 2022 5 · Frithjof Petrick, Jan Rosendahl, Christian Herold, Hermann Ney

After its introduction the Transformer architecture quickly became the gold standard for the task of neural machine translation. A major advantage of the Transformer compared to previous architectures is the faster train…

Document Level Machine TranslationMachine TranslationNMTSentence+1

DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence

2022-01-26 · Wei Zhao, Michael Strube, Steffen Eger

Recently, there has been a growing interest in designing text generation systems from a discourse coherence perspective, e.g., modeling the interdependence between sentences. Still, recent BERT-based evaluation metrics a…

Document Level Machine TranslationMachine TranslationText Generation

{BlonDe}: An Automatic Evaluation Metric for Document-level Machine Translation

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

Standard automatic metrics, e.g. BLEU, are not reliable for document-level MT evaluation. They can neither distinguish document-level improvements in translation quality from sentence-level ones, nor identify the discour…

Document Level Machine TranslationMachine TranslationSentenceTranslation

Document-level Neural Machine Translation Using Dependency RST Structure

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

Document-level machine translation (MT) extends the translation unit from the sentence to the whole document. Intuitively, discourse structure can be useful for document-level MT for its helpfulness in long-range depende…

DecoderDocument Level Machine TranslationMachine TranslationNMT+2

SMDT: Selective Memory-Augmented Neural Document Translation

2022-01-05 · Xu Zhang, Jian Yang, Haoyang Huang, Shuming Ma 외

Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation. However, little attention is paid to inaugurate more divers…

Document Level Machine TranslationDocument TranslationMachine TranslationNMT+2

Document Level Hierarchical Transformer

2021-12-01 · ALTA 2021 12 · Najam Zaidi, Trevor Cohn, Gholamreza Haffari

Generating long and coherent text is an important and challenging task encompassing many application areas such as summarization, document level machine translation and story generation. Despite the success in modeling i…

Document Level Machine TranslationImitation LearningMachine TranslationSentence+2

Contrastive Learning for Context-aware Neural Machine Translation Using Coreference Information

2021-11-01 · WMT (EMNLP) 2021 11 · Yongkeun Hwang, Hyeongu Yun, Kyomin Jung

Context-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation. Many existing works on context-awar…

Contrastive Learningcoreference-resolutionCoreference ResolutionData Augmentation+5

Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information

2021-09-13 · Yongkeun Hwang, Hyungu Yun, Kyomin Jung

Context-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation. Many existing works on context-awar…

Contrastive Learningcoreference-resolutionCoreference ResolutionData Augmentation+5

Multi-Hop Transformer for Document-Level Machine Translation

2021-06-01 · NAACL 2021 4 · Long Zhang, Tong Zhang, Haibo Zhang, Baosong Yang 외

Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of c…

Document Level Machine TranslationDocument TranslationMachine TranslationNMT+2

G-Transformer for Document-level Machine Translation

2021-05-31 · ACL 2021 5 · Guangsheng Bao, Yue Zhang, Zhiyang Teng, Boxing Chen 외

Document-level MT models are still far from satisfactory. Existing work extend translation unit from single sentence to multiple sentences. However, study shows that when we further enlarge the translation unit to a whol…

Document Level Machine TranslationInductive BiasMachine TranslationSentence+1

Measuring and Increasing Context Usage in Context-Aware Machine Translation

2021-05-07 · ACL 2021 5 · Patrick Fernandes, Kayo Yin, Graham Neubig, André F. T. Martins

Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context -- context from sentences other than those currently being translated. However, while many c…

Document Level Machine TranslationMachine TranslationTranslation

Hierarchical Learning for Generation with Long Source Sequences

2021-04-15 · Tobias Rohde, Xiaoxia Wu, Yinhan Liu

One of the challenges for current sequence to sequence (seq2seq) models is processing long sequences, such as those in summarization and document level machine translation tasks. These tasks require the model to reason a…

DecoderDocument Level Machine TranslationDocument SummarizationDocument Translation+6

Towards Personalised and Document-level Machine Translation of Dialogue

2021-04-01 · EACL 2021 2 · Sebastian Vincent

State-of-the-art (SOTA) neural machine translation (NMT) systems translate texts at sentence level, ignoring context: intra-textual information, like the previous sentence, and extra-textual information, like the gender …

Document Level Machine TranslationMachine TranslationNMTSentence+1

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation

2021-03-22 · NAACL 2022 7 · Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang 외

Standard automatic metrics, e.g. BLEU, are not reliable for document-level MT evaluation. They can neither distinguish document-level improvements in translation quality from sentence-level ones, nor identify the discour…

Document Level Machine TranslationMachine TranslationSentenceTranslation

Towards Personalised and Document-level Machine Translation of Dialogue

2021-02-11 · Sebastian T. Vincent

State-of-the-art (SOTA) neural machine translation (NMT) systems translate texts at sentence level, ignoring context: intra-textual information, like the previous sentence, and extra-textual information, like the gender …

Document Level Machine TranslationMachine TranslationNMTSentence+1

A Comparison of Approaches to Document-level Machine Translation

2021-01-26 · Zhiyi Ma, Sergey Edunov, Michael Auli

Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algor…

Document Level Machine TranslationMachine TranslationTranslation
← 이전 21–40 / 58 다음 →