paper-with-me

홈 › Papers

Document Graph for Neural Machine Translation

2020-12-07 · EMNLP 2021 11 · Mingzhou Xu, Liangyou Li, Derek. F. Wong, Qun Liu, Lidia S. Chao

Previous works have shown that contextual information can improve the performance of neural machine translation (NMT). However, most existing document-level NMT methods only consider a few number of previous sentences. How to make use of the whole document as global contexts is still a challenge. To address this issue, we hypothesize that a document can be represented as a graph that connects relevant contexts regardless of their distances. We employ several types of relations, including adjacency, syntactic dependency, lexical consistency, and coreference, to construct the document graph. Then, we incorporate both source and target graphs into the conventional Transformer architecture with graph convolutional networks. Experiments on various NMT benchmarks, including IWSLT English--French, Chinese-English, WMT English--German and Opensubtitle English--Russian, demonstrate that using document graphs can significantly improve the translation quality. Extensive analysis verifies that the document graph is beneficial for capturing discourse phenomena.

📄 PDF Abstract BibTeX arXiv:2012.03477

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Using a Graph-based Coherence Model in Document-Level Machine Translation

2017-09-01 · WS 2017 9 · Leo Born, Mohsen Mesgar, Michael Strube

Although coherence is an important aspect of any text generation system, it has received little attention in the context of machine translation (MT) so far. We hypothesize that the quality of document-level translation c…

Document Level Machine TranslationMachine TranslationText GenerationTranslation

Exploring Paracrawl for Document-level Neural Machine Translation

2023-04-20 · Yusser Al Ghussin, Jingyi Zhang, Josef van Genabith

Document-level neural machine translation (NMT) has outperformed sentence-level NMT on a number of datasets. However, document-level NMT is still not widely adopted in real-world translation systems mainly due to the lac…

Machine TranslationNMTSentenceTranslation

GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translation

2025-07-04 · Himanshu Dutta, Sunny Manchanda, Prakhar Bapat, Meva Ram Gurjar 외

Document level Machine Translation (DocMT) approaches often struggle with effectively capturing discourse level phenomena. Existing approaches rely on heuristic rules to segment documents into discourse units, which rare…

Document Level Machine TranslationDocument TranslationLarge Language ModelMachine Translation+1

Challenges in Context-Aware Neural Machine Translation

2023-05-23 · Linghao Jin, Jacqueline He, Jonathan May, Xuezhe Ma

Context-aware neural machine translation involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, and has given rise…

Machine TranslationSentenceTranslation

Multilingual Contextualization of Large Language Models for Document-Level Machine Translation

2025-04-16 · Miguel Moura Ramos, Patrick Fernandes, Sweta Agrawal, André F. T. Martins

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and…

Document Level Machine TranslationDocument TranslationMachine TranslationSentence+1