Document Level Machine Translation

7 papers with code • 1 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Using Coreference Links to Improve Spanish-to-English Machine Translation

idiap/APT WS 2017

In this paper, we present a proof-of-concept implementation of a coreference-aware decoder for document-level machine translation.

A Survey on Document-level Neural Machine Translation: Methods and Evaluation

SFFAI-AIKT/AIKT-Natural_Language_Processing 18 Dec 2019

Machine translation (MT) is an important task in natural language processing (NLP) as it automates the translation process and reduces the reliance on human translators.

Towards Making the Most of Context in Neural Machine Translation

blickwinkel1107/making-the-most-of-context-nmt 19 Feb 2020

Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted.

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

eleanorjiang/blonde 22 Mar 2021

Standard automatic metrics, e. g. BLEU, are not reliable for document-level MT evaluation.

Measuring and Increasing Context Usage in Context-Aware Machine Translation

neulab/contextual-mt ACL 2021

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.

G-Transformer for Document-level Machine Translation

baoguangsheng/g-transformer ACL 2021

However, study shows that when we further enlarge the translation unit to a whole document, supervised training of Transformer can fail.

DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence

aiphes/discoscore 26 Jan 2022

We find that (i) the majority of BERT-based metrics correlate much worse with human rated coherence than early discourse metrics, invented a decade ago; (ii) the recent state-of-the-art BARTScore is weak when operated at system level -- which is particularly problematic as systems are typically compared in this manner.