Evaluating Discourse Phenomena in Neural Machine Translation (N18-1)

Copied to clipboard

Challenge: Existing models for machine translation have been evaluated with standard automatic metrics, but are poorly adapted to evaluating discourse phenomena.
Approach: They propose to use BLEU to train multi-encoder NMT models on English subtitles to test their ability to exploit previous source and target sentences.
Outcome: The proposed multi-encoder models give limited improvements on the coreference and coherence tests.

Similar Papers

Exploiting Sentential Context for Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Existing approaches to exploit sentential context for machine translation are not well studied.
Approach: They propose a shallow sentential context that exploits top encoder layer, and a deep sentential one that aggregates sentential representations from all internal layers.
Outcome: The proposed model outperforms the strong Transformer model on the English-German and English-French benchmarks.
Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns (2020.acl-main)

Copied to clipboard

Challenge: Recent studies have focused on past sentences as context with a focus on anaphora translation.
Approach: They propose to use future context to improve NMT performance by comparing a contextual NMT model trained with past context to a context-agnostic model.
Outcome: The proposed model outperforms the context-agnostic Transformer and shows comparable and in some cases improved performance.
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (N18-2)

Copied to clipboard

Challenge: Existing methods to investigate whether sentence representations from NMT systems capture distinct semantic phenomena are limited.
Approach: They propose a process to investigate the extent to which sentence representations arising from neural machine translation systems encode distinct semantic phenomena.
Outcome: The proposed model is suited to supporting inferences at the syntax-semantics interface, compared to anaphora resolution requiring world knowledge.
A Test Set for Discourse Translation from Japanese to English (2020.lrec-1)

Copied to clipboard

Challenge: Compared with a previous study on test sets for English-to-French discourse translation, we needed different approaches because Japanese has zero pronouns and represents different senses in different characters.
Approach: They used a test set for Japanese-to-English discourse translation to evaluate the power of context-aware machine translation.
Outcome: The results show that the translation accuracy of Japanese-to-English discourse translation is improved by using context-aware neural machine translation.
Analysing concatenation approaches to document-level NMT in two different domains (D19-65)

Copied to clipboard

Challenge: a recent study has shown that discourse-related biases affect neural MT performance.
Approach: They propose a comparative evaluation scheme that contrasts coherent context with artificially scrambled documents and absent context.
Outcome: The proposed evaluation scheme contrasts coherent context with artificially scrambled documents and absent context on two popular datasets.
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion (P19-1)

Copied to clipboard

Challenge: et al., 2018: translation errors due to the lack of extra-sentential context are becoming more and more noticeable among otherwise adequate translations.
Approach: They propose a context-aware translation model that uses sentence-level data to identify inconsistencies . standard metrics are not sensitive to improvements in consistency in document-level translations .
Outcome: The proposed model shows major gains over baseline without sacrificing performance . standard metrics are not sensitive to improvements in document-level translations .
Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: In encoder-decoder neural models, multiple encoders are used to represent contextual information in addition to the individual sentence.
Approach: They propose to use multiple context encoders to encode the individual sentences in document-level neural machine translation (NMT) They propose a noisy dropout setup and a single-encoder approach to encode context sentences.
Outcome: The proposed approach encodes the context and the current sentence without contexts.
Document Graph for Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing document-level NMT methods fail to leverage contexts beyond a few set of previous sentences.
Approach: They propose to represent a document as a graph that connects relevant contexts regardless of distances.
Outcome: Experiments on IWSLT English–French, Chinese-English, WMT English–German and Opensubtitle English–Russian show that using document graphs can significantly improve translation quality.
Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination (D18-1)

Copied to clipboard

Challenge: Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model.
Approach: They propose to use mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains.
Outcome: The proposed model distinguishes and exploits word-level domain contexts on Chinese-English and English-French translation tasks.
One Sentence One Model for Neural Machine Translation (L18-1)

Copied to clipboard

Challenge: Neural machine translation (NMT) is a new state of the art that can produce better results than traditional statistical machine translation.
Approach: They propose a dynamic neural network which learns a general network as usual and fine-tunes it for each test sentence.
Outcome: The proposed method improves translation performance when similar sentences are available.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations