Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments
Cross-sentence context can provide valuable information in Machine Translation and is critical for translation of anaphoric pronouns and for providing consistent translations. In this paper, we devise simple oracle experiments targeting coreference and coherence. Oracles are an easy way to evaluate the effect of different discourse-level phenomena in NMT using BLEU and eliminate the necessity to manually define challenge sets for this purpose. We propose two context-aware NMT models and compare them against models working on a concatenation of consecutive sentences. Concatenation models perform better, but are computationally expensive. We show that NMT models taking advantage of context oracle signals can achieve considerable gains in BLEU, of up to 7.02 BLEU for coreference and 1.89 BLEU for coherence on subtitles translation. Access to strong signals allows us to make clear comparisons between context-aware models.
Code (0)
등록된 구현이 없습니다.
Tasks
Coreference ResolutionLanguage ModelingLanguage ModellingMachine TranslationNMTSentenceTranslationSimilar Papers 제목 키워드 기반
Evaluating Discourse Phenomena in Neural Machine Translation
For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models h…
Machine TranslationNMTSentenceTranslationLazy Low-Resource Coreference Resolution: a Study on Leveraging Black-Box Translation Tools
Large annotated corpora for coreference resolution are available for few languages. For machine translation, however, strong black-box systems exist for many languages. We empirically explore the appealing idea of levera…
coreference-resolutionCoreference ResolutionMachine TranslationTranslationAnalysing Coreference in Transformer Outputs
We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information. We compare system pe…
Machine TranslationTranslationContext-Aware Neural Machine Translation Learns Anaphora Resolution
Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coheren…
Machine TranslationTranslationUsing Coreference Links to Improve Spanish-to-English Machine Translation
In this paper, we present a proof-of-concept implementation of a coreference-aware decoder for document-level machine translation. We consider that better translations should have coreference links that are closer to tho…
Coreference ResolutionDecoderDiversityDocument Level Machine Translation+3