On Integrating Discourse in Machine Translation

Smith, Katherine

doi:10.18653/v1/w17-4814

Cited by 21 publications

(16 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discourse representation parsing has been gaining more attention lately. 1 The semantic analysis of text beyond isolated sentences can enhance various NLP applications such as information retrieval (Zou et al, 2014), summarization (Goyal and Eisenstein, 2016), conversational agents (Vinyals and Le, 2015), machine translation (Sim Smith, 2017;Bawden et al, 2018), and question anwsering (Rajpurkar et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Discourse Representation Parsing for Sentences and Documents

Liu

Cohen

Lapata

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

We introduce a novel semantic parsing task based on Discourse Representation Theory (DRT; Kamp and Reyle 1993). Our model operates over Discourse Representation Tree Structures which we formally define for sentences and documents. We present a general framework for parsing discourse structures of arbitrary length and granularity. We achieve this with a neural model equipped with a supervised hierarchical attention mechanism and a linguistically-motivated copy strategy. Experimental results on sentence-and documentlevel benchmarks show that our model outperforms competitive baselines by a wide margin.

show abstract

Section: Introductionmentioning

confidence: 99%

Discourse Representation Parsing for Sentences and Documents

Liu

Cohen

Lapata

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Linguistically, long-distance dependencies often arise from discourse-level phenomena such as pronominal reference, lexical cohesion, text structure, etc. Initially largely ignored, such problems have attracted increasing attention in the statistical MT (SMT) community in recent years (Hardmeier, 2012;Sim Smith, 2017). One important problem that has proved to be surprisingly difficult despite extensive research is the translation of pronouns Loáiciga et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018

Guillou¹,

Hardmeier²,

Lapshinova-Koltunski³

et al. 2018

Proceedings of the Third Conference on Machine Translation: Shared Task Papers

View full text Add to dashboard Cite

We evaluate the output of 16 English-to-German MT systems with respect to the translation of pronouns in the context of the WMT 2018 competition. We work with a test suite specifically designed to assess system quality in various fine-grained categories known to be problematic. The main evaluation scores come from a semi-automatic process, combining automatic reference matching with extensive manual annotation of uncertain cases. We find that current NMT systems are good at translating pronouns with intra-sentential reference, but the inter-sentential cases remain difficult. NMT systems are also good at the translation of event pronouns, unlike systems from the phrase-based SMT paradigm. No single system performs best at translating all types of anaphoric pronouns, suggesting unexplained random effects influencing the translation of pronouns with NMT.

show abstract

“…Research about discourse and MT has shifted from explicitly enhancing systems with discourse knowledge to evaluating how much the systems have learned specific discourse features through different resources, test suites being a popular one (cf. Sim Smith, 2017;Popescu-Belis, 2019). Throughout, however, particular discourse phenomena are consistently targeted, as they are indeed indicators of globally good, cohesive and coherent texts.…”

Section: Related Work 21 Discoursementioning

confidence: 99%

Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)

2019

View full text Add to dashboard Cite

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 performance on two different genres: news and TED talks. To do this, we manually annotate (the possibly incorrect) coreference chains in the MT outputs and evaluate the coreference chain translations. We define an error typology that aims to go further than pronoun translation adequacy and includes types such as incorrect word selection or missing words. The features of coreference chains in automatic translations are also compared to those of the source texts and human translations. The analysis shows stronger potential translationese effects in machine translated outputs than in human translations.

show abstract

On Integrating Discourse in Machine Translation

Cited by 21 publications

References 42 publications

Discourse Representation Parsing for Sentences and Documents

Discourse Representation Parsing for Sentences and Documents

A Pronoun Test Suite Evaluation of the English–German MT Systems at WMT 2018

Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)

Contact Info

Product

Resources

About