Hybrid Simplification using Deep Semantics and Machine Translation

Narayan, Shashi; Gardent, Claire

doi:10.3115/v1/p14-1041

Cited by 110 publications

(151 citation statements)

References 17 publications

Supporting

Mentioning

147

Contrasting

Order By: Relevance

“…We believe UCCA's merits in providing a cross-linguistically applicable, broadcoverage annotation will support ongoing efforts to incorporate deeper semantic structures into various applications, such as sentence simplification (Narayan and Gardent, 2014) and summarization (Liu et al, 2015).…”

Section: Resultsmentioning

confidence: 97%

A Transition-Based Directed Acyclic Graph Parser for UCCA

Hershcovich¹,

Abend²,

Rappoport³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

109

View full text Add to dashboard Cite

We present the first parser for UCCA, a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques, as it exhibits reentrancy (resulting in DAG structures), discontinuous structures and non-terminal nodes corresponding to complex semantic units. To our knowledge, the conjunction of these formal properties is not supported by any existing parser. Our transition-based parser, which uses a novel transition set and features based on bidirectional LSTMs, has value not just for UCCA parsing: its ability to handle more general graph structures can inform the development of parsers for other semantic DAG structures, and in languages that frequently use discontinuous structures.

show abstract

Section: Resultsmentioning

confidence: 97%

A Transition-Based Directed Acyclic Graph Parser for UCCA

Hershcovich¹,

Abend²,

Rappoport³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

109

View full text Add to dashboard Cite

show abstract

“…We have also incorporated features that related previous works have found to be beneficial (Štajner et al, 2013;Narayan and Gardent, 2014). The following is a brief description of our feature set.…”

Section: A Ml-based Methodsmentioning

confidence: 99%

“…The density of punctuation per sentence shows that definitions are more fragmented. These factors are problematic for sentence compression techniques that rely heavily on the syntactic parse trees of complete, well-formed sentences (Cohn and Lapata, 2009;Narayan and Gardent, 2014). One recent compression method that does not rely as heavily on syntax is the work of Filippova et al (2015).…”

Section: Introductionmentioning

confidence: 99%

Phrasal Substitution of Idiomatic Expressions

Liu

Hwa

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Idioms pose a great challenge to natural language understanding. A system that can automatically paraphrase idioms in context has applications in many NLP tasks. This paper proposes a phrasal substitution method to replace idioms with their figurative meanings in literal English. Our approach identifies relevant replacement phrases from an idiom's dictionary definition and performs appropriate grammatical and referential transformations to ensure that the idiom substitution fits seamlessly into the original context. The proposed method has been evaluated both by automatic metrics and human judgments. Results suggest that high quality paraphrases of idiomatic expressions can be achieved.

show abstract

“…However simplification by repackaging the content into multiple sentences is not naturally compatible with the standard view of statistical MT in which a system is expected to produce a single output sentence for a single input sentence. Some of the recent systems using MT techniques separately model the need for sentence splitting (Zhu et al, 2010;Woodsend and Lapata, 2011;Narayan and Gardent, 2014). Identifying heavy sentences in simplification is equivalent to identifying sentences that require syntactic simplification.…”

Section: Related Workmentioning

confidence: 99%

Detecting Content-Heavy Sentences: A Cross-Language Case Study

Nenkova

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

The information conveyed by some sentences would be more easily understood by a reader if it were expressed in multiple sentences. We call such sentences content heavy: these are possibly grammatical but difficult to comprehend, cumbersome sentences. In this paper we introduce the task of detecting content-heavy sentences in cross-lingual context. Specifically we develop methods to identify sentences in Chinese for which English speakers would prefer translations consisting of more than one sentence. We base our analysis and definitions on evidence from multiple human translations and reader preferences on flow and understandability. We show that machine translation quality when translating content heavy sentences is markedly worse than overall quality and that this type of sentence are fairly common in Chinese news. We demonstrate that sentence length and punctuation usage in Chinese are not sufficient clues for accurately detecting heavy sentences and present a richer classification model that accurately identifies these sentences.

show abstract

Hybrid Simplification using Deep Semantics and Machine Translation

Cited by 110 publications

References 17 publications

A Transition-Based Directed Acyclic Graph Parser for UCCA

A Transition-Based Directed Acyclic Graph Parser for UCCA

Phrasal Substitution of Idiomatic Expressions

Detecting Content-Heavy Sentences: A Cross-Language Case Study

Contact Info

Product

Resources

About