Syntactic/Semantic Structures for Textual Entailment Recognition

By Yashar Mehdad, Alessandro Moschitti, Fabio Massimo Zanzotto. 2010

37 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference (2019, methodology): “Our focus on using NLI to address how models understand structure follows some older work about using NLI for the evaluation of parsers (Rimell and Clark, 2010; Mehdad et al., 2010).”
Enhanced LSTM for Natural Language Inference (2016, background): “Complicated tasks such as natural language inference could well involve both, which has been discussed in the context of recognizing textual entailment (RTE) (Mehdad et al., 2010; Ferrone and Zanzotto, 2014).”
Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference (2016, background): “Complicated tasks such as natural language inference could well involve both, which has been discussed in the context of recognizing textual entailment (RTE) (Mehdad et al., 2010; Ferrone and Zanzotto, 2014).”
Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information (2018, methodology): “Earlier approaches of sentence matching mainly relied on conventional methods such as syntactic features, transformations or relation extraction [30, 19, 39, 22].”
Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, methodology): “Although this kernel achieves state-of-the-art performance in NLP tasks, such as Question Classiﬁca-tion (Bloehdorn and Moschitti, 2007b) and Textual Entailment (Mehdad et al., 2010), it offers clearly possibility of improvement: (i) better possibility to exploit semantic smoothing since, e.g., triv”
Using Bilingual Parallel Corpora for Cross-Lingual Textual Entailment (2011, methodology): “However, due to their relatively small number (especially for some languages), bilingual lexicons extracted from Wikipedia are still inadequate to provide acceptable coverage.”