Using Sentence Semantic Similarity Based on WordNet in Recognizing Textual Entailment

Castillo, Julio Javier; Cardenas, Marina E.

doi:10.1007/978-3-642-16952-6_37

Cited by 6 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on their corpus, Marelli et al (2014) state that paraphrases, entailment, and contradiction have a high similarity score; paraphrases having the highest and contradiction the lowest of them. There also was practical work using the interaction between semantic similarity and entailment: Yokote et al (2011) and Castillo and Cardenas (2010) used semantic similarity to solve entailment.…”

Section: Interactions Between Relationsmentioning

confidence: 99%

Annotating and analyzing the interactions between meaning relations

Gold¹,

Kovatchev

Zesch

2019

Proceedings of the 13th Linguistic Annotation Workshop

View full text Add to dashboard Cite

Pairs of sentences, phrases, or other text pieces can hold semantic relations such as paraphrasing, textual entailment, contradiction, specificity, and semantic similarity. These relations are usually studied in isolation and no dataset exists where they can be compared empirically. Here we present a corpus annotated with these relations and the analysis of these results. The corpus contains 520 sentence pairs, annotated with these relations. We measure the annotation reliability of each individual relation and we examine their interactions and correlations. Among the unexpected results revealed by our analysis is that the traditionally considered direct relationship between paraphrasing and bi-directional entailment does not hold in our data.

show abstract

Section: Interactions Between Relationsmentioning

confidence: 99%

Annotating and analyzing the interactions between meaning relations

Gold¹,

Kovatchev

Zesch

2019

Proceedings of the 13th Linguistic Annotation Workshop

View full text Add to dashboard Cite

show abstract

“…At present, the evaluation of multilingual systems have been taking place in three main events: the Cross Language Evaluation Forum (CLEF), 6 the Text Retrieval Conference (TREC), 7 and the NTCIR (NII Test Collection for IR Systems) Project. 8 For now, there are no evaluation contests for CLTE systems.…”

Section: Cross-lingual Textual Entailmentmentioning

confidence: 99%

“…In Sect. 6 we provide an experimental evaluation and discussion of the results achieved in monolingual and crosslingual textual entailment. Finally, Sect.…”

Section: Introductionmentioning

confidence: 98%

“…In [6] the authors showed that some basic WordNet-based measures seem to be enough to build an average score RTE system. We extend these results showing an analysis of the most widely used WordNet-based measures to measure the semantic similarity between two concepts.…”

Section: Introductionmentioning

confidence: 99%

“…We also study some efficiency considerations in order to use these semantic measures in the RTE task practice. Additionally, we use the Pirro & Seco similarity measure, which is not contained in the WordNet::Similarity package, and a measure to compute sentence similarity used in [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A WordNet-based semantic approach to textual entailment and cross-lingual textual entailment

Castillo

2011

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

In this paper we explain how to build a recognizing textual entailment (RTE) system which only uses semantic similarity measures based on WordNet. We show how the widely used WordNet-based semantic measures can be generalized to build sentence level semantic metrics in order to be used in both mono-lingual and cross-lingual textual entailment. We experiment with a wide variety of RTE datasets and evaluate the contribution of an algorithm which expands the RTE monolingual corpus. Results achieved with this method yielded significant statistical differences when predicting RTE test sets. We provide an efficiency analysis of these metrics drawing some conclusions about their practical utility in recognizing textual entailment. We also analyze the cross-lingual textual entailment task, we create a bilingual English-Spanish corpus, and propose a procedure to create a cross-lingual textual entailment corpus for any pair of languages. Finally, we show that the proposed method is enough to build an average score RTE system in both monolingual and cross-lingual textual entailment, that uses semantic information from WordNet as the only source of lexicalsemantic knowledge.

show abstract

A Semantic Oriented Approach to Textual Entailment Using WordNet-Based Measures

Castillo

2010

Advances in Artificial Intelligence

View full text Add to dashboard Cite

Using Sentence Semantic Similarity Based on WordNet in Recognizing Textual Entailment

Cited by 6 publications

References 8 publications

Annotating and analyzing the interactions between meaning relations

Annotating and analyzing the interactions between meaning relations

A WordNet-based semantic approach to textual entailment and cross-lingual textual entailment

A Semantic Oriented Approach to Textual Entailment Using WordNet-Based Measures

Contact Info

Product

Resources

About