Abstract

Determining the textual entailment between texts is important in many NLP tasks, such as summarization, question answering, and information extraction and retrieval. Various methods have been suggested based on external knowledge sources; however, such resources are not always available in all languages and their acquisition is typically laborious and very costly. Distributional word representations such as word embeddings learned over large corpora have been shown to capture syntactic and semantic word relationships. Such models have contributed to improving the performance of several NLP tasks. In this paper, we address the problem of textual entailment in Arabic. We employ both traditional features and distributional representations. Crucially, we do not depend on any external resources in the process. Our suggested approach yields state of the art performance on a standard data set, ArbTE, achieving an accuracy of 76.2 % compared to state of the art of 69.3 %.

Highlights

  • There have been a number of studies addressing the problem of Recognizing Textual Entailment (RTE)

  • Ferent way, wherein ETED systems the main focus was on the impact of Tree Edit Distance (TED) on the Arabic TE using different model extension, and in ATE and SANATE systems the focus was on the effect of negation and polarity on the Arabic TE

  • This paper shows our work to address the entailment relation in under-resourced languages, Arabic

Read more

Summary

Introduction

There have been a number of studies addressing the problem of Recognizing Textual Entailment (RTE). The core problem is to recognize semantic variability in textual expression, which can potentially have the same meaning (Dagan et al, 2010). Modeling this phenomenon has a significant impact on various NLP applications, such as question answering, machine translation, and summarization. In this paper, we propose an approach that does not rely on such external resources but rather on modeling word relations derived from large scale corpora.

Related Work
Features
Named Entity
Experiments and Result
Experimental Setup
Error Analysis and Discussion
Findings
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.