TextFlow: A Text Similarity Measure based on Continuous Sequences

Yassine Mrabet, Halil Kilicoglu, Dina Demner-Fushman


Abstract
Text similarity measures are used in multiple tasks such as plagiarism detection, information ranking and recognition of paraphrases and textual entailment. While recent advances in deep learning highlighted the relevance of sequential models in natural language generation, existing similarity measures do not fully exploit the sequential nature of language. Examples of such similarity measures include n-grams and skip-grams overlap which rely on distinct slices of the input texts. In this paper we present a novel text similarity measure inspired from a common representation in DNA sequence alignment algorithms. The new measure, called TextFlow, represents input text pairs as continuous curves and uses both the actual position of the words and sequence matching to compute the similarity value. Our experiments on 8 different datasets show very encouraging results in paraphrase detection, textual entailment recognition and ranking relevance.
Anthology ID:
P17-1071
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
763–772
Language:
URL:
https://aclanthology.org/P17-1071
DOI:
10.18653/v1/P17-1071
Bibkey:
Cite (ACL):
Yassine Mrabet, Halil Kilicoglu, and Dina Demner-Fushman. 2017. TextFlow: A Text Similarity Measure based on Continuous Sequences. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 763–772, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
TextFlow: A Text Similarity Measure based on Continuous Sequences (Mrabet et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1071.pdf
Video:
 https://aclanthology.org/P17-1071.mp4
Data
SNLI