Analysis of Sentential Paraphrase Patterns and Errors through Predicate-Argument Tuple-based Approximate Alignment


The KIPS Transactions:PartB , Vol. 19, No. 2, pp. 135-148, Apr. 2012
10.3745/KIPSTB.2012.19.2.135,   PDF Download:

Abstract

This paper proposes a model for recognizing sentential paraphrases through Predicate-Argument Tuple (PAT)-based approximate alignment between two texts. We cast the paraphrase recognition problem as a binary classification by defining and applying various alignment features which could effectively express the semantic relatedness between two sentences. Experiment confirmed the potential of our approach and error analysis revealed various paraphrase patterns not being solved by our system, which can help us devise methods for further performance improvement.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. P. Choi, S. K. Song, S. H. Myaeng, "Analysis of Sentential Paraphrase Patterns and Errors through Predicate-Argument Tuple-based Approximate Alignment," The KIPS Transactions:PartB , vol. 19, no. 2, pp. 135-148, 2012. DOI: 10.3745/KIPSTB.2012.19.2.135.

[ACM Style]
Sung Pil Choi, Sa Kwang Song, and Sung Hyon Myaeng. 2012. Analysis of Sentential Paraphrase Patterns and Errors through Predicate-Argument Tuple-based Approximate Alignment. The KIPS Transactions:PartB , 19, 2, (2012), 135-148. DOI: 10.3745/KIPSTB.2012.19.2.135.