Random Walks for Text Semantic Similarity

Many tasks in NLP stand to benefit from robust measures of semantic similarity for units above the level of individual words. Rich semantic resources such as WordNet provide local semantic information at the lexical level. However, effectively combining this information to compute scores for phrases or sentences is an open problem. Our algorithm aggregates local relatedness information via a random walk over a graph constructed from an underlying lexical resource. The stationary distribution of the graph walk forms a "semantic signature" that can be compared to another such distribution to get a relat-edness score for texts. On a paraphrase recognition task, the algorithm achieves an 18.5% relative reduction in error rate over a vector-space baseline. We also show that the graph walk similarity between texts has complementary value as a feature for recognizing textual entailment, improving on a competitive baseline system.

[1]  Patrick F. Reidy.  An Introduction to Latent Semantic Analysis , 2009 .

[2]  Paola Velardi,et al.  Structural semantic interconnections: a knowledge-based approach to word sense disambiguation , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Kevyn Collins-Thompson,et al.  Query expansion using random walk models , 2005, CIKM '05.

[4]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[5]  Ido Dagan,et al.  Web Based Probabilistic Textual Entailment , 2005 .

[6]  Eneko Agirre,et al.  Personalizing PageRank for Word Sense Disambiguation , 2009, EACL.

[7]  Thad Hughes,et al.  Lexical Semantic Relatedness with Random Graph Walks , 2007, EMNLP.

[8]  Graeme Hirst,et al.  Evaluating WordNet-based Measures of Lexical Semantic Relatedness , 2006, CL.

[9]  John D. Lafferty,et al.  Information retrieval as statistical translation , 1999, SIGIR '99.

[10]  Chris Quirk,et al.  Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources , 2004, COLING.

[11]  Michael E. Lesk,et al.  Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone , 1986, SIGDOC '86.

[12]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[13]  Rada Mihalcea,et al.  Measuring the Semantic Similarity of Texts , 2005, EMSEE@ACL.

[14]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[15]  Taher H. Haveliwala.  Topic-sensitive PageRank , 2002, IEEE Trans. Knowl. Data Eng..

[16]  Vladimir I. Levenshtein,et al.  Binary codes capable of correcting deletions, insertions, and reversals , 1965 .

[17]  Lillian Lee,et al.  On the effectiveness of the skew divergence for statistical language analysis , 2001, AISTATS.

[18]  John A. Carroll,et al.  Applied morphological processing of English , 2001, Natural Language Engineering.

[19]  William W. Cohen,et al.  Learning to rank typed graph walks: local and global approaches , 2007, WebKDD/SNA-KDD '07.

[20]  James Richard Curran,et al.  From distributional to semantic similarity , 2004 .

[21]  Miguel Ángel García Cumbreras,et al.  Combining Lexical-Syntactic Information with Machine Learning for Recognizing Textual Entailment , 2007, ACL-PASCAL@ACL.

[22]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

[23]  Eric Yeh,et al.  Learning Alignments and Leveraging Natural Logic , 2007, ACL-PASCAL@ACL.

[24]  Pavel Berkhin,et al.  A Survey on PageRank Computing , 2005, Internet Math..

[25]  Stan Szpakowicz,et al.  Roget's thesaurus and semantic similarity , 2012, RANLP.

[26]  Daniel Jurafsky,et al.  Semantic Taxonomy Induction from Heterogenous Evidence , 2006, ACL.

[27]  Carlo Strapparava,et al.  Corpus-based and Knowledge-based Measures of Text Semantic Similarity , 2006, AAAI.

[28]  David W. Conrath,et al.  Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy , 1997, ROCLING/IJCLCLP.

[29]  Philip Resnik,et al.  Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language , 1999, J. Artif. Intell. Res..