The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis

Mihai Lintean, Cristian Moldovan, Vasile Rus, Danielle McNamara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Citations (Scopus)

Abstract

In this paper, we investigate the impact of several local and global weighting schemes on Latent Semantic Analysis' (LSA) ability to capture semantic similarity between two texts. We worked with texts varying in size from sentences to paragraphs. We present a comparison of 3 local and 3 global weighting schemes across 3 different standardized data sets related to semantic similarity tasks. For local weighting, we used binary weighting, term-frequency, and log-type. For global weighting, we relied on binary, inverted document frequencies (IDF) collected from the English Wikipedia, and entropy, which is the standard weighting scheme used by most LSA-based applications. We studied all possible combinations of these weighting schemes on the following three tasks and corresponding data sets: paraphrase identification at sentence level using the Microsoft Research Paraphrase Corpus, paraphrase identification at sentence level using data from the intelligent tutoring system iSTART, and mental model detection based on student-articulated paragraphs in MetaTutor, another intelligent tutoring system. Our experiments revealed that for sentence-level texts a combination of type frequency local weighting in combination with either IDF or binary global weighting works best. For paragraph-level texts, a log-type local weighting in combination with binary global weighting works best. We also found that global weights have a greater impact for sententence-level similarity as the local weight is undermined by the small size of such texts.

Original languageEnglish (US)
Title of host publicationProceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23
Pages235-240
Number of pages6
StatePublished - 2010
Externally publishedYes
Event23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23 - Daytona Beach, FL, United States
Duration: May 19 2010May 21 2010

Other

Other23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23
CountryUnited States
CityDaytona Beach, FL
Period5/19/105/21/10

Fingerprint

Semantics
Intelligent systems
Entropy
Students
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Lintean, M., Moldovan, C., Rus, V., & McNamara, D. (2010). The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis. In Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23 (pp. 235-240)

The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis. / Lintean, Mihai; Moldovan, Cristian; Rus, Vasile; McNamara, Danielle.

Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23. 2010. p. 235-240.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lintean, M, Moldovan, C, Rus, V & McNamara, D 2010, The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis. in Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23. pp. 235-240, 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23, Daytona Beach, FL, United States, 5/19/10.
Lintean M, Moldovan C, Rus V, McNamara D. The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis. In Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23. 2010. p. 235-240
Lintean, Mihai ; Moldovan, Cristian ; Rus, Vasile ; McNamara, Danielle. / The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis. Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23. 2010. pp. 235-240
@inproceedings{32470843286d42c98902debec1d307aa,
title = "The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis",
abstract = "In this paper, we investigate the impact of several local and global weighting schemes on Latent Semantic Analysis' (LSA) ability to capture semantic similarity between two texts. We worked with texts varying in size from sentences to paragraphs. We present a comparison of 3 local and 3 global weighting schemes across 3 different standardized data sets related to semantic similarity tasks. For local weighting, we used binary weighting, term-frequency, and log-type. For global weighting, we relied on binary, inverted document frequencies (IDF) collected from the English Wikipedia, and entropy, which is the standard weighting scheme used by most LSA-based applications. We studied all possible combinations of these weighting schemes on the following three tasks and corresponding data sets: paraphrase identification at sentence level using the Microsoft Research Paraphrase Corpus, paraphrase identification at sentence level using data from the intelligent tutoring system iSTART, and mental model detection based on student-articulated paragraphs in MetaTutor, another intelligent tutoring system. Our experiments revealed that for sentence-level texts a combination of type frequency local weighting in combination with either IDF or binary global weighting works best. For paragraph-level texts, a log-type local weighting in combination with binary global weighting works best. We also found that global weights have a greater impact for sententence-level similarity as the local weight is undermined by the small size of such texts.",
author = "Mihai Lintean and Cristian Moldovan and Vasile Rus and Danielle McNamara",
year = "2010",
language = "English (US)",
isbn = "9781577354475",
pages = "235--240",
booktitle = "Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23",

}

TY - GEN

T1 - The role of local and global weighting in assessing the semantic similarity of texts using latent semantic analysis

AU - Lintean, Mihai

AU - Moldovan, Cristian

AU - Rus, Vasile

AU - McNamara, Danielle

PY - 2010

Y1 - 2010

N2 - In this paper, we investigate the impact of several local and global weighting schemes on Latent Semantic Analysis' (LSA) ability to capture semantic similarity between two texts. We worked with texts varying in size from sentences to paragraphs. We present a comparison of 3 local and 3 global weighting schemes across 3 different standardized data sets related to semantic similarity tasks. For local weighting, we used binary weighting, term-frequency, and log-type. For global weighting, we relied on binary, inverted document frequencies (IDF) collected from the English Wikipedia, and entropy, which is the standard weighting scheme used by most LSA-based applications. We studied all possible combinations of these weighting schemes on the following three tasks and corresponding data sets: paraphrase identification at sentence level using the Microsoft Research Paraphrase Corpus, paraphrase identification at sentence level using data from the intelligent tutoring system iSTART, and mental model detection based on student-articulated paragraphs in MetaTutor, another intelligent tutoring system. Our experiments revealed that for sentence-level texts a combination of type frequency local weighting in combination with either IDF or binary global weighting works best. For paragraph-level texts, a log-type local weighting in combination with binary global weighting works best. We also found that global weights have a greater impact for sententence-level similarity as the local weight is undermined by the small size of such texts.

AB - In this paper, we investigate the impact of several local and global weighting schemes on Latent Semantic Analysis' (LSA) ability to capture semantic similarity between two texts. We worked with texts varying in size from sentences to paragraphs. We present a comparison of 3 local and 3 global weighting schemes across 3 different standardized data sets related to semantic similarity tasks. For local weighting, we used binary weighting, term-frequency, and log-type. For global weighting, we relied on binary, inverted document frequencies (IDF) collected from the English Wikipedia, and entropy, which is the standard weighting scheme used by most LSA-based applications. We studied all possible combinations of these weighting schemes on the following three tasks and corresponding data sets: paraphrase identification at sentence level using the Microsoft Research Paraphrase Corpus, paraphrase identification at sentence level using data from the intelligent tutoring system iSTART, and mental model detection based on student-articulated paragraphs in MetaTutor, another intelligent tutoring system. Our experiments revealed that for sentence-level texts a combination of type frequency local weighting in combination with either IDF or binary global weighting works best. For paragraph-level texts, a log-type local weighting in combination with binary global weighting works best. We also found that global weights have a greater impact for sententence-level similarity as the local weight is undermined by the small size of such texts.

UR - http://www.scopus.com/inward/record.url?scp=77957867916&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957867916&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354475

SP - 235

EP - 240

BT - Proceedings of the 23rd International Florida Artificial Intelligence Research Society Conference, FLAIRS-23

ER -