Standard

Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification. / Pronoza, Ekaterina; Yagunova, Elena.

в: Proceedings of the IEEE, 2015, стр. 74-82.

Результаты исследований: Научные публикации в периодических изданиях › статья

Harvard

Pronoza, E & Yagunova, E 2015, 'Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification', Proceedings of the IEEE, стр. 74-82. https://doi.org/10.1109/AINL-ISMW-FRUCT.2015.7382973

APA

Pronoza, E., & Yagunova, E. (2015). Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification. Proceedings of the IEEE, 74-82. https://doi.org/10.1109/AINL-ISMW-FRUCT.2015.7382973

Vancouver

Pronoza E, Yagunova E. Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification. Proceedings of the IEEE. 2015;74-82. https://doi.org/10.1109/AINL-ISMW-FRUCT.2015.7382973

Author

Pronoza, Ekaterina ; Yagunova, Elena. / Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification. в: Proceedings of the IEEE. 2015 ; стр. 74-82.

BibTeX

@article{061dbd0fbede4da1a5e21ac2c5c67865,
title = "Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification",
abstract = "In this paper we analyze and compare different types of sentence similarity measures by applying them to the problem of sentential paraphrase classification as features. We work with Russian, and all the experiments are conducted on the Russian paraphrase corpus we have collected from the news headlines (and are collecting at the moment). Apart from the similarity features, we also analyze the corpus itself. As a result of the research we disprove the supposition that it is more difficult to distinguish between precise and loose paraphrases than between loose paraphrases and non-paraphrases. We also come up with the recommendations for the application of different similarity measures to classifying paraphrases derived from the news texts.",
keywords = "sentence similarity measure shallow similarity semantic similarity dictionary-based similarity distributional semantic similarity vector space model paraphrase identification crowdsourcing technologies",
author = "Ekaterina Pronoza and Elena Yagunova",
year = "2015",
doi = "10.1109/AINL-ISMW-FRUCT.2015.7382973",
language = "English",
pages = "74--82",
journal = "Proceedings of the IEEE",
issn = "0018-9219",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Comparison of Sentence Similarity Measures as Features for Russian Paraphrase Identification

AU - Pronoza, Ekaterina

AU - Yagunova, Elena

PY - 2015

Y1 - 2015

N2 - In this paper we analyze and compare different types of sentence similarity measures by applying them to the problem of sentential paraphrase classification as features. We work with Russian, and all the experiments are conducted on the Russian paraphrase corpus we have collected from the news headlines (and are collecting at the moment). Apart from the similarity features, we also analyze the corpus itself. As a result of the research we disprove the supposition that it is more difficult to distinguish between precise and loose paraphrases than between loose paraphrases and non-paraphrases. We also come up with the recommendations for the application of different similarity measures to classifying paraphrases derived from the news texts.

AB - In this paper we analyze and compare different types of sentence similarity measures by applying them to the problem of sentential paraphrase classification as features. We work with Russian, and all the experiments are conducted on the Russian paraphrase corpus we have collected from the news headlines (and are collecting at the moment). Apart from the similarity features, we also analyze the corpus itself. As a result of the research we disprove the supposition that it is more difficult to distinguish between precise and loose paraphrases than between loose paraphrases and non-paraphrases. We also come up with the recommendations for the application of different similarity measures to classifying paraphrases derived from the news texts.

KW - sentence similarity measure shallow similarity semantic similarity dictionary-based similarity distributional semantic similarity vector space model paraphrase identification crowdsourcing technologies

U2 - 10.1109/AINL-ISMW-FRUCT.2015.7382973

DO - 10.1109/AINL-ISMW-FRUCT.2015.7382973

M3 - Article

SP - 74

EP - 82

JO - Proceedings of the IEEE

JF - Proceedings of the IEEE

SN - 0018-9219

ER -

ID: 5799587