Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
ParaPhraser : Russian paraphrase corpus and shared task. / Pivovarova, Lidia; Pronoza, Ekaterina; Yagunova, Elena; Pronoza, Anton.
Artificial Intelligence and Natural Language - 6th Conference, AINL 2017, Revised Selected Papers. Vol. 789 CCIS Springer, Cham. ed. Springer Nature, 2018. p. 211-225 (Communications in Computer and Information Science; Vol. 789).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - ParaPhraser
T2 - 6th Conference on Artificial Intelligence and Natural Language, AINL 2017
AU - Pivovarova, Lidia
AU - Pronoza, Ekaterina
AU - Yagunova, Elena
AU - Pronoza, Anton
N1 - Pivovarova L., Pronoza E., Yagunova E., Pronoza A. (2018) ParaPhraser: Russian Paraphrase Corpus and Shared Task. In: Filchenkov A., Pivovarova L., Žižka J. (eds) Artificial Intelligence and Natural Language. AINL 2017. Communications in Computer and Information Science, vol 789. Springer, Cham
PY - 2018
Y1 - 2018
N2 - The paper describes the results of the First Russian Paraphrase Detection Shared Task held in St.-Petersburg, Russia, in October 2016. Research in the area of paraphrase extraction, detection and generation has been successfully developing for a long time while there has been only a recent surge of interest towards the problem in the Russian community of computational linguistics. We try to overcome this gap by introducing the project ParaPhraser.ru dedicated to the collection of Russian paraphrase corpus and organizing a Paraphrase Detection Shared Task, which uses the corpus as the training data. The participants of the task applied a wide variety of techniques to the problem of paraphrase detection, from rule-based approaches to deep learning, and results of the task reflect the following tendencies: the best scores are obtained by the strategy of using traditional classifiers combined with fine-grained linguistic features, however, complex neural networks, shallow methods and purely technical methods also demonstrate competitive results.
AB - The paper describes the results of the First Russian Paraphrase Detection Shared Task held in St.-Petersburg, Russia, in October 2016. Research in the area of paraphrase extraction, detection and generation has been successfully developing for a long time while there has been only a recent surge of interest towards the problem in the Russian community of computational linguistics. We try to overcome this gap by introducing the project ParaPhraser.ru dedicated to the collection of Russian paraphrase corpus and organizing a Paraphrase Detection Shared Task, which uses the corpus as the training data. The participants of the task applied a wide variety of techniques to the problem of paraphrase detection, from rule-based approaches to deep learning, and results of the task reflect the following tendencies: the best scores are obtained by the strategy of using traditional classifiers combined with fine-grained linguistic features, however, complex neural networks, shallow methods and purely technical methods also demonstrate competitive results.
KW - корпус парафраз
KW - распознавание парафраз
KW - русские парафразы
KW - дорожка по распознаванию парафраз
KW - Paraphrase corpus
KW - Paraphrase detection
KW - Russian paraphrase
KW - Shared task
UR - http://www.scopus.com/inward/record.url?scp=85037545952&partnerID=8YFLogxK
UR - http://www.mendeley.com/research/paraphraser-russian-paraphrase-corpus-shared-task
U2 - https://doi.org/10.1007/978-3-319-71746-3_18
DO - https://doi.org/10.1007/978-3-319-71746-3_18
M3 - Conference contribution
AN - SCOPUS:85037545952
SN - 9783319717456
VL - 789
T3 - Communications in Computer and Information Science
SP - 211
EP - 225
BT - Artificial Intelligence and Natural Language - 6th Conference, AINL 2017, Revised Selected Papers
PB - Springer Nature
Y2 - 19 September 2017 through 22 September 2017
ER -
ID: 11888226