?
SumTitles: a Summarization Dataset with Low Extractiveness
Ch. 503. P. 5718-5730.
Malykh V., Chernis K., Artemova E., Piontkovskaya I.
The existing dialogue summarization corpora are significantly extractive. We introduce a methodology for dataset extractiveness evaluation and present a new low-extractive corpus of movie dialogues for abstractive text summarization along with baseline evaluation. The corpus contains 153k dialogues and consists of three parts: 1) automatically aligned subtitles, 2) automatically aligned scenes from scripts, and 3) manually aligned scenes from scripts. We also present an alignment algorithm which we use to construct the corpus.
Publication based on the results of:
In book
International Committee on Computational Linguistics, 2020
Anwar S., Ustalov D., Arefyev N. et al., , in : Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019). : Minneapolis : Association for Computational Linguistics, 2019. P. 125-129.
We present our system for semantic frame induction that showed the best performance in Subtask B.1 and finished as the runner-up in Subtask A of the SemEval 2019 Task 2 on unsupervised semantic frame induction (Qasem-iZadeh et al., 2019). Our approach separates this task into two independent steps: verb clustering using word and their context ...
Added: October 10, 2020
Smetanin S., Mikhail Komarov, PeerJ Computer Science 2022 Vol. 8 Article e1181
As one of the major platforms of communication, social networks have become a valuable source of opinions and emotions. Considering that sharing of emotions offline and online is quite similar, historical posts from social networks seem to be a valuable source of data for measuring observable subjective well-being (OSWB). In this study, we calculated OSWB ...
Added: December 29, 2022
Arefyev, N, Boris S., Aleksashina T., , in : Analysis of Images, Social Networks and Texts. 8th International Conference, AIST 2019, Lecture Notes in Computer Science, Revised Selected Papers. Vol. 11832.: Cham : Springer, 2019. P. 105-121.
Word sense induction (WSI) is the problem of grouping occurrences of an ambiguous word according to the expressed sense of this word. Recently a new approach to this task was proposed, which generates possible substitutes for the ambiguous word in a particular context using neural language models, and then clusters sparse bag-of-words vectors built from ...
Added: October 9, 2020
Nikolay Arefyev, Sheludko B., Podolskiy A. et al., , in : Proceedings of the 28th International Conference on Computational Linguistics. : International Committee on Computational Linguistics, 2020. P. 1242-1255.
Lexical substitution, i.e. generation of plausible words that can replace a particular target word in a given context, is an extremely powerful technology that can be used as a backbone of various NLP applications, including word sense induction and disambiguation, lexical relation extraction, data augmentation, etc. In this paper, we present a large-scale comparative study ...
Added: December 7, 2020
Kanovich M., Kuznetsov S., Scedrov A., , in : Logic, Language, Information, and Computation: 26th International Workshop, WoLLIC 2019, Utrecht, The Netherlands, July 2-5, 2019, Proceedings. Vol. 11541: Lecture Notes in Computer Science.: Berlin, Heidelberg : Springer, 2019. P. 373-391.
Language and relational models, or L-models and R-models, are two natural classes of models for the Lambek calculus. Completeness w.r.t. L-models was proved by Pentus and completeness w.r.t. R-models by Andréka and Mikulás. It is well known that adding both additive conjunction and disjunction together yields incompleteness, because of the distributive law. The product-free Lambek ...
Added: September 4, 2019
Struyanskiy O., Arefyev, N., , in : Supplementary Proceedings of the 7th International Conference on Analysis of Images, Social Networks and Texts (AIST-SUP 2018), Moscow, Russia, July 5-7, 2018. : Aachen : CEUR Workshop Proceedings, 2018. P. 208-213.
Attentional neural networks have achieved remarkable results for a number of tasks in the past few years. The fascinating success of neural networks with attention mechanism in natural language processing, especially in machine translation, suggests that these models can capture the meaning of ambiguous words considering their context. In this paper we introduce a new ...
Added: October 9, 2020
Nikolay Arefyev, Boris S., Panchenko A., , in : Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2019. : INCOMA Ltd, 2019. P. 62-70.
Word Sense Induction (WSI) is the task of grouping of occurrences of an ambiguous word according to their meaning. In this work, we improve the approach to WSI proposed by Amrami and Goldberg (2018) based on clustering of lexical substitutes for an ambiguous word in a particular context obtained from neural language models. Namely, we ...
Added: October 9, 2020
Arefyev Nikolay, Sheludko B., Adis D. et al., , in : Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019). : Minneapolis : Association for Computational Linguistics, 2019. P. 31-38.
We describe our solutions for semantic frame and role induction subtasks of SemEval 2019 Task 2. Our approaches got the highest scores, and the solution for the frame induction problem officially took the first place. The main contributions of this paper are related to the semantic frame induction problem. We propose a combined approach that ...
Added: October 10, 2020
Lopukhina Anastasia, Pletenev S., Nikiforova A. et al., , in : Proceedings of the Second Workshop on Linguistic and Neurocognitive Resources. : Marseille : European Language Resources Association (ELRA), 2020. P. 28-37.
Linguistics predictability is the degree of confidence in which language unit (word, part of speech, etc.) will be the next in the sequence. Experiments have shown that the correct prediction simplifies the perception of a language unit and its integration into the context. As a result of an incorrect prediction, language processing slows down. Currently, ...
Added: April 20, 2021
Arefyev N V., Fedoseev M., Kabanov A. et al., , in : Компьютерная лингвистика и интеллектуальные технологии: по материалам ежегодной международной конференции «Диалог» (Москва, 17–20 июня 2020 г.). Issue 19(26): дополнительный том.: -, 2020. P. 13-32.
Expert-built lexical resources are known to provide information of good quality for the cost of low coverage. This property limits their applicability in modern NLP applications. Building descriptions of lexical-semantic relations manually in sufficient volume requires a huge amount of qualified human labour. However, given some initial version of a taxonomy is already built, automatic ...
Added: October 9, 2020