?
Language Models for Cloze Task Answer Generation in Russian
P. 28–37.
Lopukhina Anastasia, Pletenev S., Nikiforova A., Sinitsyna D., Sorokin S.
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, to get a measure of the language unit predictability, a neurolinguistic experiment known as a cloze task has to be conducted on a large number of participants. Cloze tasks are resource-consuming and are criticized by some researchers as an insufficiently valid measure of predictability. In this paper, we compare different language models that attempt to simulate human respondents’ performance on the cloze task. Using a language model to create cloze task simulations would require significantly less time and conduct studies related to linguistic predictability.
In book
Marseille: European Language Resources Association (ELRA), 2020.
Alexeeva M., Myachykov A., Бермудез-Маргаретто Б. et al., Brain Research 2024 Article 1836
Automatic parsing of syntactic information by the human brain is a well-established phenomenon, but its mechanisms remain poorly understood. Its best-known neurophysiological reflection is the so-called early left-anterior negativity (ELAN) component of event-related potentials (ERPs), with two alternative hypotheses for its origin: (1) error detection, or (2) morphosyntactic prediction/priming. To test these alternatives, we conducted ...
Added: December 10, 2024
Kirill Romanyuk, Sarvar Anvarov, Mark Shumilov et al., Complexity 2023 Vol. 2023 Article 7572061
The COVID-19 pandemic affected financial instruments and markets all around the world. Credit default swap contracts of EU companies were analysed in this paper. The data consist of daily credit default swap spreads and market capitalisations of EU companies, exchange rates, LIBOR rates, bond yields, and commodity futures prices from January 2010 to February 2022. ...
Added: December 24, 2023
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
Pimenova N., Известия РАН. Серия литературы и языка 2022 Т. 81 № 5 С. 110–114
. ...
Added: October 4, 2022
Pan J., Yan M., Richter E. M. et al., Behavior Research Methods 2022 Vol. 54 No. 4 P. 1989–2000
This report introduces the Beijing Sentence Corpus (BSC). This is a Chinese sentence corpus of eye-tracking data with relatively clear word boundaries. In addition, we report predictability norms for each word in the corpus. Eye movement corpora are available in alphabetic scripts such as English, German, and French. However, there is no publicly available corpus ...
Added: December 23, 2021
Lopukhina A., Lopukhin K., Laurinavichyute A., Plos One 2021 Vol. 16 No. 1 P. 1–26
During reading or listening, people can generate predictions about the lexical and morphosyntactic properties of upcoming input based on available context. Psycholinguistic experiments that study predictability or control for it conventionally rely on a human-based approach and estimate predictability via the cloze task. Our study investigated an alternative corpus-based approach for estimating predictability via language ...
Added: January 29, 2021
Petrovskiy V., Андреева А. И., Мир психологии. Научно-методический журнал 2018 № №3 (95) С. 224–232
The article discusses the problems of criteria for assessing the importance of scientific facts in psycho- logy, as well as the accuracy of expert assessments of psychologists predicting the results of psychological experiments. The personal approach of V. A. Petrovskiy is presented, which estimates the nontriviality of scientific facts. The principle of analyzing the nontriviality ...
Added: January 10, 2021
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
Malykh V., Chernis K., Artemova E. et al., , in: Proceedings of the 28th International Conference on Computational Linguistics.: International Committee on Computational Linguistics, 2020. Ch. 503 P. 5718–5730.
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) ...
Added: December 6, 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
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
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
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
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 PapersVol. 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, 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
Kanovich M., Kuznetsov S., Scedrov A., , in: Logic, Language, Information, and Computation: 26th International Workshop, WoLLIC 2019, Utrecht, The Netherlands, July 2-5, 2019, ProceedingsVol. 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
Khlinova O. V., Yasnitsky L., Skachkova I. V., , in: Advances in Intelligent Systems and ComputingVol. 850: Digital Science.: Switzerland: Springer, 2019. P. 359–365.
This article describes development experience of the neural network
system for medical diagnostic of gastrointestinal diseases. There was used
patient’s practical medical information for its creation. As input parameters were
taken into consideration different factor groups, include demographic, patient’s
complaints, life history, medical history and additional methods of research.
Neural network model allowed making a significance assessment of factors,
which have ...
Added: January 10, 2019
Sirchenko A., / Series 1672194. "UCSD Economics working papers". 2010. No. 1672194.
The National Bank of Poland does not publish the Monetary Policy Councils voting
records before the subsequent policy meeting. Using real-time data, this paper shows
that a prompter release of the voting records could improve the predictability of policy
decisions. The voting patterns reveal strong and robust predictive content even after
controlling for policy bias and responses to ination, ...
Added: September 29, 2014
Gushchin A. A., Annales Academiae Scientiarum Fennicae. Series A I. Mathematica 1992 Т. 17 № 1 С. 29–38
We consider some aspects of quasi-likelihood methods used in estimation of parameters of stochastic processes. ...
Added: October 9, 2013