?
Improving Text Generation via Neural Discourse Planning
P. 1543–1544.
Alexander Chernyavskiy
Recent Transformer-based approaches to NLG like GPT-2 can generate syntactically coherent original texts. However, these generated texts have serious flaws. One of them is a global discourse incoherence. We present an approach to estimate the quality of discourse structure. Empirical results confirm that the discourse structure of currently generated texts is inaccurate. We propose the research directions to plan it and fill in the text in its leaves using the pipeline consisting of two GPT-based generation models. The suggested approach is universal and can be applied to different languages.
In book
Association for Computing Machinery (ACM), 2022.
Микулинский А. Д., , in: Синергия языков и культур 2022: междисциплинарные исследования.: St. Petersburg: -, 2023. P. 335–351.
The paper is devoted to the issue of the local structure modeling of the eSports commentary spoken genre on an example of the Dota 2 computer discipline. ESports commentary is a spontaneous and creative speech aimed at describing of what is happening on the computer-gaming field. The main factors that force us to study it ...
Added: May 12, 2024
Chernyavskiy A., Ostyakova L., Ilvovsky D., , in: Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024).: Association for Computational Linguistics, 2024. P. 149–160.
Recent language models have significantly boosted conversational AI by enabling fast and cost-effective response generation in dialogue systems. However, dialogue systems based on neural generative approaches often lack truthfulness, reliability, and the ability to analyze the dialogue flow needed for smooth and consistent conversations with users. To address these issues, we introduce GroundHog, a modified ...
Added: May 9, 2024
Chernyavskiy A., Ilvovsky D., Nakov P., , in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: (Volume 1: Long Papers).: Association for Computational Linguistics, 2024. P. 1452–1462.
Added: May 9, 2024
Galitsky B., Ilvovsky D., Goncharova E., , in: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог». Вып. 22.Вып. 22.: [б.и.], 2023.
We extend the concept of a discourse tree (DT) in the discourse representation of text towards data of various forms and natures. The communicative DT to include speech act theory, extended DT to ascend to the level of multiple documents, entity DT to track how discourse covers various entities were defined previously in computational linguistics, we now proceed ...
Added: November 10, 2023
Alexander Chernyavskiy, Ilvovsky D., , in: Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue.: Association for Computational Linguistics, 2023. P. 519–529.
Recent transformer-based approaches to multi-party conversation generation may produce syntactically coherent but discursively inconsistent dialogues in some cases. To address this issue, we propose an approach to integrate a dialogue act planning stage into the end-to-end transformer-based generation pipeline. This approach consists of a transformer fine-tuning procedure based on linearized dialogue representations that include special ...
Added: October 6, 2023
Chernyavskiy A., Ilvovsky D., Galitsky B., , in: Proceedings of the Student Research Workshop Associated with RANLP 2021.: INCOMA Ltd, 2021. P. 36–43.
Recent transformer-based approaches to NLG like GPT-2 can generate syntactically coherent original texts. However, these generated texts have serious flaws: global discourse incoherence and meaninglessness of sentences in terms of entity values. We address both of these flaws: they are independent but can be combined to generate original texts that will be both consistent and ...
Added: May 29, 2022
Chernyavskiy A., Ilvovsky D., , in: Proceedings of the First Workshop on Computational Approaches to Discourse.: Association for Computational Linguistics, 2020. P. 76–85.
In this paper, the utility and advantages of the discourse analysis for text pairs categorization and ranking are investigated. We consider two tasks in which discourse structure seems useful and important: automatic verification of political statements, and ranking in question answering systems. We propose a neural network based approach to learn the match between pairs ...
Added: November 18, 2020
Association for Computational Linguistics, 2020.
Added: November 18, 2020
Galitsky B., Ilvovsky D., Kuznetsov S., Journal of Experimental and Theoretical Artificial Intelligence 2018 Vol. 30 No. 5 P. 637–663
We solve the argument mining problem by investigating discourse and communicative text structure. A new formal graph-based structure called communicative discourse tree (CDT) is defined. It consists of a discourse tree with additional labels on edges, which stand for verbs. These verbs represent communicative actions. Discourse trees are based on rhetoric relations, extracted from a ...
Added: October 28, 2018
Pimenova N., В кн.: Материалы XXI чтений памяти И. М. Тронского "Индоевропейское языкознание и классическая филология - XXI".Т. XXI.: СПб.: Наука, 2017. С. 661–671.
The author investigates the features of the Gothic demonstratives sa
‘this, that’ and jains ‘that’ in quoted speech and narrative contexts, which
help to reconstruct and describe relations within the deixis system at an
early stage of the grammaticalization of definite article (the stage of
anaphoric article). ...
Added: October 23, 2018
Linnik A., Bastiaanse R., Stede M. et al., Aphasiology 2022 Vol. 36 No. 2 P. 123–146
Background: Coherence is the quality which distinguishes discourse from a random collection of sentences. People with aphasia have been reported to produce less-coherent discourse than non-language-impaired speakers. It is largely unclear how coherence is established in natural language and what leads to its impairment in aphasia.
Aims: This paper presents a cross-methodological investigation on coherence in ...
Added: September 29, 2016
Khrabrova V. E., Национальная Ассоциация Ученых 2014 Т. 4 № 5 С. 41–43
The paper deals with the problem of using graphic visuals in English class as a means ofenhancing discourse structure awareness from the psychoeducational perspective. The issue under consideration has become actual in teaching English for Specific Purposes, e.g. Economics in English, as well as Academic English. Discourse structures are basic text models making it possible ...
Added: February 6, 2015