no code implementations • EcomNLP (COLING) 2020 • Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova
Information retrieval chatbots are widely used as assistants, to help users formulate their requirements about the products they want to purchase, and navigate to the set of items that satisfies their requirements in the best way.
no code implementations • EcomNLP (COLING) 2020 • Boris Galitsky, Dmitry Ilvovsky
We propose a novel way of conversational recommendation, where instead of asking questions to the user to acquire their preferences; the recommender tracks their conversation with other people, including customer support agents (CSA), and joins the conversation only when it is time to introduce a recommendation.
no code implementations • RANLP 2021 • Alexander Chernyavskiy, Dmitry Ilvovsky, Boris Galitsky
We address both of these flaws: they are independent but can be combined to generate original texts that will be both consistent and truthful.
no code implementations • RANLP 2021 • Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova
Machine reading comprehension (MRC) is one of the most challenging tasks in natural language processing domain.
no code implementations • EMNLP (CODI) 2020 • Alexander Chernyavskiy, Dmitry Ilvovsky
To this end, the neural TreeLSTM model is modified to effectively encode discourse trees and DSNDM model based on it is suggested to analyze pairs of texts.
no code implementations • CLIB 2020 • Dmitry Ilvovsky, Alexander Kirillovich, Boris Galitsky
We define extended discourse trees, introduce means to manipulate with them, and outline scenarios of multi-document navigation to extend the abilities of the interactive information retrieval-based chat bot.
no code implementations • CLIB 2022 • Alexander Kirillovich, Natalia Loukachevitch, Maksim Kulaev, Angelina Bolshina, Dmitry Ilvovsky
We present a sense-annotated corpus for Russian.
1 code implementation • 10 Oct 2022 • Momchil Hardalov, Anton Chernyavskiy, Ivan Koychev, Dmitry Ilvovsky, Preslav Nakov
Thus, an interesting approach has emerged: to perform automatic fact-checking by verifying whether an input claim has been previously fact-checked by professional fact-checkers and to return back an article that explains their decision.
no code implementations • NAACL 2022 • Anton Chernyavskiy, Dmitry Ilvovsky, Pavel Kalinin, Preslav Nakov
The use of contrastive loss for representation learning has become prominent in computer vision, and it is now getting attention in Natural Language Processing (NLP).
no code implementations • 16 Apr 2021 • Anton Chernyavskiy, Dmitry Ilvovsky, Preslav Nakov
The rise of Internet has made it a major source of information.
no code implementations • 9 Apr 2021 • Anton Chernyavskiy, Dmitry Ilvovsky, Preslav Nakov
Recent advances in neural architectures, such as the Transformer, coupled with the emergence of large-scale pre-trained models such as BERT, have revolutionized the field of Natural Language Processing (NLP), pushing the state of the art for a number of NLP tasks.
1 code implementation • SEMEVAL 2020 • Anton Chernyavskiy, Dmitry Ilvovsky, Preslav Nakov
We describe our system for SemEval-2020 Task 11 on Detection of Propaganda Techniques in News Articles.
no code implementations • WS 2019 • Anton Chernyavskiy, Dmitry Ilvovsky
It is widely accepted that factual data verification is a challenge even for the experts.
no code implementations • WS 2019 • Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova
We demo a chatbot that delivers content in the form of virtual dialogues automatically produced from plain texts extracted and selected from documents.
no code implementations • RANLP 2019 • Boris Galitsky, Dmitry Ilvovsky
We introduce a concept of a virtual discourse tree to improve question answering (Q/A) recall for complex, multi-sentence questions.
no code implementations • RANLP 2019 • Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova
We present a chatbot that delivers content in the form of virtual dialogues automatically produced from the plain texts that are extracted and selected from the documents.
no code implementations • RANLP 2019 • Boris Galitsky, Dmitry Ilvovsky
We explore anatomy of answers with respect to which text fragments from an answer are worth matching with a question and which should not be matched.
no code implementations • 7 Mar 2019 • Gerhard Wohlgenannt, Ariadna Barinova, Dmitry Ilvovsky, Ekaterina Chernyak
Among the contributions are the evaluation of various word embedding techniques on the different task types, with the findings that even embeddings trained on small corpora perform well for example on the word intrusion task.
no code implementations • 4 Mar 2019 • Gerhard Wohlgenannt, Ekaterina Chernyak, Dmitry Ilvovsky, Ariadna Barinova, Dmitry Mouromtsev
In this research, we manually create high-quality datasets in the digital humanities domain for the evaluation of language models, specifically word embedding models.
no code implementations • WS 2018 • Boris Galitsky, Dmitry Ilvovsky
In this section we propose a reasoning-based approach to a dialogue management for a customer support chat bot.
no code implementations • RANLP 2017 • Boris Galitsky, Dmitry Ilvovsky
The system achieves rhetoric agreement by learning pairs of discourse trees (DTs) for question (Q) and answer (A).
no code implementations • EACL 2017 • Boris Galitsky, Dmitry Ilvovsky
We then combine DTs for the paragraphs of documents to form what we call extended DT, which is a basis for interactive content exploration facilitated by the chat bot.
no code implementations • WS 2016 • Gerhard Wohlgenannt, Ekaterina Chernyak, Dmitry Ilvovsky
In this paper a social network is extracted from a literary text.