DSA Faculty
API
← к списку преподавателей

Ильвовский Дмитрий Алексеевич

Факультет компьютерных наук

Профиль на hse.ru ↗ тел.: +7 (495) 772-95-90 | 27319 | +7 (916) 569-70-22
Публикаций
67
Языков
1
Наград
7
Конференций
5
Профиль Публикации (67) Курсы (5)

Профессиональные интересы

компьютерная лингвистикаанализ формальных понятий

Должности

  • Доцент — Факультет компьютерных наук, Департамент анализа данных и искусственного интеллекта
  • Научный сотрудник — Факультет компьютерных наук, Международная лаборатория интеллектуальных систем и структурного анализа

Био

  • · Начал работать в НИУ ВШЭ в 2011 году.
  • · Научно-педагогический стаж: 10 лет.

Образование

  • 2017 · Кандидат наук
  • 2010 · Специалитет: Московский авиационный институт, специальность «Прикладная математика и информатика», квалификация «Математик. Системный программист»

Опыт работы

  • · 2012 - н.в.: Научно-учебная лаборатория интеллектуальных систем и структурного анализа (Младший научный сотрудник)
  • · 2007 - н.в.: Эксперт отделения «Корпоративные Интернет-решения» компании ФОРС Центр разработки

Награды и поощрения

  • · Благодарность НИУ ВШЭ (январь 2024)
  • · Благодарность проректора НИУ ВШЭ (август 2021)
  • · Благодарность Факультета компьютерных наук НИУ ВШЭ (август 2017)
  • · Персональная надбавка ректора (2016–2017)
  • · Надбавка за академическую работу (2020–2021)
  • · Надбавка за публикацию в журнале из Списка А (и приравненном к нему научном издании) (2025–2026, 2024–2025, 2023–2024)
  • · Надбавка за публикацию в международном рецензируемом научном издании (2022–2023, 2021–2022, 2017–2019)

Гранты и проекты

  • — · на соискание учёной степени кандидата наук

Конференции (5)

Показать все
  • · 2023: ДИЗАЙН МЕЖДИСЦИПЛИНАРНЫХ ИССЛЕДОВАНИЙ В КОНТЕКСТЕ СБЛИЖЕНИЯ МОДЕЛЕЙ ЕСТЕСТВЕННО-НАУЧНОГО И ГУМАНИТАРНО- СОЦИАЛЬНОГО ЗНАНИЯ (Москва). Доклад: Искусственный интеллект как утилита базовой новостной грамотности
  • · 2016: Компьютерная лингвистика и интеллектуальные технологии (Диалог 22) (Москва). Доклад: Style and Genre Classification by Means of Deep Textual Parsing
  • · 2016: Пятнадцатая национальная конференция по искусственному интеллекту с международным участием (КИИ-2016) (Смоленск). Доклад: Discovering disinformation: discourse-level approach
  • · 2015: 7th International Joint Conference on Natural Language Processing, ACL 2015 (Beijing). Доклад: Rhetoric Map of an Answer to Compound Queries.
  • · 2015: Recent Advances in Natural Language Processing, RANLP 2015 (Hissar). Доклад: Text Classification into Abstract Classes Based on Discourse Structure

Идентификаторы исследователя

Публикации (67)

On a Chatbot Conducting Dialogue-in-Dialogue

2019 · CHAPTER · en

We demo a chatbot that delivers content in the form of virtual dialogues automatically produced from plain texts extracted and selected from documents. This virtual dialogue content is provided in the form of answers derived from the found and selected documents split into fragments, and questions are automatically generated for these answers.

DOI ↗ PDF ↗

On a Chatbot Providing Virtual Dialogues

2019 · CHAPTER · en

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. This virtual dialogue content is provided in the form of answers derived from the found and selected documents split into fragments, and questions that are automatically generated for these answers based on the initial text.

DOI ↗ PDF ↗

Information Retrieval Chatbots Based on Conceptual Models

2019 · CHAPTER · en

Customer support systems based on chatbots gain an increasing popularity. Chatbots are becoming more and more important to a plethora of applications not only for social services. Modern information retrieval (IR) chatbots are based on simple queries to a database and do not ensure intelligent dialogues with users. In this paper we propose an IR-chatbot model that incorporates a concept-based knowledge model and an index-guided traversal through it to ensure the discovery of information relevant for users and coherent to their preferences. The proposed approach not only supports a search session, but also helps users to discover properties of items and sequentially refine an imprecise query.

DOI ↗ PDF ↗

Two Discourse Tree-Based Approaches to Indexing Answers

2019 · CHAPTER · en

We explore anatomy of answers with re-spect to which text fragments from an an-swer are worth matching with a question and which should not be matched. We ap-ply the RhetoricalStructure Theory to build a discourse tree of an answer and se-lect elementary discourse units that are suitable for indexing. Manual rules for se-lection of these discourse units as well as automated classification based on web search engine mining are evaluated con-cerning improving search accuracy. We form two sets of question-answer pairs for FAQ and community QA search domains and use them for evaluation of the pro-posed indexing methodology, which deliv-ers up to 16 percent improvement in search recall.

PDF ↗

Discourse-Based Approach to Involvement of Background Knowledge for Question Answering

2019 · CHAPTER · en

We introduce a concept of a virtualdiscourse treeto improve question answering (Q/A) recall for complex, multi-sentence questions. Augmenting thediscourse tree of an answer with tree fragments obtained from text corpora playing the role of ontology, we obtain on the flya canonical discourse representation of this answer that is independent of thethought structure of a given author. This mechanism is critical for finding an answer that is not only relevant in terms of questions entities but also in terms of inter-relations between these entities in an answer and its style. We evaluate the Q/A system enabled with virtualdiscourse trees and observe a substantial increase of performanceanswering complex questions such as Yahoo! Answers and www.2carpros.com.

PDF ↗

On the End-to-End Argument Validation System based on Communicative Discourse Trees

2019 · CHAPTER · en

We formulate a problem of an assessment of argumentation validity based on rhetorical analysis of text. Argumentation structure can be detected in text in the form of discourse trees extended with edge labels for communicative actions. Extracted argumentation structureisrepresentedas a defeasible logic program and issubject to dialectical analysisto establish the validity of the arguments for the main claim being communicated. We evaluate the accuracy of argument mining and then argument validation as well as anoverall performanceof an end-to-end argumentation system.

PDF ↗

On a Chatbot Conducting Virtual Dialogues

2019 · CHAPTER · en

We present a demo of the chatbot that delivers content in the form of virtual dialogues automatically produced from the plain texts extracted and selected from the documents. This virtual dialogue content is provided in the form of answers derived from the found and selected documents split into fragments, and questions are automatically generated for these answers.

PDF ↗

Extract and Aggregate: A Novel Domain-Independent Approach to Factual Data Verification

2019 · CHAPTER · en

Triggered by Internet development, a large amount of information is published in online sources. However, it is a well-known fact that publications are inundated with inaccurate data. That is why fact-checking has become a significant topic in the last 5 years. It is widely accepted that factual data verification is a challenge even for the experts. This paper presents a domain-independent fact checking system. It can solve the fact verification problem entirely or at the individual stages. The proposed model combines various advanced methods of text data analysis, such as BERT and Infersent. The theoretical and empirical study of the system features is carried out. Based on FEVER and Fact Checking Challenge test-collections, experimental results demonstrate that our model can achieve the score on a par with state-of-the-art models designed by the specificity of particular datasets.

DOI ↗

Detecting logical argumentation in text via communicative discourse tree

2018 · ARTICLE · en

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 text according to Rhetoric Structure Theory. The problem is tackled as a binary classification task, where the positive class corresponds to texts with arguments and the negative class corresponds to texts with no arguments. The feature engineering for the classification task is conducted, deciding on which syntactic and discourse features are associated with logical argumentation. Text classification framework based on syntactic, discourse and communicative discourse text structures with a number of learning approaches is implemented. Evaluation on a combined data-set is provided.

DOI ↗ PDF ↗

Глубинное обучение для автоматической обработки текстов

2017 · ARTICLE · ru

Нейронные сети позволяют находить скрытые связи и закономерности в текстах, но эти связи не могут быть представлены в явном виде. Нейронные сети — пусть и мощный, но достаточно тривиальный инструмент, вызывающий скептицизм у компаний, разрабатывающих промышленные решения в области анализа данных, и у ведущих компьютерных лингвистов.

Курсы (5)