Dr. Nicolay Rusnachenko

My name is Nicolay Rusnachenko, and I am specialized in Information Retrieval (IR) and Natural Language Processing. I defend my PhD thesisin textual IR 📜, with the degree approved by UK ENIC 🎓. At present, I am a Research Fellow at Bournemouth University 💼 working on transform the UK/global healthcare sector by marking medical images with multi-modal Natural Language Processing (NLP) techniques 🧑‍💻. Along side with it, I contribute in advances of the vast amount of IR fields, including: Sentiment Analysis, Text Summarization, Dialogue Assistants.

Email  /  CV  /  LinkedIn  /  GitHub  / 
Google Scholar  / Research Gate / Semantic / Scopus / WoS / ORCID / PeerJ
Twitter /  Hugging Face /  Youtube /  News /  bluesky /  Blog

🏃 athletics-profile

Proceeding of the earlier proposed MediExtract distil-tuning framework, which has been reforged to support decoder-based models (LLMs) with role-based prompt formation. The key contribution of the novel framework is its scalable potentials to other modalities.

RuOpinionNE-2024 proceeds the past year RuSentNE-2023 that go further with:
↗️ annotation of other sources of opinion causes: entities, out-of-context object (None), and 📏 evaluation of factual statements that support the extracted sentiment.

In this talk we cover LLM evaluation concepts through the detailed overview of manual reporting directions in liver cancer imaging. We cover radiological imaging aspects that doctors tend to mention ✍️ and see how these aspects could be retrieved by LLM 🤖 by means of NLP and IR techniques. We provide recommendations on model scale choice and findings out of result analysis. This contributes to the similar studies presented at CASA-2025.

This milestone grants me skills for evaluating Autonomous Intelligent Systems (AIS). Generative AI and Large Language Models as the most recent advances in AI inevitably takes part in products of various fields: transportation, manufacturing, retail / customer service, healthcare, finance, education (AI learning platforms). The completed training makes me a right person for ensuring quality of the AIS-powered products and services, especially with the focus on personal expertise in: AI, NLP, and Information Retrieval.

MediExtract Distillation Framework (MEDF) is a a hybrid teacher-student distillation process that leverages the power of LLMs in information capturing to enhance the performance of a smaller student model. Model training involves two feedforward branches per iteration: one using ground truth as labels and another using generated structured medical key information as an auxiliary supervision.

A hub of third-party providers and tutorials to help you instantly apply various NLP techniques.

A tiny Python no-string package for performing translation of a massive stream of texts with native support of pre-annotated fixed-spans that are invariant for translator. Powered by AREkit-pipelines.

In this talk, by saying reading in between the lines, we refer to performing such and Implicit IR that involves extraction of such information that is related to, i.e. ✍ ️author / 👩‍⚕️ patient / 🧑‍🦰 character etc.

Presented an update on NLP advances in MMI-NLP project in end-to-end system for training novice practitioners. We showcase the importance on NLP application for processing medical narratives of liver-related MRI/CT scan series, such as one mentioned in "Series Descriptions" of the DICOM metadata. The end-to-end concept advances were demonstrated as well.

A lightweight, no-strings-attached Chain-of-Thought framework for your LLM, ensuring reliable results for bulk input requests stored in CSV / JSONL / sqlite. It allows applying series of prompts formed into schema

A no-strings framework for Named Entity Recognition (NER) in large textual collection with third-party AI models via very accessible API. Powered by AREkit-pipelines.

The talk is devoted to application of Large Language Models (LLMs) for retrieving implicit information from non-structured texts via reasoning the result sentiment label. To enhance model reasoning capabilities 🧠, we adopt Chain-of-Thought technique and explore its proper adaptation in Sentiment Analysis task.

This paper proposes the workflow of automatic profiling fictional character from literature novel books. The workflow is aimed at character personalities construction by solely rely on their comments in book: dialogue utterances and surrounding text, paragraphs.

We propose a loss function which combines: (1) structured contrastive loss and (2) Pearson loss. For exploiting the related function in BERT optimization process, we propose "Adversarial Training with Fast Gradient Method (FGM)". To improve model generalization ability we exploit "mix-up" as a data augmentation technique to mix inputs with the labels in specific range.

We adopt two-stage method SFT (🟥) + inference (🟩) as contrastive reasoning calibration (CRC). For the training, we enrich input samples: standard, role-play, contrastive. We concatenate the article and task content togerther in input to train model predict all track results (1,2,3).

We fine-tune Flan-T5-base (250M) with the reforged THoR-ISA framework for Emotion Cause Extraction. Our final submission is 3'rd place by F1-proportional and 4-5'th by F1-strict which counts the emotion cause span borders. Our THOR-ECAC is publicly available.

We propose a two-phase SFT training strategy: (i) data-processing and (ii) model training. In (i) we combine CoT + knowledge-distillation concept (using GPT-3.5) + CoT steps for CoT-NumHG; this resource is then adopted in (ii) for the full-param SFT

This is the Russian version of the talk devoted to application of Large Language Models (LLMs) for retrieving implicit information from non-structured texts via reasoning the result sentiment label. To enhance model reasoning capabilities 🧠, we adopt Chain-of-Thought technique and explore its proper adaptation in Sentiment Analysis task.

Presented a multi-disciplinary research to transform the UK/global healthcare sector and allied training using digital technologies derived from the creative industries sector. In particular, the personal findings on Multimodal LLM-based system development and research to be conducted has been demonstrated in a form of the demo setups.

We explore LLMs reasoning capabilities in Targeted Sentiment Analysis task. In particular we assess LLM models in two modes: (i) zero-shot-learning (ZSL) (ii) fine-tuning with prompt and CoT THoR proposed at ACL-2023. The fine-tuned Flan-T5-xl outperforms the prior top submission at RuSentNE-2023.

AREkit-based application for a granular view onto sentiments between entities for large document collections, including books, mass-media, Twitter/X, and more. See our online demo

AREkit-based application for a granular view onto sentiments between entities in a mass-media texts written in Russian. Project presentation.

To enhance the engagement of chatbots, we need to imbue them with unique personalities and speech patterns. We propose an automated system that uses character dialogues from literary works. We used the Chinese classic, Dream of the Red Chamber. Our system efficiently extracts dialogues and personality traits from the book, creates a personality map for each character, generates responses that reflect these traits.

This report represent a study of how well the annotated relations in NEREL could be predicted by ChatGPT-3.5.

Application of the transformer-based model for the named entity recognition task in legal texts.

Participants are offered the task of extracting sentiments of three classes (neg, pos, neutral) from news texts in relation to pre-marked entities such as PERSON, ORG, PROFESSION, COUNTRY, NATIONALITY within a separate sentence.

A first LongT5-based model pre-trained on a large amount of unlabeled Vietnamese texts and fine-tuned within the manually summarized texts from ViMS and VMDS and VLSP2022 collections

Taking a facilitator Role in the The Rivers Trust project. The Rivers Trust company leads the Catchment Systems Thinking Cooperative (CaSTCo) project, which has been set up to provide a national framework for sharing water environment data across a range of stakeholders. To the best of our personal knowledge we were the first who experiment with the Graph Neural Networks application (GNN) for water quality assessment.

In this talk we cover the advances of machine-learning approaches in sentiment analysis of large mass-media documents. Complements the past talk at Wolfson College (Oxford) with the detailed description of long-input transformers, RLHF training overview.

In this talk we examine the limitations of BERT model from the input size perspective. To address the shortcommings, authors propose a related position embeddings in order to implement local-window based sparse attention. To attend the distant tokens, authors propose a Global-Attention mechanism in addition to the sparsed one for the main input. Another main contribution is input structuring in attention mechanism.

In this talk we cover the advances of machine-learning approaches in sentiment analysis of large mass-media documents. We provide both evolution of the task over time including a survey of task-oriented models starting from the conventional linear classification approaches to the applications findings of the recently announced ChatGPT model.

About Tensorflow-based framework which lists attentive implementation of the conventional neural network models (CNN, RNN-based), applicable for Relation Extraction classification tasks as well as API for custom model implementation

Low Resource Context Relation Sampler for contexts with relations for fact-checking and fine-tuning your LLM models, powered by AREkit

This talk represent a brief introduction into Natural Language Processing by highlighting tasks that are relevant in Reputation Tracking domain.

Document level Attitude and Relation Extraction toolkit (AREkit) for sampling mass-media news into datasets for your ML-model training and evaluation

AREkit-based application for a granular view onto sentiments between entities in a mass-media texts written in Russian. Project presentation.

We propose distant-supervision approach for mass-media annotation, based on RuSentiFrames knowledge-base. We built and propose RuAttitudes collection for Sentiment Attitude Extraction task and adopt it for neural-networks training process, including BERT-based language models.

For Biomedical domain. We investigate: (1) which search interface elements searchers are look at when searching for docs to answer complex questions, and (2) relationship between individual differences and the interface elements which users are looked at.

This is a curated list of works devoted to sentiment attitude extraction domain. The latter considered as an area of studies, in which sentiment analysis and relation extraction are inextricably linked

This repository is an official results benchmark for automatic sentiment attitude extraction task within RuSentRel-1.1 collection, for the following models: conventional approaches (SVM, RandomForest, kNN, NB, Gradient Boosting), CNN-based networks, RNN-based networks, Attentive models, BERT-based language models.

This lecture is devoted to the works that were done within last 4 years, which is related sentiment attitude extraction task.

This lecture is devoted to the works that were done within the past 4 years, which is related sentiment attitude extraction task.

Participant of summer school.

Application of Distant Supervision in model training process results in a weight distribution biasing: frames in between subject and object of attitude got more weight values; the latter reflects the pattern of frame-based approach, utilized in RuAttitudes collection development.

Provides a description of the developed RuSentiFrames lexicon with the related application for attitude extraction

Pages: 169-179. The paper describes the task of automatic extraction of attitudes between the subjects mentioned in the text, as well as their connection with the implicit expression of the author's attitude to these subjects. A RuSentiFrames vocabulary is presented, in which the basic attitudes associated of Russian predicate words are described.

Participant of summer school.

First time application of automatic attitudes extraction from raw news, based on news title presentation simplicity.

Utilizing a set of sentence level attitudes with related metrics to perform a sentiment prediction. As for input of neural network based models, in prior works all the models deals with an attitudes limited by a single sentence.

An application of CNN based architecture (adapted for relation extraction) towards sentiment attitudes extraction task.

An application of CNN based architecture (adapted for relation extraction) towards sentiment attitudes extraction task. Presented at Third Workshop "Computational linguistics and language science" (CCLS-2018), HSE, Moscow.

The first approach, i.e introduction of sentiment attitudes extraction task. Includes developed dataset with related experiments.

Introduction of sentiment attitudes extraction task. Includes developed RuSentRel with related experiments.

Provides details on lexicon development using twitter messages (related works [pmi], [dev], [sota]). Sentiment classification of user reviews using SVM. Master degree paper.

This guy shares a great template!