Papers by Dmitri Roussinov

3 papers
Recognizing Semantic Relations by Combining Transformers and Fully Connected Models (2020.lrec-1)

Copied to clipboard

Challenge: Current approaches to recognizing semantic relations between words are limited and require a word-path model.
Approach: They propose a distributional approach that is based on an attention-based transformer and a word path model that combines useful properties of a convolutional network with a fully connected language model.
Outcome: The proposed model outperforms the state-of-the-art in terms of performance and data sources.
BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models have improved performance of text classification tasks, but they still suffer from spurious domain-specific clues.
Approach: They propose a method to augment pretrained language models by generating texts in any desired genre and on any desired topic.
Outcome: The proposed method improves on genre classification tasks while showing no improvement for other topics.
Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have pushed the boundaries of natural language processing, but their consistency is often limited when applied to unfamiliar domains.
Approach: They propose a method that controls which predictive indicators are used and which are excluded during classification.
Outcome: The proposed method reduces the OOD gap by up to 20 percentage points in a few-shot setup.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations