Papers by Elena Mikhalkova

2 papers
Russian Jeopardy! Data Set for Question-Answering Systems (2022.lrec-1)

Copied to clipboard

Challenge: Question answering is one of the most common tasks in natural language processing . open-domain questions cover a wide range of topics and do not necessarily come in form of an actual question.
Approach: They describe a Russian question-like question set collected from the Russian analogue of Jeopardy! They observe its linguistic features and the related QA-task.
Outcome: The proposed data set includes 379,284 quiz-like questions with 29,375 from the Russian analogue of Jeopardy!
Modelling Narrative Elements in a Short Story: A Study on Annotation Schemes and Guidelines (2020.lrec-1)

Copied to clipboard

Challenge: Text-processing algorithms that annotate main components of a story are in great need of corpora and well-agreed annotation schemes.
Approach: They propose a model that generalizes a narrative structure in the form of world building elements (characters, time and space) and text worlds themselves and switches between them.
Outcome: The proposed model can be used for annotating narratives in corpora of literary texts, criminal evidence, teaching materials, quests, etc.

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