Abstract An open-source DeepPavlov Dream Platform is specifically tailored for
development of complex dialog systems like Generative AI Assistants. The stack prioritizes …

The inclination of large language models (LLMs) to produce mistaken assertions, known as
hallucinations, can be problematic. These hallucinations could potentially be harmful since …

Although capitalisation is an important feature for the Named Entity Recognition (NER) task,
the NER input data is not always cased. Recent studies suggest two main methods of …

This article investigates the knowledge transfer from the RuQTopics dataset. This Russian
topical dataset combines a large sample number (361,560 single-label, 170,930 multi-label) …

This article presents a system that translates natural language questions into SPARQL
queries. The question answering system includes a syntax parser that generates a parse …

In this work, we propose an efficient answer retrieval system** EARS**: a production-ready,
factual question answering (QA) system that combines local knowledge base search with …

Although the task of named entity recognition (NER) is usually solved as a sequence
tagging problem via traditional supervised learning approaches which require the presence …

In this work, we investigate knowledge transfer from the RuQTopics dataset. This Russian
topical dataset combines a large number of data points (361, 560 single-label, 170, 930 …

Few-shot intent classification and out-of-scope (OOS) detection are core components of task-
oriented dialogue systems. Solving both tasks can be challenging because of limited data …

В работе описывается система, которая переводит вопрос на естественном языке в
SPARQL-запрос. В состав вопросно-ответной системы входят: синтаксический парсер …