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

Abstract We present DeepPavlov 1.0, an open-source framework for using Natural
Language Processing (NLP) models by leveraging transfer learning techniques …

In this paper we describe a generative question answering system which relies on text or
knowledge graphs to find supporting evidence. The goal of generative QA is to provide a …

In learning-based functionality stealing, the attacker is trying to build a local model based on
the victim's outputs. The attacker has to make choices regarding the local model's …

The paper makes use of the annotated task-oriented corpus of Holocaust testimonies in
Russian (ruOHQA) to train a question-answer neural network model. We start from data …

Named Entity Sentiment analysis (NESA) is one of the most actively developing application
domains in Natural Language Processing (NLP). Social media NESA is a significant field of …

Введение: многочисленные исследования говорят о том, что современные крупные
нейронные сети, как правило, имеют избыточное количество параметров. Целью …

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 …

We study performance of BERT-like distributive semantic language models on anaphora
resolution and related tasks with the purpose of selecting a model for on-device inference …