Saved in:
Bibliographic Details
Main Author: Zaitsev, Konstantin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.09181
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911953584128000
author Zaitsev, Konstantin
author_facet Zaitsev, Konstantin
contents The paper presents a study of methods for extracting information about dialogue participants and evaluating their performance in Russian. To train models for this task, the Multi-Session Chat dataset was translated into Russian using multiple translation models, resulting in improved data quality. A metric based on the F-score concept is presented to evaluate the effectiveness of the extraction models. The metric uses a trained classifier to identify the dialogue participant to whom the persona belongs. Experiments were conducted on MBart, FRED-T5, Starling-7B, which is based on the Mistral, and Encoder2Encoder models. The results demonstrated that all models exhibited an insufficient level of recall in the persona extraction task. The incorporation of the NCE Loss improved the model's precision at the expense of its recall. Furthermore, increasing the model's size led to enhanced extraction of personas.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09181
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring the Effectiveness of Methods for Persona Extraction
Zaitsev, Konstantin
Computation and Language
The paper presents a study of methods for extracting information about dialogue participants and evaluating their performance in Russian. To train models for this task, the Multi-Session Chat dataset was translated into Russian using multiple translation models, resulting in improved data quality. A metric based on the F-score concept is presented to evaluate the effectiveness of the extraction models. The metric uses a trained classifier to identify the dialogue participant to whom the persona belongs. Experiments were conducted on MBart, FRED-T5, Starling-7B, which is based on the Mistral, and Encoder2Encoder models. The results demonstrated that all models exhibited an insufficient level of recall in the persona extraction task. The incorporation of the NCE Loss improved the model's precision at the expense of its recall. Furthermore, increasing the model's size led to enhanced extraction of personas.
title Exploring the Effectiveness of Methods for Persona Extraction
topic Computation and Language
url https://arxiv.org/abs/2407.09181