Standard

Developing a Question Answering System on the Material of Holocaust Survivors’ Testimonies in Russian. / Bukreeva, Liudmila; Guseva, Daria; Dolgushin, Mikhail; Evdokimova, Vera; Obotnina, Vasilisa.

Speech and Computer . 2023. p. 357-366 (Lecture Notes in Computer Science ; Vol. 14339).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Bukreeva, L, Guseva, D, Dolgushin, M, Evdokimova, V & Obotnina, V 2023, Developing a Question Answering System on the Material of Holocaust Survivors’ Testimonies in Russian. in Speech and Computer . Lecture Notes in Computer Science , vol. 14339, pp. 357-366, The 25th International Conference on Speech and Computer (SPECOM), Hubli-Dharwad, India, 29/11/23. https://doi.org/10.1007/978-3-031-48312-7_29

APA

Bukreeva, L., Guseva, D., Dolgushin, M., Evdokimova, V., & Obotnina, V. (2023). Developing a Question Answering System on the Material of Holocaust Survivors’ Testimonies in Russian. In Speech and Computer (pp. 357-366). (Lecture Notes in Computer Science ; Vol. 14339). https://doi.org/10.1007/978-3-031-48312-7_29

Vancouver

Bukreeva L, Guseva D, Dolgushin M, Evdokimova V, Obotnina V. Developing a Question Answering System on the Material of Holocaust Survivors’ Testimonies in Russian. In Speech and Computer . 2023. p. 357-366. (Lecture Notes in Computer Science ). https://doi.org/10.1007/978-3-031-48312-7_29

Author

Bukreeva, Liudmila ; Guseva, Daria ; Dolgushin, Mikhail ; Evdokimova, Vera ; Obotnina, Vasilisa. / Developing a Question Answering System on the Material of Holocaust Survivors’ Testimonies in Russian. Speech and Computer . 2023. pp. 357-366 (Lecture Notes in Computer Science ).

BibTeX

@inproceedings{7aed4d215434462389f0023523ee69e0,
title = "Developing a Question Answering System on the Material of Holocaust Survivors{\textquoteright} Testimonies in Russian",
abstract = "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 preprocessing, present statistical analysis of the collected corpus for approximately 1500 pairs of questions and answers and describe its strengths and limitations. Also, we carry out experiments on automatic processing of the ruOHQA corpus using pre-trained transformer-based neural network models. Finally, we explore the capability of several models to generate simplified high-quality answers to questions and compare their results. The kind of research we present allows us to extract knowledge from oral history archives more productively.",
keywords = "Corpora, Question Answering, Visual History Archives",
author = "Liudmila Bukreeva and Daria Guseva and Mikhail Dolgushin and Vera Evdokimova and Vasilisa Obotnina",
year = "2023",
month = nov,
day = "22",
doi = "10.1007/978-3-031-48312-7_29",
language = "English",
isbn = "9783031483110",
series = "Lecture Notes in Computer Science ",
pages = "357--366",
booktitle = "Speech and Computer",
note = "null ; Conference date: 29-11-2023 Through 01-12-2023",
url = "https://www.iitdh.ac.in/specom-2023/",

}

RIS

TY - GEN

T1 - Developing a Question Answering System on the Material of Holocaust Survivors’ Testimonies in Russian

AU - Bukreeva, Liudmila

AU - Guseva, Daria

AU - Dolgushin, Mikhail

AU - Evdokimova, Vera

AU - Obotnina, Vasilisa

PY - 2023/11/22

Y1 - 2023/11/22

N2 - 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 preprocessing, present statistical analysis of the collected corpus for approximately 1500 pairs of questions and answers and describe its strengths and limitations. Also, we carry out experiments on automatic processing of the ruOHQA corpus using pre-trained transformer-based neural network models. Finally, we explore the capability of several models to generate simplified high-quality answers to questions and compare their results. The kind of research we present allows us to extract knowledge from oral history archives more productively.

AB - 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 preprocessing, present statistical analysis of the collected corpus for approximately 1500 pairs of questions and answers and describe its strengths and limitations. Also, we carry out experiments on automatic processing of the ruOHQA corpus using pre-trained transformer-based neural network models. Finally, we explore the capability of several models to generate simplified high-quality answers to questions and compare their results. The kind of research we present allows us to extract knowledge from oral history archives more productively.

KW - Corpora

KW - Question Answering

KW - Visual History Archives

UR - https://www.mendeley.com/catalogue/10aefa45-2994-394d-9d05-d3ffaeec0649/

U2 - 10.1007/978-3-031-48312-7_29

DO - 10.1007/978-3-031-48312-7_29

M3 - Conference contribution

SN - 9783031483110

T3 - Lecture Notes in Computer Science

SP - 357

EP - 366

BT - Speech and Computer

Y2 - 29 November 2023 through 1 December 2023

ER -

ID: 114283349