Comparing RNN and Transformer Context Representations in the Czech Answer Selection Task

Marek Medved, Radoslav Sabol, Aleš Horák

2022

Abstract

Open domain question answering now inevitably builds upon advanced neural models processing large unstructured textual sources serving as a kind of underlying knowledge base. In case of non-mainstream highly- inflected languages, the state-of-the-art approaches lack large training datasets emphasizing the need for other improvement techniques. In this paper, we present detailed evaluation of a new technique employing various context representations in the answer selection task where the best answer sentence from a candidate document is identified as the most relevant to the human entered question. The input data here consists not only of each sentence in isolation but also of its preceding sentence(s) as the context. We compare seven different context representations including direct recurrent network (RNN) embeddings and several BERT-model based sentence embedding vectors. All experiments are evaluated with a new version 3.1 of the Czech question answering benchmark dataset SQAD with possible multiple correct answers as a new feature. The comparison shows that the BERT-based sentence embeddings are able to offer the best context representations reaching the mean average precision results of 83.39% which is a new best score for this dataset.

Paper Citation

in Harvard Style

Medved M., Sabol R. and Horák A. (2022). Comparing RNN and Transformer Context Representations in the Czech Answer Selection Task. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-547-0, pages 388-394. DOI: 10.5220/0010827000003116

in Bibtex Style

@conference{icaart22,
author={Marek Medved and Radoslav Sabol and Aleš Horák},
title={Comparing RNN and Transformer Context Representations in the Czech Answer Selection Task},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2022},
pages={388-394},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010827000003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Comparing RNN and Transformer Context Representations in the Czech Answer Selection Task
SN - 978-989-758-547-0
AU - Medved M.
AU - Sabol R.
AU - Horák A.
PY - 2022
SP - 388
EP - 394
DO - 10.5220/0010827000003116