Dynamic Forecasting of Conversation Derailment

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

Standard

Dynamic Forecasting of Conversation Derailment. / Kementchedjhieva, Yova Radoslavova; Søgaard, Anders.

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. p. 7915–7919.

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

Harvard

Kementchedjhieva, YR & Søgaard, A 2021, Dynamic Forecasting of Conversation Derailment. in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, pp. 7915–7919, 2021 Conference on Empirical Methods in Natural Language Processing, 07/11/2021. https://doi.org/10.18653/v1/2021.emnlp-main.624

APA

Kementchedjhieva, Y. R., & Søgaard, A. (2021). Dynamic Forecasting of Conversation Derailment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 7915–7919). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.emnlp-main.624

Vancouver

Kementchedjhieva YR, Søgaard A. Dynamic Forecasting of Conversation Derailment. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. 2021. p. 7915–7919 https://doi.org/10.18653/v1/2021.emnlp-main.624

Author

Kementchedjhieva, Yova Radoslavova ; Søgaard, Anders. / Dynamic Forecasting of Conversation Derailment. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. pp. 7915–7919

Bibtex

@inproceedings{b338ef1d362342d8b0bad548da3c4259,
title = "Dynamic Forecasting of Conversation Derailment",
abstract = "Online conversations can sometimes take a turn for the worse, either due to systematic cultural differences, accidental misunderstandings, or mere malice. Automatically forecasting derailment in public online conversations provides an opportunity to take early action to moderate it. Previous work in this space is limited, and we extend it in several ways. We apply a pretrained language encoder to the task, which outperforms earlier approaches. We further experiment with shifting the training paradigm for the task from a static to a dynamic one to increase the forecast horizon. This approach shows mixed results: in a high-quality data setting, a longer average forecast horizon can be achieved at the cost of a small drop in F1; in a low-quality data setting, however, dynamic training propagates the noise and is highly detrimental to performance.",
author = "Kementchedjhieva, {Yova Radoslavova} and Anders S{\o}gaard",
year = "2021",
doi = "10.18653/v1/2021.emnlp-main.624",
language = "English",
pages = "7915–7919",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
publisher = "Association for Computational Linguistics",
note = "2021 Conference on Empirical Methods in Natural Language Processing ; Conference date: 07-11-2021 Through 11-11-2021",

}

RIS

TY - GEN

T1 - Dynamic Forecasting of Conversation Derailment

AU - Kementchedjhieva, Yova Radoslavova

AU - Søgaard, Anders

PY - 2021

Y1 - 2021

N2 - Online conversations can sometimes take a turn for the worse, either due to systematic cultural differences, accidental misunderstandings, or mere malice. Automatically forecasting derailment in public online conversations provides an opportunity to take early action to moderate it. Previous work in this space is limited, and we extend it in several ways. We apply a pretrained language encoder to the task, which outperforms earlier approaches. We further experiment with shifting the training paradigm for the task from a static to a dynamic one to increase the forecast horizon. This approach shows mixed results: in a high-quality data setting, a longer average forecast horizon can be achieved at the cost of a small drop in F1; in a low-quality data setting, however, dynamic training propagates the noise and is highly detrimental to performance.

AB - Online conversations can sometimes take a turn for the worse, either due to systematic cultural differences, accidental misunderstandings, or mere malice. Automatically forecasting derailment in public online conversations provides an opportunity to take early action to moderate it. Previous work in this space is limited, and we extend it in several ways. We apply a pretrained language encoder to the task, which outperforms earlier approaches. We further experiment with shifting the training paradigm for the task from a static to a dynamic one to increase the forecast horizon. This approach shows mixed results: in a high-quality data setting, a longer average forecast horizon can be achieved at the cost of a small drop in F1; in a low-quality data setting, however, dynamic training propagates the noise and is highly detrimental to performance.

U2 - 10.18653/v1/2021.emnlp-main.624

DO - 10.18653/v1/2021.emnlp-main.624

M3 - Article in proceedings

SP - 7915

EP - 7919

BT - Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics

T2 - 2021 Conference on Empirical Methods in Natural Language Processing

Y2 - 7 November 2021 through 11 November 2021

ER -

ID: 299821897