Identifying ESG Impact with Key Information

Le Qiu; Bo Peng; Jinghang Gu; Yu Yin Hsu; Emmanuele Chersoni

Identifying ESG Impact with Key Information

Le Qiu, Bo Peng, Jinghang Gu, Yu Yin Hsu, Emmanuele Chersoni

Department of Chinese and Bilingual Studies

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

The paper presents a concise summary of our work for the ML-ESG-2 shared task, exclusively on the Chinese and English datasets. ML-ESG-2 aims to ascertain the influence of news articles on corporations, specifically from an ESG perspective. To this end, we generally explored the capability of key information for impact identification and experimented with various techniques at different levels. For instance, we attempted to incorporate important information at the word level with TF-IDF, at the sentence level with TextRank, and at the document level with summarization. The final results reveal that the one with GPT-4 for summarisation yields the best predictions.

Original language	English
Title of host publication	Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing
Editors	Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen, Hiroki Sakaji, Kiyoshi Izumi
Publisher	Association for Computational Linguistics (ACL)
Pages	51-56
ISBN (Electronic)	9798891760240
Publication status	Published - Nov 2023
Event	Sixth Workshop on Financial Technology and Natural Language Processing - Nusa Dua, Bali, Indonesia Duration: 1 Nov 2023 → 1 Nov 2023 https://sites.google.com/nlg.csie.ntu.edu.tw/finnlp2023/home

Conference

Conference	Sixth Workshop on Financial Technology and Natural Language Processing
Country/Territory	Indonesia
City	Bali
Period	1/11/23 → 1/11/23
Internet address	https://sites.google.com/nlg.csie.ntu.edu.tw/finnlp2023/home

More information

Cite this

Qiu, L., Peng, B., Gu, J., Hsu, Y. Y., & Chersoni, E. (2023). Identifying ESG Impact with Key Information. In C.-C. Chen, H.-H. Huang, H. Takamura, H.-H. Chen, H. Sakaji, & K. Izumi (Eds.), Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing (pp. 51-56). Association for Computational Linguistics (ACL). https://aclanthology.org/2023.finnlp-2.7.pdf

@inproceedings{7338b5d647b04d5eb24c6395848f4b0a,

title = "Identifying ESG Impact with Key Information",

abstract = "The paper presents a concise summary of our work for the ML-ESG-2 shared task, exclusively on the Chinese and English datasets. ML-ESG-2 aims to ascertain the influence of news articles on corporations, specifically from an ESG perspective. To this end, we generally explored the capability of key information for impact identification and experimented with various techniques at different levels. For instance, we attempted to incorporate important information at the word level with TF-IDF, at the sentence level with TextRank, and at the document level with summarization. The final results reveal that the one with GPT-4 for summarisation yields the best predictions.",

author = "Le Qiu and Bo Peng and Jinghang Gu and Hsu, {Yu Yin} and Emmanuele Chersoni",

year = "2023",

month = nov,

language = "English",

pages = "51--56",

editor = "Chung-Chi Chen and Hen-Hsen Huang and Hiroya Takamura and Hsin-Hsi Chen and Hiroki Sakaji and Kiyoshi Izumi",

booktitle = "Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing",

publisher = "Association for Computational Linguistics (ACL)",

note = "Sixth Workshop on Financial Technology and Natural Language Processing ; Conference date: 01-11-2023 Through 01-11-2023",

url = "https://sites.google.com/nlg.csie.ntu.edu.tw/finnlp2023/home",

}

Qiu, L, Peng, B, Gu, J , Hsu, YY & Chersoni, E 2023, Identifying ESG Impact with Key Information. in C-C Chen, H-H Huang, H Takamura, H-H Chen, H Sakaji & K Izumi (eds), Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing. Association for Computational Linguistics (ACL), pp. 51-56, Sixth Workshop on Financial Technology and Natural Language Processing, Bali, Indonesia, 1/11/23. <https://aclanthology.org/2023.finnlp-2.7.pdf>

Identifying ESG Impact with Key Information. / Qiu, Le; Peng, Bo; Gu, Jinghang et al.
Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing. ed. / Chung-Chi Chen; Hen-Hsen Huang; Hiroya Takamura; Hsin-Hsi Chen; Hiroki Sakaji; Kiyoshi Izumi. Association for Computational Linguistics (ACL), 2023. p. 51-56.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Identifying ESG Impact with Key Information

AU - Qiu, Le

AU - Peng, Bo

AU - Gu, Jinghang

AU - Hsu, Yu Yin

AU - Chersoni, Emmanuele

PY - 2023/11

Y1 - 2023/11

N2 - The paper presents a concise summary of our work for the ML-ESG-2 shared task, exclusively on the Chinese and English datasets. ML-ESG-2 aims to ascertain the influence of news articles on corporations, specifically from an ESG perspective. To this end, we generally explored the capability of key information for impact identification and experimented with various techniques at different levels. For instance, we attempted to incorporate important information at the word level with TF-IDF, at the sentence level with TextRank, and at the document level with summarization. The final results reveal that the one with GPT-4 for summarisation yields the best predictions.

AB - The paper presents a concise summary of our work for the ML-ESG-2 shared task, exclusively on the Chinese and English datasets. ML-ESG-2 aims to ascertain the influence of news articles on corporations, specifically from an ESG perspective. To this end, we generally explored the capability of key information for impact identification and experimented with various techniques at different levels. For instance, we attempted to incorporate important information at the word level with TF-IDF, at the sentence level with TextRank, and at the document level with summarization. The final results reveal that the one with GPT-4 for summarisation yields the best predictions.

M3 - Conference article published in proceeding or book

SP - 51

EP - 56

BT - Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing

A2 - Chen, Chung-Chi

A2 - Huang, Hen-Hsen

A2 - Takamura, Hiroya

A2 - Chen, Hsin-Hsi

A2 - Sakaji, Hiroki

A2 - Izumi, Kiyoshi

PB - Association for Computational Linguistics (ACL)

T2 - Sixth Workshop on Financial Technology and Natural Language Processing

Y2 - 1 November 2023 through 1 November 2023

ER -

Identifying ESG Impact with Key Information

Abstract

Conference

More information

Fingerprint

Cite this