Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation

Sixing Yan; Ting Zhu

doi:10.18653/v1/2022.finnlp-1.3

Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation

Sixing Yan
, Ting Zhu

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

Automatic generating financial report from a set of news is important but challenging. The financial reports is composed of key points of the news and corresponding inferring and reasoning from specialists in financial domain with professional knowledge. The challenges lie in the effective learning of the extra knowledge that is not well presented in the news, and the misalignment between topic of input news and output knowledge in target reports. In this work, we introduce a disentangled variational topic inference approach to learn two latent variables for news and report, respectively. We use a publicly available dataset to evaluate the proposed approach. The results demonstrate its effectiveness of enhancing the language informativeness and the topic accuracy of the generated financial reports.

Original language	English
Title of host publication	FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop
Editors	Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen
Publisher	Association for Computational Linguistics (ACL)
Pages	18-24
Number of pages	7
ISBN (Electronic)	9781959429104
DOIs	https://doi.org/10.18653/v1/2022.finnlp-1.3
Publication status	Published - Dec 2022
Event	4th Workshop on Financial Technology and Natural Language Processing, FinNLP 2022 - Abu Dhabi, United Arab Emirates Duration: 8 Dec 0202 → …

Publication series

Name	Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP

Conference

Conference	4th Workshop on Financial Technology and Natural Language Processing, FinNLP 2022
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	8/12/02 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.18653/v1/2022.finnlp-1.3

Cite this

Yan, S., & Zhu, T. (2022). Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation. In C.-C. Chen, H.-H. Huang, H. Takamura, & H.-H. Chen (Eds.), FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop (pp. 18-24). (Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.finnlp-1.3

Yan, Sixing ; Zhu, Ting. / Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation. FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop. editor / Chung-Chi Chen ; Hen-Hsen Huang ; Hiroya Takamura ; Hsin-Hsi Chen. Association for Computational Linguistics (ACL), 2022. pp. 18-24 (Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP).

@inproceedings{eec48149cde64e89980959d1c30c6a9a,

title = "Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation",

abstract = "Automatic generating financial report from a set of news is important but challenging. The financial reports is composed of key points of the news and corresponding inferring and reasoning from specialists in financial domain with professional knowledge. The challenges lie in the effective learning of the extra knowledge that is not well presented in the news, and the misalignment between topic of input news and output knowledge in target reports. In this work, we introduce a disentangled variational topic inference approach to learn two latent variables for news and report, respectively. We use a publicly available dataset to evaluate the proposed approach. The results demonstrate its effectiveness of enhancing the language informativeness and the topic accuracy of the generated financial reports.",

author = "Sixing Yan and Ting Zhu",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics; 4th Workshop on Financial Technology and Natural Language Processing, FinNLP 2022 ; Conference date: 08-12-0202",

year = "2022",

month = dec,

doi = "10.18653/v1/2022.finnlp-1.3",

language = "English",

series = "Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP",

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

pages = "18--24",

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

booktitle = "FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop",

address = "Australia",

}

Yan, S & Zhu, T 2022, Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation. in C-C Chen, H-H Huang, H Takamura & H-H Chen (eds), FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop. Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP, Association for Computational Linguistics (ACL), pp. 18-24, 4th Workshop on Financial Technology and Natural Language Processing, FinNLP 2022, Abu Dhabi, United Arab Emirates, 8/12/02. https://doi.org/10.18653/v1/2022.finnlp-1.3

Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation. / Yan, Sixing; Zhu, Ting.
FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop. ed. / Chung-Chi Chen; Hen-Hsen Huang; Hiroya Takamura; Hsin-Hsi Chen. Association for Computational Linguistics (ACL), 2022. p. 18-24 (Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation

AU - Yan, Sixing

AU - Zhu, Ting

PY - 2022/12

Y1 - 2022/12

N2 - Automatic generating financial report from a set of news is important but challenging. The financial reports is composed of key points of the news and corresponding inferring and reasoning from specialists in financial domain with professional knowledge. The challenges lie in the effective learning of the extra knowledge that is not well presented in the news, and the misalignment between topic of input news and output knowledge in target reports. In this work, we introduce a disentangled variational topic inference approach to learn two latent variables for news and report, respectively. We use a publicly available dataset to evaluate the proposed approach. The results demonstrate its effectiveness of enhancing the language informativeness and the topic accuracy of the generated financial reports.

AB - Automatic generating financial report from a set of news is important but challenging. The financial reports is composed of key points of the news and corresponding inferring and reasoning from specialists in financial domain with professional knowledge. The challenges lie in the effective learning of the extra knowledge that is not well presented in the news, and the misalignment between topic of input news and output knowledge in target reports. In this work, we introduce a disentangled variational topic inference approach to learn two latent variables for news and report, respectively. We use a publicly available dataset to evaluate the proposed approach. The results demonstrate its effectiveness of enhancing the language informativeness and the topic accuracy of the generated financial reports.

UR - https://www.scopus.com/pages/publications/85153295666

U2 - 10.18653/v1/2022.finnlp-1.3

DO - 10.18653/v1/2022.finnlp-1.3

M3 - Conference proceeding

AN - SCOPUS:85153295666

T3 - Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP

SP - 18

EP - 24

BT - FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop

A2 - Chen, Chung-Chi

A2 - Huang, Hen-Hsen

A2 - Takamura, Hiroya

A2 - Chen, Hsin-Hsi

PB - Association for Computational Linguistics (ACL)

T2 - 4th Workshop on Financial Technology and Natural Language Processing, FinNLP 2022

Y2 - 8 December 0202

ER -

Yan S, Zhu T. Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation. In Chen CC, Huang HH, Takamura H, Chen HH, editors, FinNLP 2022 - 4th Workshop on Financial Technology and Natural Language Processing, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2022. p. 18-24. (Proceedings of Workshop on Financial Technology and Natural Languag, FinNLP). doi: 10.18653/v1/2022.finnlp-1.3

Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this