HYPHEN: Hyperbolic Hawkes Attention For Text Streams

Shivam Agarwal, Ramit Sawhney, Sanchit Ahuja, Ritesh Soun, Sudheer Chava


Abstract
Analyzing the temporal sequence of texts from sources such as social media, news, and parliamentary debates is a challenging problem as it exhibits time-varying scale-free properties and fine-grained timing irregularities. We propose a Hyperbolic Hawkes Attention Network (HYPHEN), which learns a data-driven hyperbolic space and models irregular powerlaw excitations using a hyperbolic Hawkes process. Through quantitative and exploratory experiments over financial NLP, suicide ideation detection, and political debate analysis we demonstrate HYPHEN’s practical applicability for modeling online text sequences in a geometry agnostic manner.
Anthology ID:
2022.acl-short.69
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
620–627
Language:
URL:
https://aclanthology.org/2022.acl-short.69
DOI:
10.18653/v1/2022.acl-short.69
Bibkey:
Cite (ACL):
Shivam Agarwal, Ramit Sawhney, Sanchit Ahuja, Ritesh Soun, and Sudheer Chava. 2022. HYPHEN: Hyperbolic Hawkes Attention For Text Streams. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 620–627, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
HYPHEN: Hyperbolic Hawkes Attention For Text Streams (Agarwal et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.acl-short.69.pdf
Software:
 2022.acl-short.69.software.zip
Code
 gtfintechlab/hyphen-acl
Data
StockNet