Measuring Semantic Relations between Human Activities

Steven Wilson, Rada Mihalcea


Abstract
The things people do in their daily lives can provide valuable insights into their personality, values, and interests. Unstructured text data on social media platforms are rich in behavioral content, and automated systems can be deployed to learn about human activity on a broad scale if these systems are able to reason about the content of interest. In order to aid in the evaluation of such systems, we introduce a new phrase-level semantic textual similarity dataset comprised of human activity phrases, providing a testbed for automated systems that analyze relationships between phrasal descriptions of people’s actions. Our set of 1,000 pairs of activities is annotated by human judges across four relational dimensions including similarity, relatedness, motivational alignment, and perceived actor congruence. We evaluate a set of strong baselines for the task of generating scores that correlate highly with human ratings, and we introduce several new approaches to the phrase-level similarity task in the domain of human activities.
Anthology ID:
I17-1067
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
664–673
Language:
URL:
https://aclanthology.org/I17-1067
DOI:
Bibkey:
Cite (ACL):
Steven Wilson and Rada Mihalcea. 2017. Measuring Semantic Relations between Human Activities. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 664–673, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Measuring Semantic Relations between Human Activities (Wilson & Mihalcea, IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-1067.pdf
Data
SICK