Journal
2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021)
Volume -, Issue -, Pages 8065-8077Publisher
ASSOC COMPUTATIONAL LINGUISTICS-ACL
Keywords
-
Categories
Funding
- UK Engineering and Physical Sciences Research Council [EP/V048597/1, EP/T017112/1]
- Turing Al Fellowship - UK Research and Innovation [EP/V020579/1]
Ask authors/readers for more resources
The research explores embedding events and temporal relations in hyperbolic spaces, proposing two methods for encoding event and temporal relations. Experimental results demonstrate the advantages of revisiting tasks in different geometrical spaces.
Detecting events and their evolution through time is a crucial task in natural language understanding. Recent neural approaches to event temporal relation extraction typically map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs. However, embeddings in the Euclidean space cannot capture richer asymmetric relations such as event temporal relations. We thus propose to embed events into hyperbolic spaces, which are intrinsically oriented at modeling hierarchical structures. We introduce two approaches to encode events and their temporal relations in hyperbolic spaces. One approach leverages hyperbolic embeddings to directly infer event relations through simple geometrical operations. In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task. Thorough experimental assessments on widely used datasets have shown the benefits of revisiting the tasks on a different geometrical space, resulting in state-of-the-art performance on several standard metrics. Finally, the ablation study and several qualitative analyses highlighted the rich event semantics implicitly encoded into hyperbolic spaces. (1)
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available