Neural Event Semantics for Grounded Language Understanding

Shyamal Buch, Li Fei-Fei, Noah D. Goodman


Abstract
Abstract We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding. Our approach treats all words as classifiers that compose to form a sentence meaning by multiplying output scores. These classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention. NES is trainable end-to-end by gradient descent with minimal supervision. We evaluate our method on compositional grounded language tasks in controlled synthetic and real-world settings. NES offers stronger generalization capability than standard function-based compositional frameworks, while improving accuracy over state-of-the-art neural methods on real-world language tasks.
Anthology ID:
2021.tacl-1.52
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
875–890
Language:
URL:
https://aclanthology.org/2021.tacl-1.52
DOI:
10.1162/tacl_a_00402
Bibkey:
Cite (ACL):
Shyamal Buch, Li Fei-Fei, and Noah D. Goodman. 2021. Neural Event Semantics for Grounded Language Understanding. Transactions of the Association for Computational Linguistics, 9:875–890.
Cite (Informal):
Neural Event Semantics for Grounded Language Understanding (Buch et al., TACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2021.tacl-1.52.pdf