skip to main content


This content will become publicly available on June 1, 2024

Title: Interpretable by Design: Learning Predictors by Composing Interpretable Queries
Award ID(s):
2031985
NSF-PAR ID:
10428815
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume:
45
Issue:
6
ISSN:
0162-8828
Page Range / eLocation ID:
7430 to 7443
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be interpreted via compositional operations such as sentence fusion or difference. It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space. To more effectively bridge the continuous embedding and discrete text spaces, we explore the plausibility of incorporating various compositional properties into the sentence embedding space that allows us to interpret embedding transformations as compositional sentence operations. We propose InterSent, an end-to-end framework for learning interpretable sentence embeddings that supports compositional sentence operations in the embedding space. Our method optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddings. Experimental results demonstrate that our method significantly improves the interpretability of sentence embeddings on four textual generation tasks over existing approaches while maintaining strong performance on traditional semantic similarity tasks. 
    more » « less