Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference

Ohad Rozen, Shmuel Amar, Vered Shwartz, Ido Dagan


Abstract
We present InferBert, a method to enhance transformer-based inference models with relevant relational knowledge. Our approach facilitates learning generic inference patterns requiring relational knowledge (e.g. inferences related to hypernymy) during training, while injecting on-demand the relevant relational facts (e.g. pangolin is an animal) at test time. We apply InferBERT to the NLI task over a diverse set of inference types (hypernymy, location, color, and country of origin), for which we collected challenge datasets. In this setting, InferBert succeeds to learn general inference patterns, from a relatively small number of training instances, while not hurting performance on the original NLI data and substantially outperforming prior knowledge enhancement models on the challenge data. It further applies its inferences successfully at test time to previously unobserved entities. InferBert is computationally more efficient than most prior methods, in terms of number of parameters, memory consumption and training time.
Anthology ID:
2021.starsem-1.8
Volume:
Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
Month:
August
Year:
2021
Address:
Online
Editors:
Lun-Wei Ku, Vivi Nastase, Ivan Vulić
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
89–98
Language:
URL:
https://aclanthology.org/2021.starsem-1.8
DOI:
10.18653/v1/2021.starsem-1.8
Bibkey:
Cite (ACL):
Ohad Rozen, Shmuel Amar, Vered Shwartz, and Ido Dagan. 2021. Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 89–98, Online. Association for Computational Linguistics.
Cite (Informal):
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference (Rozen et al., *SEM 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.starsem-1.8.pdf
Code
 ohadrozen/inferbert
Data
GLUEMultiNLI