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.
Original language | English |
---|---|
Title of host publication | *SEM 2021 - 10th Conference on Lexical and Computational Semantics, Proceedings of the Conference |
Editors | Lun-Wei Ku, Vivi Nastase, Ivan Vulic |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 89-98 |
Number of pages | 10 |
ISBN (Electronic) | 9781954085770 |
State | Published - 2021 |
Event | 10th Conference on Lexical and Computational Semantics, *SEM 2021 - Virtual, Bangkok, Thailand Duration: 5 Aug 2021 → 6 Aug 2021 |
Publication series
Name | *SEM 2021 - 10th Conference on Lexical and Computational Semantics, Proceedings of the Conference |
---|
Conference
Conference | 10th Conference on Lexical and Computational Semantics, *SEM 2021 |
---|---|
Country/Territory | Thailand |
City | Virtual, Bangkok |
Period | 5/08/21 → 6/08/21 |
Bibliographical note
Publisher Copyright:© 2021 Lexical and Computational Semantics
Funding
The work described herein was supported in part by grants from Intel Labs, Facebook, the Israel Science Foundation grant 1951/17, the Israeli Ministry of Science and Technology and the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1).
Funders | Funder number |
---|---|
DIP | DA 1600/1-1 |
German-Israeli Project Cooperation | |
Intel Labs | |
Deutsche Forschungsgemeinschaft | |
Israel Science Foundation | 1951/17 |
Ministry of science and technology, Israel |