Probing for Bridging Inference in Transformer Language Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Probing for Bridging Inference in Transformer Language Models

Onkar Pandit
  • Function : Author
  • PersonId : 1052276
Yufang Hou
  • Function : Author
  • PersonId : 1104994


We probe pre-trained transformer language models for bridging inference. We first investigate individual attention heads in BERT and observe that attention heads at higher layers prominently focus on bridging relations incomparison with the lower and middle layers, also, few specific attention heads concentrate consistently on bridging. More importantly, we consider language models as a whole in our second approach where bridging anaphora resolution is formulated as a masked token prediction task (Of-Cloze test). Our formulation produces optimistic results without any finetuning, which indicates that pre-trained language models substantially capture bridging inference. Our further investigation shows that the distance between anaphor-antecedent and the context provided to language models play an important role in the inference.
Fichier principal
Vignette du fichier
BridgingProbingBERT.pdf (341.25 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03284110 , version 1 (12-07-2021)


  • HAL Id : hal-03284110 , version 1


Onkar Pandit, Yufang Hou. Probing for Bridging Inference in Transformer Language Models. NAACL 2021 - Annual Conference of the North American Chapter of the Association for Computational Linguistics, Jun 2021, Online Conference, Mexico. ⟨hal-03284110⟩
42 View
62 Download


Gmail Mastodon Facebook X LinkedIn More