English

Interactive Model with Structural Loss for Language-based Abductive Reasoning

Computation and Language 2022-12-21 v2 Artificial Intelligence

Abstract

The abductive natural language inference task (α\alphaNLI) is proposed to infer the most plausible explanation between the cause and the event. In the α\alphaNLI task, two observations are given, and the most plausible hypothesis is asked to pick out from the candidates. Existing methods model the relation between each candidate hypothesis separately and penalize the inference network uniformly. In this paper, we argue that it is unnecessary to distinguish the reasoning abilities among correct hypotheses; and similarly, all wrong hypotheses contribute the same when explaining the reasons of the observations. Therefore, we propose to group instead of ranking the hypotheses and design a structural loss called ``joint softmax focal loss'' in this paper. Based on the observation that the hypotheses are generally semantically related, we have designed a novel interactive language model aiming at exploiting the rich interaction among competing hypotheses. We name this new model for α\alphaNLI: Interactive Model with Structural Loss (IMSL). The experimental results show that our IMSL has achieved the highest performance on the RoBERTa-large pretrained model, with ACC and AUC results increased by about 1\% and 5\% respectively.

Keywords

Cite

@article{arxiv.2112.00284,
  title  = {Interactive Model with Structural Loss for Language-based Abductive Reasoning},
  author = {Linhao Li and Ming Xu and Yongfeng Dong and Xin Li and Ao Wang},
  journal= {arXiv preprint arXiv:2112.00284},
  year   = {2022}
}

Comments

The paper is under consideration at Pattern Recognition Letters

R2 v1 2026-06-24T07:59:06.134Z