DeepAI AI Chat
Log In Sign Up

Interactive Model with Structural Loss for Language-based Abductive Reasoning

by   Linhao Li, et al.
Hebei University of Technology
Tianjin University
West Virginia University

The abductive natural language inference task (αNLI) is proposed to infer the most plausible explanation between the cause and the event. In the αNLI 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 αNLI: 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.


L2R2: Leveraging Ranking for Abductive Reasoning

The abductive natural language inference task (αNLI) is proposed to eval...

Generating Hypothetical Events for Abductive Inference

Abductive reasoning starts from some observations and aims at finding th...

Knowledge Engineering for Planning-Based Hypothesis Generation

In this paper, we address the knowledge engineering problems for hypothe...

Natural Language Deduction through Search over Statement Compositions

In settings from fact-checking to question answering, we frequently want...

Reasoning and Facts Explanation in Valuation Based Systems

In the literature, the optimization problem to identify a set of composi...

Learning to Rank for Plausible Plausibility

Researchers illustrate improvements in contextual encoding strategies vi...

Using Hypotheses as a Debugging Aid

As developers debug, developers formulate hypotheses about the cause of ...