Interactive Model with Structural Loss for Language-based Abductive Reasoning

12/01/2021
by   Linhao Li, et al.
0

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.

READ FULL TEXT
research
05/22/2020

L2R2: Leveraging Ranking for Abductive Reasoning

The abductive natural language inference task (αNLI) is proposed to eval...
research
06/07/2021

Generating Hypothetical Events for Abductive Inference

Abductive reasoning starts from some observations and aims at finding th...
research
08/27/2014

Knowledge Engineering for Planning-Based Hypothesis Generation

In this paper, we address the knowledge engineering problems for hypothe...
research
07/17/2023

Abductive Reasoning with the GPT-4 Language Model: Case studies from criminal investigation, medical practice, scientific research

This study evaluates the GPT-4 Large Language Model's abductive reasonin...
research
09/15/2023

Self-Consistent Narrative Prompts on Abductive Natural Language Inference

Abduction has long been seen as crucial for narrative comprehension and ...
research
01/16/2022

Natural Language Deduction through Search over Statement Compositions

In settings from fact-checking to question answering, we frequently want...
research
12/21/2018

Reasoning and Facts Explanation in Valuation Based Systems

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

Please sign up or login with your details

Forgot password? Click here to reset