DeepAI AI Chat
Log In Sign Up

L2R2: Leveraging Ranking for Abductive Reasoning

by   Yunchang Zhu, et al.
Institute of Computing Technology, Chinese Academy of Sciences

The abductive natural language inference task (αNLI) is proposed to evaluate the abductive reasoning ability of a learning system. In the αNLI task, two observations are given and the most plausible hypothesis is asked to pick out from the candidates. Existing methods simply formulate it as a classification problem, thus a cross-entropy log-loss objective is used during training. However, discriminating true from false does not measure the plausibility of a hypothesis, for all the hypotheses have a chance to happen, only the probabilities are different. To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities. With this new perspective, a novel L2R^2 approach is proposed under the learning-to-rank framework. Firstly, training samples are reorganized into a ranking form, where two observations and their hypotheses are treated as the query and a set of candidate documents respectively. Then, an ESIM model or pre-trained language model, e.g. BERT or RoBERTa, is obtained as the scoring function. Finally, the loss functions for the ranking task can be either pair-wise or list-wise for training. The experimental results on the ART dataset reach the state-of-the-art in the public leaderboard.


page 1

page 2

page 3

page 4


Interactive Model with Structural Loss for Language-based Abductive Reasoning

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

Language Modelling via Learning to Rank

We consider language modelling (LM) as a multi-label structured predicti...

Diversify and Disambiguate: Learning From Underspecified Data

Many datasets are underspecified, which means there are several equally ...

Learning to Rank for Plausible Plausibility

Researchers illustrate improvements in contextual encoding strategies vi...

Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation

Pairwise ranking methods are the basis of many widely used discriminativ...

Multi-Stage Document Ranking with BERT

The advent of deep neural networks pre-trained via language modeling tas...

Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution

Hard cases of pronoun resolution have been used as a long-standing bench...