L2R²: Leveraging Ranking for Abductive Reasoning
Yunchang Zhu,Liang Pang,Yanyan Lan,Xueqi Cheng +3 more
- pp 1961-1964
TLDR
In this paper, a learning-to-rank framework was proposed to evaluate the abductive reasoning ability of a learning system, where two observations are given and the most plausible hypothesis is asked to pick out from the candidates.Abstract:
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 L2R2 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.read more
Citations
More filters
Posted Content
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
TL;DR: This article proposed RAINBOW, a new multi-task benchmark to evaluate commonsense models, emphasizing their generality on new tasks and building on diverse, recently introduced benchmarks, such as aNLI and commonsenseQA.
Proceedings ArticleDOI
Learning Event Graph Knowledge for Abductive Reasoning
TL;DR: This paper proposed a variational autoencoder based model ege-RoBERTa, which employs a latent variable to capture the necessary commonsense knowledge from event graph for guiding the abductive reasoning task.
Posted Content
Social Commonsense Reasoning with Multi-Head Knowledge Attention
Debjit Paul,Anette Frank +1 more
TL;DR: This work proposes a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell, and is the first to demonstrate that a model that learns to perform counterfactual reasoning helps predicting the best explanation in an abductive reasoning task.
Proceedings ArticleDOI
Generating Hypothetical Events for Abductive Inference.
Debjit Paul,Anette Frank +1 more
TL;DR: This paper propose a multi-task model MTL to solve the abduction NLI task, which predicts a plausible explanation by considering different possible events emerging from candidate hypotheses and selecting the one that is most similar to the observed outcome.
Posted Content
Generating Hypothetical Events for Abductive Inference
Debjit Paul,Anette Frank +1 more
TL;DR: This article propose a multi-task model MTL to solve the abduction NLI task, which predicts a plausible explanation by considering different possible events emerging from candidate hypotheses and selecting the one that is most similar to the observed outcome.
References
More filters
Posted Content
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yinhan Liu,Myle Ott,Naman Goyal,Jingfei Du,Mandar Joshi,Danqi Chen,Omer Levy,Michael Lewis,Luke Zettlemoyer,Veselin Stoyanov +9 more
TL;DR: It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.
Proceedings ArticleDOI
Learning to rank using gradient descent
Chris J.C. Burges,Tal Shaked,Erin L. Renshaw,Ari Lazier,Matt Deeds,Nicole A. Hamilton,Greg Hullender +6 more
TL;DR: RankNet is introduced, an implementation of these ideas using a neural network to model the underlying ranking function, and test results on toy data and on data from a commercial internet search engine are presented.
Proceedings ArticleDOI
Learning to rank: from pairwise approach to listwise approach
TL;DR: It is proposed that learning to rank should adopt the listwise approach in which lists of objects are used as 'instances' in learning, and introduces two probability models, respectively referred to as permutation probability and top k probability, to define a listwise loss function for learning.