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.
- Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen tau Yih, and Yejin Choi. 2020. Abductive Commonsense Reasoning. In ICLR.Google Scholar
- Chris Burges, Tal Shaked, Erin Renshaw, Ari Lazier, Matt Deeds, Nicole Hamilton,and Greg Hullender. 2005. Learning to rank using gradient descent. In ICML. 89--96.Google Scholar
- Christopher J Burges, Robert Ragno, and Quoc V Le. 2007. Learning to rank with nonsmooth cost functions. In NIPS. 193--200.Google Scholar
- Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li. 2007. Learning to rank: from pairwise approach to listwise approach. In ICML. 129--136.Google Scholar
- Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, and Diana Inkpen. 2017. Enhanced LSTM for Natural Language Inference. In ACL. 1657--1668.Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186.Google Scholar
- Ralf Herbrich. 2000. Large margin rank boundaries for ordinal regression. Advances in large margin classifiers(2000), 115--132.Google Scholar
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv: 1907.11692(2019).Google Scholar
- Charles Sanders Peirce. 1965.Principles of philosophy and Elements of logic. Vol. 1. Belknap Press of Harvard University Press.Google Scholar
- Tao Qin, Tie-Yan Liu, and Hang Li. 2010. A general approximation framework for direct optimization of information retrieval measures.Information retrieval13, 4 (2010), 375--397.Google Scholar
- Fen Xia, Tie-Yan Liu, Jue Wang, Wensheng Zhang, and Hang Li. 2008. List wise approach to learning to rank: theory and algorithm. In ICML. 1192--1199.Google Scholar
Index Terms
- L2R²: Leveraging Ranking for Abductive Reasoning
Recommendations
Quality-biased ranking for queries with commercial intent
WWW '13 Companion: Proceedings of the 22nd International Conference on World Wide WebModern search engines are good enough to answer popular commercial queries with mainly highly relevant documents. However, our experiments show that users behavior on such relevant commercial sites may differ from one to another web-site with the same ...
Ranking Relevance in Yahoo Search
KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningSearch engines play a crucial role in our daily lives. Relevance is the core problem of a commercial search engine. It has attracted thousands of researchers from both academia and industry and has been studied for decades. Relevance in a modern search ...
Abductive case-based reasoning: Research Articles
This article introduces abductive case-based reasoning (CBR) and attempts to show that abductive CBR and deductive CBR can be integrated in clinical process and problem solving. Then it provides a unified formalization for integration of abduction, ...
Comments