Neural Conversational QA: Learning to Reason vs Exploiting Patterns

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 794–805, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 794 Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning Lianhui Qin†‡ Vered Shwartz †‡ Peter West †‡ Chandra Bhagavatula‡ Jena D. Hwang ‡ Ronan Le Bras ‡ Antoine Bosselut †‡ Yejin Choi†‡ †Paul G. Allen School of Computer Science & Engineering, University of Washington ‡Allen Institute for Artificial Intelligence {lianhuiq, pawest, antoineb, yejin}@cs.washington.edu {vered, chandrab, jenah, ronanlb}@allenai.org Abstract Abductive and counterfactual reasoning, core abilities of everyday human cognition, require reasoning about what might have happened at time t, while conditioning on multiple contexts from the relative past and future. However, simultaneous incorporation of past and future contexts using generative language models (LMs) can be challenging, as they are trained either to condition only on the past context or to perform narrowly scoped text-infilling. In this paper, we propose DELOREAN, a new unsupervised decoding algorithm that can flex- ibly incorporate both the past and future con- texts using only off-the-shelf, left-to-right lan- guage models and no supervision. The key in- tuition of our algorithm is incorporating the fu- ture through back-propagation, during which, we only update the internal representation of the output while fixing the model parameters. By alternating between forward and backward propagation, DELOREAN can decode the out- put representation that reflects both the left and right contexts. We demonstrate that our approach is general and applicable to two nonmonotonic reasoning tasks: abductive text generation and counterfactual story revision, where DELOREAN outperforms a range of unsupervised and some supervised methods, based on automatic and human evaluation.1 1 Introduction Everyday causal reasoning requires reasoning about the likely explanations to partially observ- able past and future (abductive reasoning (Peirce, 1960)) and reasoning about the alternative future based on counterfactual past (counterfactual rea- soning). Such nonmonotonic reasoning requires 1Code is available at https://github.com/ qkaren/unsup_gen_for_cms_reasoning She hit the rope and the tire fell on top of her. Abductive Reasoning Ray hung a tire on a rope to make his daughter a swing. Past Observation Ray ran to his daughter to make sure she was okay. Future Observation Original Ending Zeke thought about being a vampire or a wizard. Then he decided on a scarier costume. Zeke dressed up like a skeleton. Zeke thought about Lannister, but he didn’t want to look like a Lannister. He wanted to look like a Stark. Zeke dressed up like a Stark. Story Context Zeke was throwing a party. All his friends were dressing up for this Halloween party. All his friends were dressing up for this Game of Thrones themed party. [Counterfactual] DELOREAN Rewritten Ending Hypothesis Counterfactual Reasoning Figure 1: DELOREAN, our proposed method, with gen- erated reasoning results. Top: the goal in abductive reasoning is to generate a hypothesis (Y ) of what hap- pened between the observed past (X) and future (Z) contexts. Bottom: In counterfactual reasoning, given a story context altered by a counterfactual condition, X, and the …

Content truncated to 500 words