Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision

• URL: http://arxiv.org/abs/2012.08012v1
• Date: Mon, 14 Dec 2020 23:50:20 GMT
• Title: Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
• Authors: Faeze Brahman, Vered Shwartz, Rachel Rudinger, Yejin Choi
• Abstract summary: We investigate the extent to which neural models can reason about natural language rationales that explain model predictions. We use pre-trained language models, neural knowledge models, and distant supervision from related tasks. Our model shows promises at generating post-hoc rationales explaining why an inference is more or less likely given the additional information.
• Score: 44.32874972577682
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The black-box nature of neural models has motivated a line of research that aims to generate natural language rationales to explain why a model made certain predictions. Such rationale generation models, to date, have been trained on dataset-specific crowdsourced rationales, but this approach is costly and is not generalizable to new tasks and domains. In this paper, we investigate the extent to which neural models can reason about natural language rationales that explain model predictions, relying only on distant supervision with no additional annotation cost for human-written rationales. We investigate multiple ways to automatically generate rationales using pre-trained language models, neural knowledge models, and distant supervision from related tasks, and train generative models capable of composing explanatory rationales for unseen instances. We demonstrate our approach on the defeasible inference task, a nonmonotonic reasoning task in which an inference may be strengthened or weakened when new information (an update) is introduced. Our model shows promises at generating post-hoc rationales explaining why an inference is more or less likely given the additional information, however, it mostly generates trivial rationales reflecting the fundamental limitations of neural language models. Conversely, the more realistic setup of jointly predicting the update or its type and generating rationale is more challenging, suggesting an important future direction.

Related papers

• Representation Surgery: Theory and Practice of Affine Steering [72.61363182652853]
  Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. One natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model's representations. This paper investigates the formal and empirical properties of steering functions.
  arXiv  Detail & Related papers  (2024-02-15T00:20:30Z)
• Emulating the Human Mind: A Neural-symbolic Link Prediction Model with Fast and Slow Reasoning and Filtered Rules [4.979279893937017]
  We introduce a novel Neural-Symbolic model named FaSt-FLiP. Our objective is to combine a logical and neural model for enhanced link prediction.
  arXiv  Detail & Related papers  (2023-10-21T12:45:11Z)
• Unsupervised Selective Rationalization with Noise Injection [7.17737088382948]
  unsupervised selective rationalization produces rationales alongside predictions by chaining two jointly-trained components, a rationale generator and a predictor. We introduce a novel training technique that effectively limits generation of implausible rationales by injecting noise between the generator and the predictor. We achieve sizeable improvements in rationale plausibility and task accuracy over the state-of-the-art across a variety of tasks, including our new benchmark.
  arXiv  Detail & Related papers  (2023-05-27T17:34:36Z)
• Can Rationalization Improve Robustness? [39.741059642044874]
  We investigate whether neural NLP models can provide robustness to adversarial attacks in addition to their interpretable nature. We generate various types of 'AddText' attacks for both token and sentence-level rationalization tasks. Our experiments reveal that the rationale models show the promise to improve robustness, while they struggle in certain scenarios.
  arXiv  Detail & Related papers  (2022-04-25T17:02:42Z)
• Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning [27.841725567976315]
  We propose a novel framework utilizing Adversarial Inverse Reinforcement Learning. This framework provides global explanations for decisions made by a Reinforcement Learning model. We capture intuitive tendencies that the model follows by summarizing the model's decision-making process.
  arXiv  Detail & Related papers  (2022-03-30T17:01:59Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• On robustness of generative representations against catastrophic forgetting [17.467589890017123]
  Catastrophic forgetting of previously learned knowledge while learning new tasks is a widely observed limitation of contemporary neural networks. In this work, we aim at answering this question by posing and validating a set of research hypotheses related to the specificity of representations built internally by neural models. We observe that representations learned by discriminative models are more prone to catastrophic forgetting than their generative counterparts, which sheds new light on the advantages of developing generative models for continual learning.
  arXiv  Detail & Related papers  (2021-09-04T11:33:24Z)
• The Neural Coding Framework for Learning Generative Models [91.0357317238509]
  We propose a novel neural generative model inspired by the theory of predictive processing in the brain. In a similar way, artificial neurons in our generative model predict what neighboring neurons will do, and adjust their parameters based on how well the predictions matched reality.
  arXiv  Detail & Related papers  (2020-12-07T01:20:38Z)
• Towards Interpretable Natural Language Understanding with Explanations as Latent Variables [146.83882632854485]
  We develop a framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Our framework treats natural language explanations as latent variables that model the underlying reasoning process of a neural model.
  arXiv  Detail & Related papers  (2020-10-24T02:05:56Z)
• Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge [96.92252296244233]
  Large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. We show that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements. Our work paves a path towards open-domain systems that constantly improve by interacting with users who can instantly correct a model by adding simple natural language statements.
  arXiv  Detail & Related papers  (2020-06-11T17:02:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.