RuleBert: Teaching Soft Rules to Pre-trained Language Models

Saeed, M. A.; Ahmadi, Naser; Nakov, Preslav; Papotti, Paolo

doi:10.48550/arxiv.2109.13006

Cited by 3 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Embedding-based methods first convert symbolic facts and rules to embeddings and then apply neural network layers on top to softly predict answers. Recent work in deductive reasoning focused on tasks where rules and facts are expressed in natural language (Talmor et al, 2020;Saeed et al, 2021;Clark et al, 2020b;Kassner et al, 2020). Such tasks are more challenging because the model has to first understand the logic described in the natural language sentences before performing logical reasoning.…”

Section: Related Workmentioning

confidence: 99%

Reasoning over Logically Interacted Conditions for Question Answering

Sun¹,

Cohen²,

Salakhutdinov³

2022

Preprint

View full text Add to dashboard Cite

Some questions have multiple answers that are not equally correct, i.e. answers are different under different conditions. Conditions are used to distinguish answers as well as to provide additional information to support them. In this paper, we study a more challenging task where answers are constrained by a list of conditions that logically interact, which requires performing logical reasoning over the conditions to determine the correctness of the answers. Even more challenging, we only provide evidences for a subset of the conditions, so some questions may not have deterministic answers. In such cases, models are asked to find probable answers and identify conditions that need to be satisfied to make the answers correct. We propose a new model, TReasoner, for this challenging reasoning task. TReasoner consists of an entailment module, a reasoning module, and a generation module (if the answers are free-form text spans). TReasoner achieves state-of-the-art performance on two benchmark conditional QA datasets, outperforming the previous state-of-the-art by 3-10 points. 1

show abstract

Section: Related Workmentioning

confidence: 99%

Reasoning over Logically Interacted Conditions for Question Answering

Sun¹,

Cohen²,

Salakhutdinov³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Chain of thought sequence modeling. The idea of decomposing multi-step problems into intermediate steps (the so-called chain of thought [58]) and learning the intermediate steps using a sequence model has been applied to domain specific problems such as program induction [59], learning to solve math problems [60], learning to execute [61], learning to reason [62,63,64,65,66,67], and language model prompting [58]. The chain of thought imitation learning problem we formulate is domain agnostic and applicable to many sequential decision making task traditionally solved by imitation learning in a Markovian setting such as robot locomotion, navigation, manipulation, and strategy games.…”

Section: Related Workmentioning

confidence: 99%

Chain of Thought Imitation with Procedure Cloning

Yang¹,

Schuurmans²,

Abbeel³

et al. 2022

Preprint

View full text Add to dashboard Cite

Imitation learning aims to extract high-performance policies from logged demonstrations of expert behavior. It is common to frame imitation learning as a supervised learning problem in which one fits a function approximator to the input-output mapping exhibited by the logged demonstrations (input observations to output actions). While the framing of imitation learning as a supervised input-output learning problem allows for applicability in a wide variety of settings, it is also an overly simplistic view of the problem in situations where the expert demonstrations provide much richer insight into expert behavior. For example, applications such as path navigation, robot manipulation, and strategy games acquire expert demonstrations via planning, search, or some other multi-step algorithm, revealing not just the output action to be imitated but also the procedure for how to determine this action. While these intermediate computations may use tools not available to the agent during inference (e.g., environment simulators), they are nevertheless informative as a way to explain an expert's mapping of state to actions. To properly leverage expert procedure information without relying on the privileged tools the expert may have used to perform the procedure, we propose procedure cloning, which applies supervised sequence prediction to imitate the series of expert computations. This way, procedure cloning learns not only what to do (i.e., the output action), but how and why to do it (i.e., the procedure). Through empirical analysis on navigation, simulated robotic manipulation, and game-playing environments, we show that imitating the intermediate computations of an expert's behavior enables procedure cloning to learn policies exhibiting significant generalization to unseen environment configurations, including those configurations for which running the expert's procedure directly is infeasible. 1

show abstract

“…For example, there is work that uses discrete parses to template neural network components (Arabshahi et al, 2018;Mao et al, 2019;Yi et al, 2018). There is also work that seeks to embed symbolic knowledge into network parameters via special loss functions (Xu et al, 2018;Seo et al, 2021) or carefully curated datasets (Lample and Charton, 2019;Clark et al, 2020;Saeed et al, 2021) and architectures (?). Other related work seeks to incorporate logical constraints into text generation models .…”

Section: Related Workmentioning

confidence: 99%

Automatic Rule Induction for Efficient and Interpretable Semi-Supervised Learning

Pryzant¹,

Yang²,

Yi‐chong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as blackbox correlation engines that are difficult to explain and sometimes behave unreliably. In this paper, we propose tackling both of these challenges via Automatic Rule Induction (ARI), a simple and general-purpose framework for the automatic discovery and integration of symbolic rules into pretrained transformer models. First, we extract weak symbolic rules from low-capacity machine learning models trained on small amounts of labeled data. Next, we use an attention mechanism to integrate these rules into high-capacity pretrained transformer models. Last, the rule-augmented system becomes part of a self-training framework to boost supervision signal on unlabeled data. These steps can be layered beneath a variety of existing weak supervision and semisupervised NLP algorithms in order to improve performance and interpretability. Experiments across nine sequence classification and relation extraction tasks suggest that ARI can improve state-of-the-art methods with no manual effort and minimal computational overhead.

show abstract

RuleBert: Teaching Soft Rules to Pre-trained Language Models

Cited by 3 publications

References 27 publications

Reasoning over Logically Interacted Conditions for Question Answering

Reasoning over Logically Interacted Conditions for Question Answering

Chain of Thought Imitation with Procedure Cloning

Automatic Rule Induction for Efficient and Interpretable Semi-Supervised Learning

Contact Info

Product

Resources

About