More Like this

1. Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification

   https://doi.org/10.18653/v1/2024.findings-naacl.165  

   Vacareanu, Robert; Alam, Fahmida; Islam, Md Asiful; Riaz, Haris; Surdeanu, Mihai (June 2024, Association for Computational Linguistics)

   This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation org:parents boost the performance on that relation by as much as 26% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component. 

   more » « less
2. Physiowise: A Physics-aware Approach to Dicrotic Notch Identification

   https://doi.org/10.1145/3578556  

   Saffarpour, Mahya; Basu, Debraj; Radaei, Fatemeh; Vali, Kourosh; Adams, Jason Y.; Chuah, Chen-Nee; Ghiasi, Soheil (April 2023, ACM Transactions on Computing for Healthcare)

   Dicrotic Notch (DN), one of the most significant and indicative features of the arterial blood pressure (ABP) waveform, becomes less pronounced and thus harder to identify as a matter of aging and pathological vascular stiffness. Generalizable and automatic DN identification for such edge cases is even more challenging in the presence of unexpected ABP waveform deformations that happen due to internal and external noise sources or pathological conditions that cause hemodynamic instability. We propose a physics-aware approach, named Physiowise (PW), that first employs a cardiovascular model to augment the original ABP waveform and reduce unexpected deformations, then apply a set of predefined rules on the augmented signal to find DN locations. We have tested the proposed method on in-vivo data gathered from 14 pigs under hemorrhage and sepsis study. Our result indicates 52% overall mean error improvement with 16% higher detection accuracy within the lowest permitted error range of 30 ms. An additional hybrid methodology is also proposed to allow combining augmentation with any application-specific user-defined rule set. 

   more » « less
3. Learning Compositional Rules via Neural Program Synthesis

   Nye, M.; Solar-Lezama, A.; Tenenbaum, J. B.; Lake, B. M. (October 2020, Advances in Neural Information Processing Systems 33 (NeurIPS 2020))

   null (Ed.)

   Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and combining these rules to form compositional rule-based systems. Current neural architectures, on the other hand, often fail to generalize in a compositional manner, especially when evaluated in ways that vary systematically from training. In this work, we present a neuro-symbolic model which learns entire rule systems from a small set of examples. Instead of directly predicting outputs from inputs, we train our model to induce the explicit system of rules governing a set of previously seen examples, drawing upon techniques from the neural program synthesis literature. Our rule-synthesis approach outperforms neural meta-learning techniques in three domains: an artificial instruction-learning domain used to evaluate human learning, the SCAN challenge datasets, and learning rule-based translations of number words into integers for a wide range of human languages. 

   more » « less
4. Equality Saturation Theory Exploration à la Carte

   https://doi.org/10.1145/3622834  

   Pal, Anjali; Saiki, Brett; Tjoa, Ryan; Richey, Cynthia; Zhu, Amy; Flatt, Oliver; Willsey, Max; Tatlock, Zachary; Nandi, Chandrakana (October 2023, Proceedings of the ACM on Programming Languages)

   Rewrite rules are critical in equality saturation, an increasingly popular technique in optimizing compilers, synthesizers, and verifiers. Unfortunately, developing high-quality rulesets is difficult and error-prone. Recent work on automatically inferring rewrite rules does not scale to large terms or grammars, and existing rule inference tools are monolithic and opaque. Equality saturation users therefore struggle to guide inference and incrementally construct rulesets. As a result, most users still manually develop and maintain rulesets. This paper proposes Enumo, a new domain-specific language for programmable theory exploration. Enumo provides a small set of core operators that enable users to strategically guide rule inference and incrementally build rulesets. Short Enumo programs easily replicate results from state-of-the-art tools, but Enumo programs can also scale to infer deeper rules from larger grammars than prior approaches. Its composable operators even facilitate developing new strategies for ruleset inference. We introduce a new fast-forwarding strategy that does not require evaluating terms in the target language, and can thus support domains that were out of scope for prior work. We evaluate Enumo and fast-forwarding across a variety of domains. Compared to state-of-the-art techniques, enumo can synthesize better rulesets over a diverse set of domains, in some cases matching the effects of manually-developed rulesets in systems driven by equality saturation. 

   more » « less
5. Alignment Completeness for Relational Hoare Logics

   https://doi.org/10.1109/LICS52264.2021.9470690  

   Nagasamudram, Ramana; Naumann, David A. (June 2021, IEEE Logic in Computer Science)

   null (Ed.)

   Relational Hoare logics (RHL) provide rules for reasoning about relations between programs. Several RHLs include a rule we call sequential product that infers a relational correctness judgment from judgments of ordinary Hoare logic (HL). Other rules embody sensible patterns of reasoning and have been found useful in practice, but sequential product is relatively complete on its own (with HL). As a more satisfactory way to evaluate RHLs, a notion of alignment completeness is introduced, in terms of the inductive assertion method and product automata. Alignment completeness results are given to account for several different sets of rules. The notion may serve to guide the design of RHLs and relational verifiers for richer programming languages and alignment patterns. 

   more » « less