相关论文: Inducing Constraint Grammars

Grammars written as Constraint Handling Rules (CHR) can be executed as efficient and robust bottom-up parsers that provide a straightforward, non-backtracking treatment of ambiguity. Abduction with integrity constraints as well as other…

We explore a new language model inversion problem under strict black-box, zero-shot, and limited data conditions. We propose a novel training-free framework that reconstructs prompts using only a limited number of text outputs from a…

Constraint programming is used for a variety of real-world optimisation problems, such as planning, scheduling and resource allocation problems. At the same time, one continuously gathers vast amounts of data about these problems. Current…

Clustering is a fundamental tool that has garnered significant interest across a wide range of applications including text analysis. To improve clustering accuracy, many researchers have incorporated background knowledge, typically in the…

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

Popular debiased estimation methods for causal inference -- such as augmented inverse propensity weighting and targeted maximum likelihood estimation -- enjoy desirable asymptotic properties like statistical efficiency and double robustness…

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…

Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the…

Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science. Bayesian models that build in strong inductive biases - factors that…

Large language models' behavior is often shaped by instructions such as system prompts, refusal boundaries, privacy constraints, and tool-use rules that must hold at inference time. Yet in practice these constraints can be violated under…

A major challenge in inductive logic programming is learning big rules. To address this challenge, we introduce an approach where we join small rules to learn big rules. We implement our approach in a constraint-driven system and use…

This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based…

Prior knowledge and symbolic rules in machine learning are often expressed in the form of label constraints, especially in structured prediction problems. In this work, we compare two common strategies for encoding label constraints in a…

This paper presents a constrained policy gradient algorithm. We introduce constraints for safe learning with the following steps. First, learning is slowed down (lazy learning) so that the episodic policy change can be computed with the…

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

A statistical model for segmentation and word discovery in child directed speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described and results of empirical tests showing…

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an…

Solving constraints involving inductive (aka recursive) definitions is challenging. State-of-the-art SMT/CHC solvers and first-order logic provers provide only limited support for solving such constraints, especially when they involve,…

This paper describes an efficient rule generation algorithm, called rule generation from artificial neural networks (RGANN) to generate symbolic rules from ANNs. Classification rules are sought in many areas from automatic knowledge…