Related papers: Towards meta-interpretive learning of programming …
We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…
We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs,…
We have recently witnessed tremendous success of Machine Learning (ML) in practical applications. Computer vision, speech recognition and language translation have all seen a near human level performance. We expect, in the near future, most…
This report outlines an approach to learning generative models from data. We express models as probabilistic programs, which allows us to capture abstract patterns within the examples. By choosing our language for programs to be an…
Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now. We believe that it is important to leverage both the hierarchical structure of complex tasks and to use expert…
An attempt at unifying logic and functional programming is reported. As a starting point, we take the view that "logic programs" are not about logic but constitute inductive definitions of sets and relations. A skeletal language design…
New models for natural language understanding have recently made an unparalleled amount of progress, which has led some researchers to suggest that the models induce universal text representations. However, current benchmarks are…
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…
The main objective of explanations is to transmit knowledge to humans. This work proposes to construct informative explanations for predictions made from machine learning models. Motivated by the observations from social sciences, our…
Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-language (VL) models…
Typical spoken language understanding systems provide narrow semantic parses using a domain-specific ontology. The parses contain intents and slots that are directly consumed by downstream domain applications. In this work we discuss…
Software refactoring is the process of changing the structure of software without any alteration in its behavior and functionality. Presuming it is carried out in appropriate opportunities, refactoring enhances software quality…
This paper delves into the intricacies of code summarization using advanced transformer-based language models. Through empirical studies, we evaluate the efficacy of code summarization by altering function and variable names to explore…
Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity…
Multi-modal visual understanding of images with prompts involves using various visual and textual cues to enhance the semantic understanding of images. This approach combines both vision and language processing to generate more accurate…
Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream…
In this paper, we propose a new feature extraction technique for program execution logs. First, we automatically extract complex patterns from a program's behavior graph. Then, we embed these patterns into a continuous space by training an…
This paper contains examples for a companion paper "The Prolog Debugger and Declarative Programming", which discusses (in)adequacy of the Prolog debugger for declarative programming. Logic programming is a declarative programming paradigm.…
We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…
We introduce a generalized logic programming paradigm where programs, consisting of facts and rules with the usual syntax, can be enriched by co-facts, which syntactically resemble facts but have a special meaning. As in coinductive logic…