Related papers: Discrete Reasoning Templates for Natural Language …

Abductive explanations (AXp's) are widely used for understanding decisions of classifiers. Existing definitions are suitable when features are independent. However, we show that ignoring constraints when they exist between features may lead…

Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power…

Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key…

Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably…

The abstract of a scientific paper distills the contents of the paper into a short paragraph. In the biomedical literature, it is customary to structure an abstract into discourse categories like BACKGROUND, OBJECTIVE, METHOD, RESULT, and…

Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning…

In this letter we present a very general method to extract information from a generic string of characters, e.g. a text, a DNA sequence or a time series. Based on data-compression techniques, its key point is the computation of a suitable…

Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map…

Humans have the innate capability to answer diverse questions, which is rooted in the natural ability to correlate different concepts based on their semantic relationships and decompose difficult problems into sub-tasks. On the contrary,…

It has recently been observed that neural language models trained on unstructured text can implicitly store and retrieve knowledge using natural language queries. In this short paper, we measure the practical utility of this approach by…

Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…

Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work proposes a simple technique for addressing this issue: use a…

Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised…

Many real-world applications (e.g., note taking, search) require extracting a sentence or paragraph from a document and showing that snippet to a human outside of the source document. Yet, users may find snippets difficult to understand as…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining…

The growing range of applications of Machine Learning (ML) in a multitude of settings motivates the ability of computing small explanations for predictions made. Small explanations are generally accepted as easier for human decision makers…

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Compositional, structured models are appealing because they explicitly decompose problems and provide interpretable intermediate outputs that give confidence that the model is not simply latching onto data artifacts. Learning these models…

Teaching a computer to read and answer general questions pertaining to a document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architecture called the Reasoning Network (ReasoNet) for machine…