Related papers: Iterative method of generating artificial context-…
We present an algorithm for computing n-gram probabilities from stochastic context-free grammars, a procedure that can alleviate some of the standard problems associated with n-grams (estimation from sparse data, lack of linguistic…
Models such as finite state automata are widely used to abstract the behavior of software systems by capturing the sequences of events observable during their execution. Nevertheless, models rarely exist in practice and, when they do, get…
Background knowledge is typically needed for successful comprehension of topical and domain specific reading passages, such as in the STEM domain. However, there are few automated measures of student knowledge that can be readily deployed…
The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the context of large language models automating people-sensitive…
Recently, methods based on deep learning have dominated the field of text recognition. With a large number of training data, most of them can achieve the state-of-the-art performances. However, it is hard to harvest and label sufficient…
In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural…
An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the original sentence with their corresponding synonyms and make necessary changes to ensure the new sentences are fluent and grammatically…
Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is…
Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…
To obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While the latter approach typically…
We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices. We…
Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a…
Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft…
Often, when analyzing the behaviour of systems modelled as context-free languages, we wish to know if two languages overlap. To this end, we present an effective semi-decision procedure for regular separability of context-free languages,…
We consider the problem of learning an unknown context-free grammar when the only knowledge available and of interest to the learner is about its structural descriptions with depth at most $\ell.$ The goal is to learn a cover context-free…
Generating structured input files to test programs can be performed by techniques that produce them from a grammar that serves as the specification for syntactically correct input files. Two interesting scenarios then arise for effective…
Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even…
Recently, generative AIs like ChatGPT have become available to the wide public. These tools can for instance be used by students to generate essays or whole theses. But how does a teacher know whether a text is written by a student or an…
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains…
Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical to deploy for many use cases. We here focus on how fairness…