Related papers: Determining the Unithood of Word Sequences using a…
To address the challenge of quantifying uncertainty in the outputs generated by language models, we propose a novel measure of semantic uncertainty, semantic spectral entropy, that is statistically consistent under mild assumptions. This…
Sentence ordering is a general and critical task for natural language generation applications. Previous works have focused on improving its performance in an external, downstream task, such as multi-document summarization. Given its…
Based on existing ideas in the field of imprecise probabilities, we present a new approach for assessing the reliability of the individual predictions of a generative probabilistic classifier. We call this approach robustness…
Stopword removal is a critical stage in many Machine Learning methods but often receives little consideration, it interferes with the model visualizations and disrupts user confidence. Inappropriately chosen or hastily omitted stopwords not…
Conducting experiments with diverse participants in their native languages can uncover insights into culture, cognition, and language that may not be revealed otherwise. However, conducting these experiments online makes it difficult to…
Large Language Models (LLMs) have shown significant advances in text generation but often lack the reliability needed for autonomous deployment in high-stakes domains like healthcare, law, and finance. Existing approaches rely on external…
This dissertation presents several new methods of supervised and unsupervised learning of word sense disambiguation models. The supervised methods focus on performing model searches through a space of probabilistic models, and the…
Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best…
Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine…
Automated reasoning about uncertain knowledge has many applications. One difficulty when developing such systems is the lack of a completely satisfactory integration of logic and probability. We address this problem directly. Expressive…
In this paper, we introduce a new measure called Term_Class relevance to compute the relevancy of a term in classifying a document into a particular class. The proposed measure estimates the degree of relevance of a given term, in placing…
Diversity in patent language is growing and makes finding synonyms for conducting patent searches more and more challenging. In addition to that, most approaches for dealing with diverse patent language are based on manual search and human…
This paper proposes a method for measuring semantic similarity between words as a new tool for text analysis. The similarity is measured on a semantic network constructed systematically from a subset of the English dictionary, LDOCE…
Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the…
Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised…
This writing: a) Draws attention to the intricacies inherent to the pursuit of a universal seizure definition even when powerful, well understood signal analysis methods are utilized to this end; b) Identifies this aim as a multi-objective…
We consider the task of performing probabilistic inference with probabilistic logical models. Many algorithms for approximate inference with such models are based on sampling. From a logic programming perspective, sampling boils down to…
Discovering a lexicon from unlabeled audio is a longstanding challenge for zero-resource speech processing. One approach is to search for frequently occurring patterns in speech. We revisit this idea with DUSTED: Discrete Unit Spoken-TErm…
Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the…
Probabilistic approaches to part-of-speech tagging rely primarily on whole-word statistics about word/tag combinations as well as contextual information. But experience shows about 4 per cent of tokens encountered in test sets are unknown…