Related papers: A Novel Computational and Modeling Foundation for …
Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…
Linguistic entrainment is a phenomenon where people tend to mimic each other in conversation. The core instrument to quantify entrainment is a linguistic similarity measure between conversational partners. Most of the current similarity…
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…
Discourse cohesion facilitates text comprehension and helps the reader form a coherent narrative. In this study, we aim to computationally analyze the discourse cohesion in scientific scholarly texts using multilayer network representation…
Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…
While large pretrained language models (PLMs) demonstrate incredible fluency and performance on many natural language tasks, recent work has shown that well-performing PLMs are very sensitive to what prompts are feed into them. Even when…
Automatic summarization of natural language is a current topic in computer science research and industry, studied for decades because of its usefulness across multiple domains. For example, summarization is necessary to create reviews such…
Automatic evaluation metrics are essential for the rapid development of open-domain dialogue systems as they facilitate hyper-parameter tuning and comparison between models. Although recently proposed trainable conversation-level metrics…
We devise an algorithm to generate propositions that objectively instantiate graphs supporting coherence-driven inference. We also benchmark the ability of large language models (LLMs) to reconstruct coherence graphs from (a simple…
In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are either converging or…
Text summarizing is a critical Natural Language Processing (NLP) task with applications ranging from information retrieval to content generation. Large Language Models (LLMs) have shown remarkable promise in generating fluent abstractive…
Large Language Models (LLMs) are increasingly deployed in critical applications requiring reliable reasoning, yet their internal reasoning processes remain difficult to evaluate systematically. Existing methods focus on final-answer…
Research suggests "write-to-learn" tasks improve learning outcomes, yet constructed-response methods of formative assessment become unwieldy with large class sizes. This study evaluates natural language processing algorithms to assist this…
Natural Language Processing (NLP) is an important branch of artificial intelligence that studies how to enable computers to understand, process, and generate human language. Text classification is a fundamental task in NLP, which aims to…
Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for both humans and machines. This work studies automatic quotation…
We investigate mathematically the notion of incoherence: a structural issue with reinforcement learning policies derived by naive goal-conditioning of autoregressive models. We focus on the process of re-training models on their own…
State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel'…
The non-humanlike behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon of such faulty behaviours is the generation of inconsistent predictions, which…
Empathy requires perspective-taking: empathetic responses require a person to reason about what another has experienced and communicate that understanding in language. However, most NLP approaches to empathy do not explicitly model this…
Quantum phase estimation is a core task in quantum technologies ranging from metrology to quantum computing, where it appears as a key subroutine in various algorithms. Here, we quantitatively connect the performance of phase estimation…