Related papers: Stability of Syntactic Dialect Classification Over…
Dialects introduce syntactic and lexical variations in language that occur in regional or social groups. Most NLP methods are not sensitive to such variations. This may lead to unfair behavior of the methods, conveying negative bias towards…
In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without needing any parameter updates. Although there have been extensive studies on English in-context…
Spoken language change detection (LCD) refers to identifying the language transitions in a code-switched utterance. Similarly, identifying the speaker transitions in a multispeaker utterance is known as speaker change detection (SCD). Since…
High-dimensional datasets present substantial challenges in statistical modeling across various disciplines, necessitating effective dimensionality reduction methods. Deep learning approaches, notable for their capacity to distill essential…
Recent advancements in Large Speech-Language Models have significantly bridged the gap between acoustic signals and linguistic understanding. However, a persistent performance disparity remains in speech-based input tasks compared to direct…
Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been…
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space…
Localized patterns are coherent structures embedded in a quiescent state and occur in both discrete and continuous media across a wide range of applications. While it is well-understood how domain covering patterns (for example stripes and…
Large language models (LLMs) perform in-context learning (ICL) with minimal supervised examples, which benefits various natural language processing (NLP) tasks. One of the critical research focus is the selection of prompt demonstrations.…
Understanding the decision-making processes of large language models is critical given their widespread applications. To achieve this, we aim to connect a formal mathematical framework - zigzag persistence from topological data analysis -…
We address the problem of incremental sequence classification, where predictions are updated as new elements in the sequence are revealed. Drawing on temporal-difference learning from reinforcement learning, we identify a…
Effectively normalizing textual data poses a considerable challenge, especially for low-resource languages lacking standardized writing systems. In this study, we fine-tuned a multilingual model with data from several Occitan dialects and…
The socioeconomic background of people and how they use standard forms of language are not independent, as demonstrated in various sociolinguistic studies. However, the extent to which these correlations may be influenced by the mixing of…
The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks. However, recent contextual…
Accurately interpreting words is vital in political science text analysis; some tasks require assuming semantic stability, while others aim to trace semantic shifts. Traditional static embeddings, like Word2Vec effectively capture long-term…
Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…
Syntax connects words to each other in very specific ways. Two words are syntactically connected if they depend directly on each other. Syntactic connections usually happen within a sentence. Gathering all those connection across several…
High-dimensional distributed semantic spaces have proven useful and effective for aggregating and processing visual, auditory, and lexical information for many tasks related to human-generated data. Human language makes use of a large and…
We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…
This paper measures the stability of cross-linguistic register variation. A register is a variety of a language that is associated with extra-linguistic context. The relationship between a register and its context is functional: the…