Related papers: A Task-Oriented Evaluation Framework for Text Norm…

Semantic Textual Similarity (STS) is a crucial component of many Natural Language Processing (NLP) applications. However, existing approaches typically reduce semantic nuances to a single score, limiting interpretability. To address this,…

Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (LLMs). Currently,…

Word sense plausibility rating requires predicting the human-perceived plausibility of a given word sense on a 1-5 scale in the context of short narrative stories containing ambiguous homonyms. This paper systematically compares three…

Despite the successes of language models, their evaluation remains a daunting challenge for new and existing tasks. We consider the task of text simplification, commonly used to improve information accessibility, where evaluation faces two…

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for…

Large Language Models (LLMs) are increasingly deployed for structured data generation, yet output consistency remains critical for production applications. We introduce a comprehensive framework for evaluating and improving consistency in…

Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks…

Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area…

Confidence estimation of predictions from an End-to-End (E2E) Automatic Speech Recognition (ASR) model benefits ASR's downstream and upstream tasks. Class-probability-based confidence scores do not accurately represent the quality of…

Stemming is the process of extracting root word from the given inflection word. It also plays significant role in numerous application of Natural Language Processing (NLP). The stemming problem has addressed in many contexts and by…

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding…

Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. While this approach has demonstrated strong improvements in…

We define multilevel text normalization as sequence-to-sequence processing that transforms naturally noisy text into a sequence of normalized units of meaning (morphemes) in three steps: 1) writing normalization, 2) lemmatization, 3)…

There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we…

Automated Essay Scoring (AES) is a cross-disciplinary effort involving Education, Linguistics, and Natural Language Processing (NLP). The efficacy of an NLP model in AES tests it ability to evaluate long-term dependencies and extrapolate…

Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance…

Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices but also enables people to express anti-social behaviour like online harassment,…

Level set estimation (LSE), the problem of identifying the set of input points where a function takes value above (or below) a given threshold, is important in practical applications. When the function is expensive-to-evaluate and…