Related papers: Improving Pointwise Mutual Information (PMI) by In…

The emergence of large language models (LLMs) has revolutionized numerous applications across industries. However, their "black box" nature often hinders the understanding of how they make specific decisions, raising concerns about their…

We investigate the problem of representing information measures in terms of the moments of the underlying random variables. First, we derive polynomial approximations of the conditional expectation operator. We then apply these…

We introduce a family of paper and author similarity measures based on the concept that papers are more similar if they are more likely to be retrieved during a literature search following backward and forward citations. Since this browsing…

A major computational burden, while performing document clustering, is the calculation of similarity measure between a pair of documents. Similarity measure is a function that assign a real number between 0 and 1 to a pair of documents,…

This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone does not improve performance, we introduce a novel approach…

This paper presents a new approach for measuring semantic similarity/distance between words and concepts. It combines a lexical taxonomy structure with corpus statistical information so that the semantic distance between nodes in the…

In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and…

Text classification has become indispensable due to the rapid increase of text in digital form. Over the past three decades, efforts have been made to approach this task using various learning algorithms and statistical models based on…

Cosine similarity of contextual embeddings is used in many NLP tasks (e.g., QA, IR, MT) and metrics (e.g., BERTScore). Here, we uncover systematic ways in which word similarities estimated by cosine over BERT embeddings are understated and…

This paper proposes a corpus-based language model for topic identification. We analyze the association of noun-noun and noun-verb pairs in LOB Corpus. The word association norms are based on three factors: 1) word importance, 2) pair…

Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which introduces…

Antonymy has long received particular attention in lexical semantics. Previous studies have shown that antonym pairs frequently co-occur in text, across genres and parts of speech, more often than would be expected by chance. However,…

In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos. While finding the best high-level reasoning of region assignments in videos is the focus of much recent research,…

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier…

Estimating mutual information between continuous random variables is often intractable and extremely challenging for high-dimensional data. Recent progress has leveraged neural networks to optimize variational lower bounds on mutual…

In this paper the intermediary visual content verification method based on multi-level co-occurrences is studied. The co-occurrence statistics are in general used to determine relational properties between objects based on information…

Missing data is a common problem in clinical data collection, which causes difficulty in the statistical analysis of such data. To overcome problems caused by incomplete data, we propose a new imputation method called projective resampling…

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…

Collaborative information serves as the cornerstone of recommender systems which typically focus on capturing it from user-item interactions to deliver personalized services. However, current understanding of this crucial resource remains…

The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words…