Related papers: A Large-Scale Sensitivity Analysis on Latent Embed…

For tabular datasets, the change in the relationship between the label and covariates ($Y|X$-shifts) is common due to missing variables (a.k.a. confounders). Since it is impossible to generalize to a completely new and unknown domain, we…

State-of-the-art approaches for metaphor detection compare their literal - or core - meaning and their contextual meaning using metaphor classifiers based on neural networks. However, metaphorical expressions evolve over time due to various…

We present a framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic. Our approach enables users to (1) understand the semantic space of the model, (2)…

Intertextuality is a central tenet in literary studies. It refers to the intricate links between literary texts that are created by various types of references. This paper proposes a new quantitative model of intertextuality to enable…

Despite the remarkable success of large large-scale neural networks, we still lack unified notation for thinking about and describing their representational spaces. We lack methods to reliably describe how their representations are…

With the increasing availability of high-dimensional data, analysts often rely on exploratory data analysis to understand complex data sets. A key approach to exploring such data is dimensionality reduction, which embeds high-dimensional…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training…

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

Many contrastive learning based models have achieved advanced performance in image-text matching tasks. The key of these models lies in analyzing the correlation between image-text pairs, which involves cross-modal interaction of embeddings…

We introduce the \textbf{Concept Field} of a text corpus: a local drift field with pointwise uncertainty, estimated in sentence-embedding space from the deltas between consecutive sentences. Given a candidate sentence transition, we score…

Studying how embeddings are organized in space not only enhances model interpretability but also uncovers factors that drive downstream task performance. In this paper, we present a comprehensive analysis of topological and geometric…

Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based neural…

To be discoverable in an embedding-based search process, each part of a document should be reflected in its embedding representation. To quantify any potential reflection biases, we introduce a permutation-based evaluation framework. With…

This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured prompts to enhance…

We investigate the pertinence of methods from algebraic topology for text data analysis. These methods enable the development of mathematically-principled isometric-invariant mappings from a set of vectors to a document embedding, which is…

There are a few prominent practices for conducting reviews of academic literature, including searching for specific keywords on Google Scholar or checking citations from some initial seed paper(s). These approaches serve a critical purpose…

The question of what kinds of linguistic information are encoded in different layers of Transformer-based language models is of considerable interest for the NLP community. Existing work, however, has overwhelmingly focused on word-level…

We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organization of document…

Low-dimensional embeddings for data from disparate sources play critical roles in multi-modal machine learning, multimedia information retrieval, and bioinformatics. In this paper, we propose a supervised dimensionality reduction method…