Related papers: Disentangling Linguistic Features with Dimension-W…
Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research,…
Embeddings are generic representations that are useful for many NLP tasks. In this paper, we introduce DENSIFIER, a method that learns an orthogonal transformation of the embedding space that focuses the information relevant for a task in…
Assessing personality traits using large language models (LLMs) has emerged as an interesting and challenging area of research. While previous methods employ explicit questionnaires, often derived from the Big Five model of personality, we…
Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…
Embeddings in AI convert symbolic structures into fixed-dimensional vectors, effectively fusing multiple signals. However, the nature of this fusion in real-world data is often unclear. To address this, we introduce two methods: (1)…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
Similarity measures are a vital tool for understanding how language models represent and process language. Standard representational similarity measures such as cosine similarity and Euclidean distance have been successfully used in static…
Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that…
Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…
Distributed word representations (word embeddings) have recently contributed to competitive performance in language modeling and several NLP tasks. In this work, we train word embeddings for more than 100 languages using their corresponding…
Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper,…
Self-supervised learning models for speech processing, such as wav2vec2, HuBERT, WavLM, and Whisper, generate embeddings that capture both linguistic and paralinguistic information, making it challenging to analyze tone independently of…
Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently…
Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…
We introduce a novel framework that utilizes the internal weight activations of modern Large Language Models (LLMs) to construct a metric space of languages. Unlike traditional approaches based on hand-crafted linguistic features, our…
In natural language processing (NLP) of spoken languages, word embeddings have been shown to be a useful method to encode the meaning of words. Sign languages are visual languages, which require sign embeddings to capture the visual and…
Telecom services are at the core of today's societies' everyday needs. The availability of numerous online forums and discussion platforms enables telecom providers to improve their services by exploring the views of their customers to…
Large language models (LLMs) have achieved remarkable progress in natural language generation, yet they continue to display puzzling behaviors -- such as repetition and incoherence -- even when exhibiting low perplexity. This highlights a…
Vector embedding is a foundational building block of many deep learning models, especially in natural language processing. In this paper, we present a theoretical framework for understanding the effect of dimensionality on vector…
Pitch accent detection often makes use of both acoustic and lexical features based on the fact that pitch accents tend to correlate with certain words. In this paper, we extend a pitch accent detector that involves a convolutional neural…