Related papers: Rethinking Metrics for Lexical Semantic Change Det…
The driving force behind the recent success of LSTMs has been their ability to learn complex and non-linear relationships. Consequently, our inability to describe these relationships has led to LSTMs being characterized as black boxes. To…
Speech deepfake detection (SDD) focuses on identifying whether a given speech signal is genuine or has been synthetically generated. Existing audio large language model (LLM)-based methods excel in content understanding; however, their…
The Segment Anything Model (SAM) has demonstrated impressive generalization in prompt-based segmentation. Yet, the potential of semantic text prompts remains underexplored compared to traditional spatial prompts like points and boxes. This…
Word embeddings are computed by a class of techniques within natural language processing (NLP), that create continuous vector representations of words in a language from a large text corpus. The stochastic nature of the training process of…
Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap:…
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a structured semantic representation that presents the core concepts…
Distributional semantics based on neural approaches is a cornerstone of Natural Language Processing, with surprising connections to human meaning representation as well. Recent Transformer-based Language Models have proven capable of…
This study investigates how well computational embeddings align with human semantic judgments in the processing of English compound words. We compare static word vectors (GloVe) and contextualized embeddings (BERT) against human ratings of…
Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are…
Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and…
Contextual adaptation in token embeddings plays a central role in determining how well language models maintain coherence and retain semantic relationships over extended text sequences. Static embeddings often impose constraints on lexical…
Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures extracted from word embeddings, such as the soft cosine…
Most state-of-the-art sign language models are trained on interpreter or isolated vocabulary data, which overlooks the variability that characterizes natural dialogue. However, human communication dynamically adapts to contexts and…
In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a…
Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…
Change detection (CD) is a fundamental task in remote sensing (RS) which aims to detect the semantic changes between the same geographical regions at different time stamps. Existing convolutional neural networks (CNNs) based approaches…
We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings. The results of our experiments in the domain specific…
In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal…
A promising approach for knowledge-based Word Sense Disambiguation (WSD) is to select the sense whose contextualized embeddings computed for its definition sentence are closest to those computed for a target word in a given sentence. This…
Accurately classifying accents and assessing accentedness in non-native speakers are both challenging tasks due to the complexity and diversity of accent and dialect variations. In this study, embeddings from advanced pre-trained language…