Related papers: Word-Class Embeddings for Multiclass Text Classifi…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

In recent years, machine learning has been widely adopted to automate the audio mixing process. Automatic mixing systems have been applied to various audio effects such as gain-adjustment, equalization, and reverberation. These systems can…

Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear probes on hidden-state activations from Qwen3-Embedding (0.6B, 4B, 8B) to predict CEFR…

Modern transformer-based neural architectures yield impressive results in nearly every NLP task and Word Sense Disambiguation, the problem of discerning the correct sense of a word in a given context, is no exception. State-of-the-art…

Word embeddings -- distributed word representations that can be learned from unlabelled data -- have been shown to have high utility in many natural language processing applications. In this paper, we perform an extrinsic evaluation of five…

Training data for text classification is often limited in practice, especially for applications with many output classes or involving many related classification problems. This means classifiers must generalize from limited evidence, but…

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…

Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…

Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information,…

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

In this paper, we present a new approach for word sense disambiguation (WSD) using an exemplar-based learning algorithm. This approach integrates a diverse set of knowledge sources to disambiguate word sense, including part of speech of…

Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a…

Word Sense Induction (WSI) is the ability to automatically induce word senses from corpora. The WSI task was first proposed to overcome the limitations of manually annotated corpus that are required in word sense disambiguation systems.…

Multiword expressions (MWEs) are a heterogeneous set with a glaring need for classifications. Designing a satisfactory classification involves choosing features. In the case of MWEs, many features are a priori available. Not all features…

In recent years, concepts and methods of complex networks have been employed to tackle the word sense disambiguation (WSD) task by representing words as nodes, which are connected if they are semantically similar. Despite the increasingly…

By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation…

We tackle the problem of identifying metaphors in text, treated as a sequence tagging task. The pre-trained word embeddings GloVe, ELMo and BERT have individually shown good performance on sequential metaphor identification. These…

Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings…

Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…

This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing…