This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of each token, including those without pre-assigned embeddings. This approach effectively addresses the out-of-vocabulary problem, too. Operating independently of large language models and shallow neural networks, it enables versatile applications such as corpus exploration, conceptual search, and word sense disambiguation. The method is designed to enhance token representations within topically homogeneous corpora, where the vocabulary is restricted to a specific domain, resulting in more meaningful embeddings compared to general-purpose pre-trained vectors. As an example, the methodology is applied to explore storm events and their impacts on infrastructure and communities using narratives from a subset of the NOAA Storm Events database. The article also demonstrates how the approach improves the representation of storm-related terms over time, providing valuable insights into the evolving nature of disaster narratives.

Natural Language Processing (NLP) is a vital computational method for addressing language processing, analysis, and generation. NLP tasks form the core of many daily applications, from automatic text correction to speech recognition. While significant research has focused on NLP tasks for the English language, less attention has been given to Modern Standard Arabic and Dialectal Arabic. Globalization has also contributed to the rise of Code-Switching (CS), where speakers mix languages within conversations and even within individual words (intra-word CS). This is especially common in Arab countries, where people often switch between dialects or between dialects and a foreign language they master. CS between Arabic and English is frequent in Egypt, especially on social media. Consequently, a significant amount of code-switched content can be found online. Such code-switched data needs to be investigated and analyzed for several NLP tasks to tackle the challenges of this multilingual phenomenon and Arabic language challenges. No work has been done before for several integral NLP tasks on Arabic-English CS data. In this work, we focus on the Named Entity Recognition (NER) task and other tasks that help propose a solution for the NER task on CS data, e.g., Language Identification. This work addresses this gap by proposing and applying state-of-the-art techniques for Modern Standard Arabic and Arabic-English NER. We have created the first annotated CS Arabic-English corpus for the NER task. Also, we apply two enhancement techniques to improve the NER tagger on CS data using CS contextual embeddings and data augmentation techniques. All methods showed improvements in the performance of the NER taggers on CS data. Finally, we propose several intra-word language identification approaches to determine the language type of a mixed text and identify whether it is a named entity or not.

As a fundamental task in natural language processing, word embedding converts each word into a representation in a vector space. A challenge with word embedding is that as the vocabulary grows, the vector space's dimension increases and it can lead to a vast model size. Storing and processing word vectors are resource-demanding, especially for mobile edge-devices applications. This paper explores word embedding dimension reduction. To balance computational costs and performance, we propose an efficient and effective weakly-supervised feature selection method, named WordFS. It has two variants, each utilizing novel criteria for feature selection. Experiments conducted on various tasks (e.g., word and sentence similarity and binary and multi-class classification) indicate that the proposed WordFS model outperforms other dimension reduction methods at lower computational costs.

Spiking neural networks (SNNs) offer a promising pathway to implement deep neural networks (DNNs) in a more energy-efficient manner since their neurons are sparsely activated and inferences are event-driven. However, there have been very few works that have demonstrated the efficacy of SNNs in language tasks partially because it is non-trivial to represent words in the forms of spikes and to deal with variable-length texts by SNNs. This work presents a "conversion + fine-tuning" two-step method for training SNNs for text classification and proposes a simple but effective way to encode pre-trained word embeddings as spike trains. We show empirically that after fine-tuning with surrogate gradients, the converted SNNs achieve comparable results to their DNN counterparts with much less energy consumption across multiple datasets for both English and Chinese. We also show that such SNNs are more robust to adversarial attacks than DNNs. Inspired by the biological neuro-synaptic framework, modern deep neural networks are successfully used in various applications (Krizhevsky et al., 2012; Graves & Jaitly, 2014; Mikolov et al., 2013b). However, the amount of computational power and energy required to run state-of-the-art deep neural models is considerable and continues to increase in the past decade. For example, a neural language model of GPT-3 (Brown et al., 2020) consumes roughly 190, 000 kWh to train (Dhar, 2020; Anthony et al., 2020), while the human brain performs perception, recognition, reasoning, control, and movement simultaneously with a power budget of just 20 W (Cox & Dean, 2014). Like biological neurons, spiking neural networks (SNNs) use discrete spikes to compute and transmit information, which are more biologically plausible and also energy-efficient than deep learning models. Spike-based computing fuelled with neuromorphic hardware provides a promising way to realize artificial intelligence while greatly reducing energy consumption. Although many studies have shown that SNNs can produce competitive results in vision (mostly classification) tasks (Cao et al., 2015; Diehl et al., 2015; Rueckauer et al., 2017; Shrestha & Orchard, 2018; Sengupta et al., 2019), there are very few works that have demonstrated their effectiveness in natural language processing (NLP) tasks (Diehl et al., 2016; Rao et al., 2022).

While Large Language Models (LLMs) become ever more dominant, classic pre-trained word embeddings sustain their relevance through computational efficiency and nuanced linguistic interpretation. Drawing from recent studies demonstrating that the convergence of GloVe and word2vec optimizations all tend towards log-co-occurrence matrix variants, we construct a novel word representation system called Bit-cipher that eliminates the need of backpropagation while leveraging contextual information and hyper-efficient dimensionality reduction techniques based on unigram frequency, providing strong interpretability, alongside efficiency. We use the bit-cipher algorithm to train word vectors via a two-step process that critically relies on a hyperparameter -- bits -- that controls the vector dimension. While the first step trains the bit-cipher, the second utilizes it under two different aggregation modes -- summation or concatenation -- to produce contextually rich representations from word co-occurrences. We extend our investigation into bit-cipher's efficacy, performing probing experiments on part-of-speech (POS) tagging and named entity recognition (NER) to assess its competitiveness with classic embeddings like word2vec and GloVe. Additionally, we explore its applicability in LM training and fine-tuning. By replacing embedding layers with cipher embeddings, our experiments illustrate the notable efficiency of cipher in accelerating the training process and attaining better optima compared to conventional training paradigms. Experiments on the integration of bit-cipher embedding layers with Roberta, T5, and OPT, prior to or as a substitute for fine-tuning, showcase a promising enhancement to transfer learning, allowing rapid model convergence while preserving competitive performance.

We present in this paper a novel scheme for multimodal learning named the Parallel Attention mechanism. In addition, to take into account the advantages of grammar and context in Vietnamese, we propose the Hierarchical Linguistic Features Extractor instead of using an LSTM network to extract linguistic features. Based on these two novel modules, we introduce the Parallel Attention Transformer (PAT), achieving the best accuracy compared to all baselines on the benchmark ViVQA dataset and other SOTA methods including SAAA and MCAN.

This paper presents a modified neural model for topic detection from a corpus and proposes a new metric to evaluate the detected topics. The new model builds upon the embedded topic model incorporating some modifications such as document clustering. Numerical experiments suggest that the new model performs favourably regardless of the document's length. The new metric, which can be computed more efficiently than widely-used metrics such as topic coherence, provides variable information regarding the understandability of the detected topics.

Part of Speech (POS) tagging is crucial to Natural Language Processing (NLP). It is a well-studied topic in several resource-rich languages. However, the development of computational linguistic resources is still in its infancy despite the existence of numerous languages that are historically and literary rich. Assamese, an Indian scheduled language, spoken by more than 25 million people, falls under this category. In this paper, we present a Deep Learning (DL)-based POS tagger for Assamese. The development process is divided into two stages. In the first phase, several pre-trained word embeddings are employed to train several tagging models. This allows us to evaluate the performance of the word embeddings in the POS tagging task. The top-performing model from the first phase is employed to annotate another set of new sentences. In the second phase, the model is trained further using the fresh dataset. Finally, we attain a tagging accuracy of 86.52% in F1 score. The model may serve as a baseline for further study on DL-based Assamese POS tagging.

In this blog, we shall discuss about how to build a neural network to translate from English to German. This problem appeared as the Capstone project for the coursera course Tensorflow 2: Customising your model, a part of the specialization Tensorflow2 for Deep Learning, by the Imperial College, London. The problem statement / description / steps are taken from the course itself. We shall use the concepts from the course, including building more flexible model architectures, freezing layers, data processing pipeline and sequence modelling. Here we shall use a language dataset from http://www.manythings.org/anki/

Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation budgets the choice of data representation is key. The goal of this paper is to better understand why this is so. With this goal in mind, we propose a metric that measures the extent to which a given representation is structurally aligned with a task. We conduct experiments on several text classification datasets testing a variety of models and representations. Using our proposed metric we show that an efficient representation for a task (i.e. one that enables learning from few samples) is a representation that induces a good alignment between latent input structure and class structure.