State-of-the-art (SOTA) Automatic Speech Recognition (ASR) systems primarily rely on acoustic information while disregarding additional multi-modal context. However, visual information are essential in disambiguation and adaptation. While most work focus on speaker images to handle noise conditions, this work also focuses on integrating presentation slides for the use cases of scientific presentation. In a first step, we create a benchmark for multi-modal presentation including an automatic analysis of transcribing domain-specific terminology. Next, we explore methods for augmenting speech models with multi-modal information. We mitigate the lack of datasets with accompanying slides by a suitable approach of data augmentation. Finally, we train a model using the augmented dataset, resulting in a relative reduction in word error rate of approximately 34%, across all words and 35%, for domain-specific terms compared to the baseline model.

We present a variety of methods for training complex-valued word embeddings, based on the classical Skip-gram model, with a straightforward adaptation simply replacing the real-valued vectors with arbitrary vectors of complex numbers. In a more "physically-inspired" approach, the vectors are produced by parameterised quantum circuits (PQCs), which are unitary transformations resulting in normalised vectors which have a probabilistic interpretation. We develop a complex-valued version of the highly optimised C code version of Skip-gram, which allows us to easily produce complex embeddings trained on a 3.8B-word corpus for a vocabulary size of over 400k, for which we are then able to train a separate PQC for each word. We evaluate the complex embeddings on a set of standard similarity and relatedness datasets, for some models obtaining results competitive with the classical baseline. We find that, while training the PQCs directly tends to harm performance, the quantum word embeddings from the two-stage process perform as well as the classical Skip-gram embeddings with comparable numbers of parameters. This enables a highly scalable route to learning embeddings in complex spaces which scales with the size of the vocabulary rather than the size of the training corpus. In summary, we demonstrate how to produce a large set of high-quality word embeddings for use in complex-valued and quantum-inspired NLP models, and for exploring potential advantage in quantum NLP models.

This paper introduces Cobweb4L, a novel approach for efficient language model learning that supports masked word prediction. The approach builds on Cobweb, an incremental system that learns a hierarchy of probabilistic concepts. Each concept stores the frequencies of words that appear in instances tagged with that concept label. The system utilizes an attribute value representation to encode words and their surrounding context into instances. Cobweb4L uses the information theoretic variant of category utility and a new performance mechanism that leverages multiple concepts to generate predictions. We demonstrate that with these extensions it significantly outperforms prior Cobweb performance mechanisms that use only a single node to generate predictions. Further, we demonstrate that Cobweb4L learns rapidly and achieves performance comparable to and even superior to Word2Vec. Next, we show that Cobweb4L and Word2Vec outperform BERT in the same task with less training data. Finally, we discuss future work to make our conclusions more robust and inclusive.

End-to-end (E2E) automatic speech recognition (ASR) models have become standard practice for various commercial applications. However, in real-world scenarios, the long-tailed nature of word distribution often leads E2E ASR models to perform well on common words but fall short in recognizing uncommon ones. Recently, the notion of a contextual adapter (CA) was proposed to infuse external knowledge represented by a context word list into E2E ASR models. Although CA can improve recognition performance on rare words, two crucial data imbalance problems remain. First, when using low-frequency words as context words during training, since these words rarely occur in the utterance, CA becomes prone to overfit on attending to the token due to higher-frequency words not being present in the context list. Second, the long-tailed distribution within the context list itself still causes the model to perform poorly on low-frequency context words. In light of this, we explore in-depth the impact of altering the context list to have words with different frequency distributions on model performance, and meanwhile extend CA with a simple yet effective context-balanced learning objective. A series of experiments conducted on the AISHELL-1 benchmark dataset suggests that using all vocabulary words from the training corpus as the context list and pairing them with our balanced objective yields the best performance, demonstrating a significant reduction in character error rate (CER) by up to 1.21% and a more pronounced 9.44% reduction in the error rate of zero-shot words.

As a highly successful word embedding model, Word2Vec offers an efficient method for learning distributed word representations on large datasets. However, Word2Vec lacks consideration for distances between center and context words. We propose two novel methods, Learnable Formulated Weights (LFW) and Epoch-based Dynamic Window Size (EDWS), to incorporate distance information into two variants of Word2Vec, the Continuous Bag-of-Words (CBOW) model and the Continuous Skip-gram (Skip-gram) model. For CBOW, LFW uses a formula with learnable parameters that best reflects the relationship of influence and distance between words to calculate distance-related weights for average pooling, providing insights for future NLP text modeling research. For Skip-gram, we improve its dynamic window size strategy to introduce distance information in a more balanced way. Experiments prove the effectiveness of LFW and EDWS in enhancing Word2Vec's performance, surpassing previous state-of-the-art methods.

Word meanings change over time, and word senses evolve, emerge or die out in the process. For ancient languages, where the corpora are often small and sparse, modelling such changes accurately proves challenging, and quantifying uncertainty in sense-change estimates consequently becomes important. GASC (Genre-Aware Semantic Change) and DiSC (Diachronic Sense Change) are existing generative models that have been used to analyse sense change for target words from an ancient Greek text corpus, using unsupervised learning without the help of any pre-training. These models represent the senses of a given target word such as "kosmos" (meaning decoration, order or world) as distributions over context words, and sense prevalence as a distribution over senses. The models are fitted using Markov Chain Monte Carlo (MCMC) methods to measure temporal changes in these representations. In this paper, we introduce EDiSC, an Embedded DiSC model, which combines word embeddings with DiSC to provide superior model performance. We show empirically that EDiSC offers improved predictive accuracy, ground-truth recovery and uncertainty quantification, as well as better sampling efficiency and scalability properties with MCMC methods. We also discuss the challenges of fitting these models.

Word2Vec remains one of the highly-impactful innovations in the field of Natural Language Processing (NLP) that represents latent grammatical and syntactical information in human text with dense vectors in a low dimension. Word2Vec has high computational cost due to the algorithm's inherent sequentiality, intensive memory accesses, and the large vocabularies it represents. While prior studies have investigated technologies to explore parallelism and improve memory system performance, they struggle to effectively gain throughput on powerful GPUs. We identify memory data access and latency as the primary bottleneck in prior works on GPUs, which prevents highly optimized kernels from attaining the architecture's peak performance. We present a novel algorithm, FULL-W2V, which maximally exploits the opportunities for data reuse in the W2V algorithm and leverages GPU architecture and resources to reduce access to low memory levels and improve temporal locality. FULL-W2V is capable of reducing accesses to GPU global memory significantly, e.g., by more than 89\%, compared to prior state-of-the-art GPU implementations, resulting in significant performance improvement that scales across successive hardware generations. Our prototype implementation achieves 2.97X speedup when ported from Nvidia Pascal P100 to Volta V100 cards, and outperforms the state-of-the-art by 5.72X on V100 cards with the same embedding quality. In-depth analysis indicates that the reduction of memory accesses through register and shared memory caching and high-throughput shared memory reduction leads to a significantly improved arithmetic intensity. FULL-W2V can potentially benefit many applications in NLP and other domains.

Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual informativeness with respect to a given target word. Our study makes three main contributions. First, we develop models for estimating contextual informativeness, focusing on the instructional aspect of sentences. Our attention-based approach using pre-trained embeddings demonstrates state-of-the-art performance on our single-context dataset and an existing multi-sentence context dataset. Second, we show how our model identifies key contextual elements in a sentence that are likely to contribute most to a reader's understanding of the target word. Third, we examine how our contextual informativeness model, originally developed for vocabulary learning applications for students, can be used for developing better training curricula for word embedding models in batch learning and few-shot machine learning settings. We believe our results open new possibilities for applications that support language learning for both human and machine learners.

Recent research has shown that static word embeddings can encode word frequency information. However, little has been studied about this phenomenon and its effects on downstream tasks. In the present work, we systematically study the association between frequency and semantic similarity in several static word embeddings. We find that Skip-gram, GloVe and FastText embeddings tend to produce higher semantic similarity between high-frequency words than between other frequency combinations. We show that the association between frequency and similarity also appears when words are randomly shuffled. This proves that the patterns found are not due to real semantic associations present in the texts, but are an artifact produced by the word embeddings. Finally, we provide an example of how word frequency can strongly impact the measurement of gender bias with embedding-based metrics. In particular, we carry out a controlled experiment that shows that biases can even change sign or reverse their order by manipulating word frequencies.

The present study proposes a novel method of trend detection and visualization - more specifically, modeling the change in a topic over time. Where current models used for the identification and visualization of trends only convey the popularity of a singular word based on stochastic counting of usage, the approach in the present study illustrates the popularity and direction that a topic is moving in. The direction in this case is a distinct subtopic within the selected corpus. Such trends are generated by modeling the movement of a topic by using k-means clustering and cosine similarity to group the distances between clusters over time. In a convergent scenario, it can be inferred that the topics as a whole are meshing (tokens between topics, becoming interchangeable). On the contrary, a divergent scenario would imply that each topics' respective tokens would not be found in the same context (the words are increasingly different to each other). The methodology was tested on a group of articles from various media houses present in the 20 Newsgroups dataset.