Related papers: VCDM: Leveraging Variational Bi-encoding and Deep …

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Sentence compression is the task of creating a shorter version of an input sentence while keeping important information. In this paper, we extend the task of compression by deletion with the use of contextual embeddings. Different from…

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…

The way the words are used evolves through time, mirroring cultural or technological evolution of society. Semantic change detection is the task of detecting and analysing word evolution in textual data, even in short periods of time. In…

The quest for comprehensive generative models of intonation that link linguistic and paralinguistic functions to prosodic forms has been a longstanding challenge of speech communication research. Traditional intonation models have given way…

We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding--based approaches that consider each sequence separately, our proposed framework utilizes both sequences…

Deep generative models (DGMs) and their conditional counterparts provide a powerful ability for general-purpose generative modeling of data distributions. However, it remains challenging for existing methods to address advanced conditional…

Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perform discrimination. Despite great advances in model…

Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well its context. On the other hand, static word embeddings such as…

A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single…

An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural…

Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of this, the task of learning distributed representations of…

In the current literature, most embedding models are based on the encoder-only transformer architecture to extract a dense and meaningful representation of the given input, which can be a text, an image, and more. With the recent advances…

We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to…

While deep-learning models have been shown to perform well on image-to-text datasets, it is difficult to use them in practice for captioning images. This is because captions traditionally tend to be context-dependent and offer complementary…

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the…

Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through…

Pre-trained language models such as BERT have been proved to be powerful in many natural language processing tasks. But in some text classification applications such as emotion recognition and sentiment analysis, BERT may not lead to…