Related papers: A Mutual Information Maximization Perspective of L…
Neural language models are a powerful tool to embed words into semantic vector spaces. However, learning such models generally relies on the availability of abundant and diverse training examples. In highly specialised domains this…
Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities. Traditional methods learn a single-vector embedding to represent semantics of each sample, but struggle…
Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to…
Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…
Sentence embeddings induced with various transformer architectures encode much semantic and syntactic information in a distributed manner in a one-dimensional array. We investigate whether specific grammatical information can be accessed in…
Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven…
Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we…
Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source…
The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we…
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other,…
Word embedding is central to neural machine translation (NMT), which has attracted intensive research interest in recent years. In NMT, the source embedding plays the role of the entrance while the target embedding acts as the terminal.…
In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception…
Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one…
Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…
This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to…
This paper presents a novel approach to machine learning algorithm design based on information theory, specifically mutual information (MI). We propose a framework for learning and representing functional relationships in data using…
Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the…
Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…
While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set…