Related papers: T-VSE: Transformer-Based Visual Semantic Embedding
Network representation learning (NRL) methods have received significant attention over the last years thanks to their success in several graph analysis problems, including node classification, link prediction, and clustering. Such methods…
We introduce a variety of models, trained on a supervised image captioning corpus to predict the image features for a given caption, to perform sentence representation grounding. We train a grounded sentence encoder that achieves good…
Network representation learning (NRL) methods aim to map each vertex into a low dimensional space by preserving the local and global structure of a given network, and in recent years they have received a significant attention thanks to…
Convolutional neural networks (CNN) have demonstrated outstanding Compressed Sensing (CS) performance compared to traditional, hand-crafted methods. However, they are broadly limited in terms of generalisability, inductive bias and…
Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these…
Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks such as text classification, question-answering, and token classification. However, this performance is usually…
We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to…
Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological…
We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models. We evaluate three alignment…
In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering. Instead of using the original…
Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…
Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning…
It has been found that software, like natural language texts, exhibits "naturalness", which can be captured by statistical language models. In recent years, neural language models have been proposed to represent the naturalness of software…
Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…
Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…
Transformer architectures have brought about fundamental changes to computational linguistic field, which had been dominated by recurrent neural networks for many years. Its success also implies drastic changes in cross-modal tasks with…
Subword tokenization requires balancing computational efficiency and vocabulary coverage, which often leads to suboptimal performance on languages and scripts not prioritized during training. We propose to augment pretrained language models…
Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques.…
Transformer-based models are now predominant in NLP. They outperform approaches based on static models in many respects. This success has in turn prompted research that reveals a number of biases in the language models generated by…