Related papers: Learning Multi-Relational Semantics Using Neural-E…
Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…
Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong…
Semantic Embedding Models (SEMs) have become a core component in information retrieval and natural language processing due to their ability to model semantic relevance. However, despite its growing applications in search engines, few…
Tabular deep-learning methods require embedding numerical and categorical input features into high-dimensional spaces before processing them. Existing methods deal with this heterogeneous nature of tabular data by employing separate…
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members…
Different semantic interpretation tasks such as text entailment and question answering require the classification of semantic relations between terms or entities within text. However, in most cases it is not possible to assign a direct…
While many approaches exist in the literature to learn low-dimensional representations for data collections in multiple modalities, the generalizability of multi-modal nonlinear embeddings to previously unseen data is a rather overlooked…
Implicit discourse relations bind smaller linguistic units into coherent texts. Automatic sense prediction for implicit relations is hard, because it requires understanding the semantics of the linked arguments. Furthermore, annotated…
This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning…
Using pre-trained word embeddings as input layer is a common practice in many natural language processing (NLP) tasks, but it is largely neglected for neural machine translation (NMT). In this paper, we conducted a systematic analysis on…
Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension…
Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between…
Multilingual contextual embeddings, such as multilingual BERT and XLM-RoBERTa, have proved useful for many multi-lingual tasks. Previous work probed the cross-linguality of the representations indirectly using zero-shot transfer learning on…
In recent years, multimodal AI has seen an upward trend as researchers are integrating data of different types such as text, images, speech into modelling to get the best results. This project leverages multimodal AI and matrix…
We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn…
Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on…
An interesting method of evaluating word representations is by how much they reflect the semantic representations in the human brain. However, most, if not all, previous works only focus on small datasets and a single modality. In this…
Relational representation learning has lately received an increase in interest due to its flexibility in modeling a variety of systems like interacting particles, materials and industrial projects for, e.g., the design of spacecraft. A…
Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues. However, multi-relational knowledge graphs often…