Related papers: Multi-task Learning for Universal Sentence Embeddi…

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question…

State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific…

Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates…

Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name…

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task…

Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences…

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex…

The increasing number of protein sequences decoded from genomes is opening up new avenues of research on linking protein sequence to function with transformer neural networks. Recent research has shown that the number of known protein…

Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network…

This doctoral thesis improves the transfer learning for sequence labeling tasks by adapting pre-trained neural language models. The proposed improvements in transfer learning involve introducing a multi-task model that incorporates an…

In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g. sentence similarity and paraphrase identification). Predominantly, two formulations are used for sentence-pair tasks: bi-encoders and cross-encoders.…

In this work, we investigate the performance of untrained randomly initialized encoders in a general class of sequence to sequence models and compare their performance with that of fully-trained encoders on the task of abstractive…

Learning two tasks in a single shared function has some benefits. Firstly by acquiring information from the second task, the shared function leverages useful information that could have been neglected or underestimated in the first task.…

Neural processes have recently emerged as a class of powerful neural latent variable models that combine the strengths of neural networks and stochastic processes. As they can encode contextual data in the network's function space, they…

Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual sentence-pair classifiers. Recent studies show that these tasks benefit from modeling…

Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common…

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to…

Argumentative structure prediction aims to establish links between textual units and label the relationship between them, forming a structured representation for a given input text. The former task, linking, has been identified by earlier…

Transfer learning aims at building robust prediction models by transferring knowledge gained from one problem to another. In the semantic Web, learning tasks are enhanced with semantic representations. We exploit their semantics to augment…

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer…