Related papers: Learning from Bootstrapping and Stepwise Reinforce…

Automatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content of text being translated from source to target domain. However, it does not explicitly maintain other…

Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels. However, collecting these annotations is expensive and…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted…

Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in…

Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impressive performances. Obtaining labeled data is often…

The growth of videos in our digital age and the users' limited time raise the demand for processing untrimmed videos to produce shorter versions conveying the same information. Despite the remarkable progress that summarization methods have…

Agents that can follow language instructions are expected to be useful in a variety of situations such as navigation. However, training neural network-based agents requires numerous paired trajectories and languages. This paper proposes…

The successful application of deep learning to many visual recognition tasks relies heavily on the availability of a large amount of labeled data which is usually expensive to obtain. The few-shot learning problem has attracted increasing…

Style transfer is the task of rewriting a sentence into a target style while approximately preserving content. While most prior literature assumes access to a large style-labelled corpus, recent work (Riley et al. 2021) has attempted…

While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of…

Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue…

Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model to generate style-transferred texts word by word in an autoregressive manner. However, such a…

For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system is initially…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Dialogue policy optimization often obtains feedback until task completion in task-oriented dialogue systems. This is insufficient for training intermediate dialogue turns since supervision signals (or rewards) are only provided at the end…

This paper explores the use of latent bootstrapping, an alternative self-supervision technique, for pretraining language models. Unlike the typical practice of using self-supervision on discrete subwords, latent bootstrapping leverages…

Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-supervised learning methods achieved impressive performance. In…

Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…