Related papers: Learning from Bootstrapping and Stepwise Reinforce…

The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the…

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supervised formality…

Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between style polarities, UTST for controllable intensity is more…

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.…

Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals…

We consider the problem of complementary fashion prediction. Existing approaches focus on learning an embedding space where fashion items from different categories that are visually compatible are closer to each other. However, creating…

The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style". In this paper, we show that this condition is not…

Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However,…

Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. However, collecting and labeling real text images is expensive and time-consuming, which limits the availability of real data.…

Pre-trained word embeddings are the primary method for transfer learning in several Natural Language Processing (NLP) tasks. Recent works have focused on using unsupervised techniques such as language modeling to obtain these embeddings. In…

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill'…

In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk…

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…

Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent…