Related papers: Unsupervised Text Generation by Learning from Sear…
Unsupervised text representation learning (TRL) is a fundamental task in natural language processing, which is beneficial for improving search and recommendations with the web's unlabeled texts. A recent empirical study finds that the…
This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement learning (RL). AsRL methods unsuccessfully scale to large…
Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language…
Automatic question generation is one of the most challenging tasks of Natural Language Processing. It requires "bidirectional" language processing: firstly, the system has to understand the input text (Natural Language Understanding) and it…
Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field. Natural language understanding is to extract the core semantic meaning from the given utterances, while natural…
Generative Artificial Intelligence (AI) has rapidly become a powerful tool, capable of generating various types of data, such as images and text. However, despite the significant advancement of generative AI, time series generative AI…
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result which correlates weakly with human judgments, whereas…
Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description. Existing methods are dominated by training models with parallel image-text pairs,…
Large language models generate fluent texts and can follow natural language instructions to solve a wide range of tasks without task-specific training. Nevertheless, it is notoriously difficult to control their generation to satisfy the…
Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level…
Recent work on unsupervised question answering has shown that models can be trained with procedurally generated question-answer pairs and can achieve performance competitive with supervised methods. In this work, we consider the task of…
This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with…
Generative Adversarial Networks (GANs) have shown great promise recently in image generation. Training GANs for language generation has proven to be more difficult, because of the non-differentiable nature of generating text with recurrent…
Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions and actions, which may cause unnecessary…
Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…
We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. Our probabilistic approach models non-parallel data from two domains as a partially observed parallel…
Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open text generation. However, controlling the generated text's properties such as the topic, style, and sentiment is challenging and often requires…
Most existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar. We propose a syntax-guided generation schema, which…
We propose GRS: an unsupervised approach to sentence simplification that combines text generation and text revision. We start with an iterative framework in which an input sentence is revised using explicit edit operations, and add…