Related papers: Neural Text Generation with Artificial Negative Ex…

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to…

The decoding algorithm is critical for open-ended text generation, transforming latent representations into coherent and meaningful outputs. This paper investigates the self-reinforcement effect in text generation and the effectiveness of a…

In this paper, we explore the artificial generation of typographical errors based on real-world statistics. We first draw on a small set of annotated data to compute spelling error statistics. These are then invoked to introduce errors into…

This paper seeks to develop a deeper understanding of the fundamental properties of neural text generations models. The study of artifacts that emerge in machine generated text as a result of modeling choices is a nascent research area.…

We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it.…

Although deep learning models have brought tremendous advancements to the field of open-domain dialogue response generation, recent research results have revealed that the trained models have undesirable generation behaviors, such as…

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to…

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to…

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted…

Automatically discovering failures in vision models under real-world settings remains an open challenge. This work demonstrates how off-the-shelf, large-scale, image-to-text and text-to-image models, trained on vast amounts of data, can be…

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…

Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. This paradigm leads to (i) diverse but low-quality samples due to mismatched learning objective and evaluation metric (likelihood…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

We present a novel, alternative framework for learning generative models with goal-conditioned reinforcement learning. We define two agents, a goal conditioned agent (GC-agent) and a supervised agent (S-agent). Given a user-input initial…

One of the prominent methods for explaining the decision of a machine-learning classifier is by a counterfactual example. Most current algorithms for generating such examples in the textual domain are based on generative language models.…

Generative models of language exhibit impressive capabilities but still place non-negligible probability mass over undesirable outputs. In this work, we address the task of updating a model to avoid unwanted outputs while minimally changing…

Text generation is the automated process of producing written or spoken language using computational methods. It involves generating coherent and contextually relevant text based on predefined rules or learned patterns. However, challenges…

We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…

Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples…