Related papers: Tactical Generation in a Free Constituent Order La…

Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text…

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

In task-oriented conversation systems, natural language generation systems that generate sentences with specific information related to conversation flow are useful. Our study focuses on language generation by considering various…

Early work on narrative modeling used explicit plans and goals to generate stories, but the language generation itself was restricted and inflexible. Modern methods use language models for more robust generation, but often lack an explicit…

Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose an interactive learning procedure called Mechanical Turker…

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative…

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…

Recent work has studied the emergence of language among deep reinforcement learning agents that must collaborate to solve a task. Of particular interest are the factors that cause language to be compositional -- i.e., express meaning by…

Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and…

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many…

We present a novel and effective approach for generating new clothing on a wearer through generative adversarial learning. Given an input image of a person and a sentence describing a different outfit, our model "redresses" the person as…

Undirected neural sequence models have achieved performance competitive with the state-of-the-art directed sequence models that generate monotonically from left to right in machine translation tasks. In this work, we train a policy that…

Text classification has seen an increased use in both academic and industry settings. Though rule based methods have been fairly successful, supervised machine learning has been shown to be most successful for most languages, where most…

We consider the task of text generation in language models with constraints specified in natural language. To this end, we first create a challenging benchmark Cognac that provides as input to the model a topic with example text, along with…

The ability to flexibly compose previously acquired skills to execute intelligent behaviors is a hallmark of natural intelligence. Such compositional flexibility is often attributed to context-dependent gating mechanisms that determine how…

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Natural language generation plays a critical role in spoken dialogue systems. We present a new approach to natural language generation for task-oriented dialogue using recurrent neural networks in an encoder-decoder framework. In contrast…

Prior work on generating explanations in a planning and decision-making context has focused on providing the rationale behind an AI agent's decision making. While these methods provide the right explanations from the explainer's…