Related papers: Controllable Paraphrase Generation with a Syntacti…

Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is…

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…

An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural…

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate. While modifying the pretrained models via fine-tuning remains the…

We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by…

We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth. In contrast to earlier work, our method uses in-context learning rather than finetuning, making it…

Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controlling several stylistic aspects of the generated text, in addition to its content. The method is based…

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representations of a logical…

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…

Recent advancements in self-attention neural network architectures have raised the bar for open-ended text generation. Yet, while current methods are capable of producing a coherent text which is several hundred words long, attaining…

We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem…

This paper proposes a novel neural model for the understudied task of generating text from keywords. The model takes as input a set of un-ordered keywords, and part-of-speech (POS) based template instructions. This makes it ideal for…

In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and…

Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In…

We consider the problem of parsing natural language descriptions into source code written in a general-purpose programming language like Python. Existing data-driven methods treat this problem as a language generation task without…

Existing pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel framework that uses large-scale language models and adds…

Many neural network models nowadays have achieved promising performances in Chit-chat settings. The majority of them rely on an encoder for understanding the post and a decoder for generating the response. Without given assigned semantics,…

Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. In this work, we explore the hypothesis that syntactic dependencies can be represented in language model attention…

Syntactically controlled paraphrase generation has become an emerging research direction in recent years. Most existing approaches require annotated paraphrase pairs for training and are thus costly to extend to new domains. Unsupervised…

Machine-generated citation sentences can aid automated scientific literature review and assist article writing. Current methods in generating citation text were limited to single citation generation using the citing document and a cited…