Related papers: Plan-then-Generate: Controlled Data-to-Text Genera…
Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which…
Recent advances in deep neural language models combined with the capacity of large scale datasets have accelerated the development of natural language generation systems that produce fluent and coherent texts (to various degrees of success)…
Recent advances in text-to-image synthesis make it possible to visualize machine imaginations for a given context. On the other hand, when generating text, human writers are gifted at creative visualization, which enhances their writings by…
Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…
The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…
Citation generation aims to generate a citation sentence that refers to a chosen paper in the context of a manuscript. However, a rigid citation generation process is at odds with an author's desire to control specific attributes, such as…
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…
Pre-trained language models (PLM) have achieved remarkable advancement in table-to-text generation tasks. However, the lack of labeled domain-specific knowledge and the topology gap between tabular data and text make it difficult for PLMs…
Recent research in behaviour understanding through language grounding has shown it is possible to automatically generate behaviour models from textual instructions. These models usually have goal-oriented structure and are modelled with…
Text-based audio generation models have limitations as they cannot encompass all the information in audio, leading to restricted controllability when relying solely on text. To address this issue, we propose a novel model that enhances the…
End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors. We introduce an approach to learning representations of messages in dialogues by…
Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper,…
We consider the task of generating designs directly from natural language descriptions, and consider floor plan generation as the initial research area. Language conditional generative models have recently been very successful in generating…
Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not allow authors to guide text generation in desired topical…
The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story…
Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world dataset consisting of package leaflets of European medicines.…
Responses in task-oriented dialogue systems often realize multiple propositions whose ultimate form depends on the use of sentence planning and discourse structuring operations. For example a recommendation may consist of an explicitly…
Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates. However, existing methods usually train the generator and…
A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across…
Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper…