Related papers: Step-by-Step: Separating Planning from Realization…
The task of text classification is usually divided into two stages: {\it text feature extraction} and {\it classification}. In this standard formalization categories are merely represented as indexes in the label vocabulary, and the model…
Existing multi-agent video generation systems use LLM agents to orchestrate neural video generators, producing visually impressive but semantically unreliable outputs with no ground truth annotations. We present an agentic system that…
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…
Previous text-to-image synthesis algorithms typically use explicit textual instructions to generate/manipulate images accurately, but they have difficulty adapting to guidance in the form of coarsely matched texts. In this work, we attempt…
Researchers have relegated natural language processing tasks to Transformer-type models, particularly generative models, because these models exhibit high versatility when performing generation and classification tasks. As the size of these…
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…
Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are…
Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual states. However, can unified multimodal models trained on…
Large language models (LLMs) have been widely employed for graph-to-text generation tasks. However, the process of finetuning LLMs requires significant training resources and annotation work. In this paper, we explore the capability of…
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token,…
Iterative evaluation of LLMs during training is essential to ensure expected capability development, but can be time- and compute-intensive. While NLU tasks, where the model selects from fixed answer choices, are cheap to evaluate,…
Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…
Neural text generation (data- or text-to-text) demonstrates remarkable performance when training data is abundant which for many applications is not the case. To collect a large corpus of parallel data, heuristic rules are often used but…
Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts. While existing prompting methods are normally restricted to providing…
This paper contributes to speeding up the design and deployment of engineering dynamical systems by proposing a strategy for exploiting domain and expert knowledge for the automated generation of a dynamical system computational model…
Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…
Referring Expression Generation (REG) is the task of generating contextually appropriate references to entities. A limitation of existing REG systems is that they rely on entity-specific supervised training, which means that they cannot…
Significant progress has been made on text generation by pre-trained language models (PLMs), yet distinguishing between human and machine-generated text poses an escalating challenge. This paper offers an in-depth evaluation of three…
The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs…
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…