Related papers: LOGEN: Few-shot Logical Knowledge-Conditioned Text…

The knowledge graph (KG) stores a large amount of structural knowledge, while it is not easy for direct human understanding. Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the KG, and at…

We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically employ…

We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game between speakers and listeners, in which a speaker should…

Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…

Few-shot learning (FSL) aims to enable models to recognize novel objects or classes with limited labelled data. Feature generators, which synthesize new data points to augment limited datasets, have emerged as a promising solution to this…

Knowledge graphs (KGs) often contain sufficient information to support the inference of new facts. Identifying logical rules not only improves the completeness of a knowledge graph but also enables the detection of potential errors, reveals…

Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages…

Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios. However, if data in additional modalities exist (e.g. text) this can…

Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We…

Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…

Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data and text, especially…

The rampant proliferation of large language models, fluent enough to generate text indistinguishable from human-written language, gives unprecedented importance to the detection of machine-generated text. This work is motivated by an…

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing information retrieval systems. This paper presents a few-shot…

Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly…

Recently some studies have highlighted the potential of Large Language Models (LLMs) as effective generators of supervised training data, offering advantages such as enhanced inference efficiency and reduced costs associated with data…

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part…

Few-shot relation classification seeks to classify incoming query instances after meeting only few support instances. This ability is gained by training with large amount of in-domain annotated data. In this paper, we tackle an even harder…

Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem…