相关论文: Semi-Supervised Neural Text Generation by Joint Le…

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

Traditional table-to-text natural language generation (NLG) tasks focus on generating text from schemas that are already seen in the training set. This limitation curbs their generalizabilities towards real-world scenarios, where the…

Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To…

Deep neural network models have helped named entity (NE) recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to…

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two…

Recently advancements in sequence-to-sequence neural network architectures have led to an improved natural language understanding. When building a neural network-based Natural Language Understanding component, one main challenge is to…

In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images. We present a method…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e.g., Radford et al., 2019). While this approach underperforms its supervised counterpart,…

Deep learning algorithms are often said to be data hungry. The performance of such algorithms generally improve as more and more annotated data is fed into the model. While collecting unlabelled data is easier (as they can be scraped easily…

Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for…

Traditional supervised 3D medical image segmentation models need voxel-level annotations, which require huge human effort, time, and cost. Semi-supervised learning (SSL) addresses this limitation of supervised learning by facilitating…

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

Prevalent supervised learning methods in natural language processing (NLP) are notoriously data-hungry, which demand large amounts of high-quality annotated data. In practice, acquiring such data is a costly endeavor. Recently, the superior…

Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to…

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…

In the quest for super-human performance, Large Language Models (LLMs) have traditionally been tethered to human-annotated datasets and predefined training objectives-a process that is both labor-intensive and inherently limited. This paper…

Human annotations are an important source of information in the development of natural language understanding approaches. As under the pressure of productivity annotators can assign different labels to a given text, the quality of produced…

Data sparsity is one of the key challenges associated with model development in Natural Language Understanding (NLU) for conversational agents. The challenge is made more complex by the demand for high quality annotated utterances commonly…