Related papers: DefExt: A Semi Supervised Definition Extraction To…

We propose and study a novel supervised approach to learning statistical semantic relatedness models from subjectively annotated training examples. The proposed semantic model consists of parameterized co-occurrence statistics associated…

Effective cross-lingual transfer remains a critical challenge in scaling the benefits of large language models from high-resource to low-resource languages. Towards this goal, prior studies have explored many approaches to combine task…

Extracting topics from text has become an essential task, especially with the rapid growth of unstructured textual data. Most existing works rely on highly computational methods to address this challenge. In this paper, we argue that…

This paper proposes an efficient example sampling method for example-based word sense disambiguation systems. To construct a database of practical size, a considerable overhead for manual sense disambiguation (overhead for supervision) is…

The versatility to learn from a handful of samples is the hallmark of human intelligence. Few-shot learning is an endeavour to transcend this capability down to machines. Inspired by the promise and power of probabilistic deep learning, we…

This paper presents a model-based, unsupervised algorithm for recovering word boundaries in a natural-language text from which they have been deleted. The algorithm is derived from a probability model of the source that generated the text.…

Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem. In recent years, TSE draws increasing attention due to…

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled…

Entity extraction is an important task in text mining and natural language processing. A popular method for entity extraction is by comparing substrings from free text against a dictionary of entities. In this paper, we present several…

We show that state-of-the-art self-supervised language models can be readily used to extract relations from a corpus without the need to train a fine-tuned extractive head. We introduce RE-Flex, a simple framework that performs constrained…

This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in…

We cast a suite of information extraction tasks into a text-to-triple translation framework. Instead of solving each task relying on task-specific datasets and models, we formalize the task as a translation between task-specific input text…

Extractive summarization aims to form a summary by directly extracting sentences from the source document. Existing works mostly formulate it as a sequence labeling problem by making individual sentence label predictions. This paper…

In self-supervised visual representation learning, a feature extractor is trained on a "pretext task" for which labels can be generated cheaply, without human annotation. A central challenge in this approach is that the feature extractor…

Text summarization aims to extract essential information from a piece of text and transform the text into a concise version. Existing unsupervised abstractive summarization models leverage recurrent neural networks framework while the…

NPtool is a fast and accurate system for extracting noun phrases from English texts for the purposes of e.g. information retrieval, translation unit discovery, and corpus studies. After a general introduction, the system architecture is…

Relation extraction (RE) plays an important role in extracting knowledge from unstructured text but requires a large amount of labeled corpus. To reduce the expensive annotation efforts, semisupervised learning aims to leverage both labeled…

Conventional graph-based dependency parsers guarantee a tree structure both during training and inference. Instead, we formalize dependency parsing as the problem of independently selecting the head of each word in a sentence. Our model…

Tracking progress in machine learning has become increasingly difficult with the recent explosion in the number of papers. In this paper, we present AxCell, an automatic machine learning pipeline for extracting results from papers. AxCell…

Language Model pre-training uses broad data mixtures to enhance performance across domains and languages. However, training on such heterogeneous text corpora requires extensive and expensive efforts. Since these data sources vary…