Related papers: Semi-Supervised Event Extraction with Paraphrase C…

Events are inter-related in documents. Motivated by the one-sense-per-discourse theory, we hypothesize that a participant tends to play consistent roles across multiple events in the same document. However recent work on document-level…

Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge.…

Event extraction, the technology that aims to automatically get the structural information from documents, has attracted more and more attention in many fields. Most existing works discuss this issue with the token-level multi-label…

We propose a voting-driven semi-supervised approach to automatically acquire the typical duration of an event and use it as pseudo-labeled data. The human evaluation demonstrates that our pseudo labels exhibit surprisingly high accuracy and…

Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well…

Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain. To reduce the annotation cost, one attractive solution is to leverage a large number of unlabeled images to…

Current event detection models under super-vised learning settings fail to transfer to newevent types. Few-shot learning has not beenexplored in event detection even though it al-lows a model to perform well with high gener-alization on new…

We propose a novel unsupervised keyphrase extraction approach that filters candidate keywords using outlier detection. It starts by training word embeddings on the target document to capture semantic regularities among the words. It then…

We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains. Among event mentions…

We provide a prescription to train optimal machine-learning-based event selectors and categorizers that maximize the statistical significance of a potential signal excess in high energy physics (HEP) experiments, as quantified by any of six…

We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered…

We present an approach to event coreference resolution by developing a general framework for clustering that uses supervised representation learning. We propose a neural network architecture with novel Clustering-Oriented Regularization…

The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high…

Computational modeling is crucial for understanding and analyzing complex systems. In biology, model creation is a human dependent task that requires reading hundreds of papers and conducting wet lab experiments, which would take days or…

The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential…

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these…

Semi-supervised clustering seeks to augment traditional clustering methods by incorporating side information provided via human expertise in order to increase the semantic meaningfulness of the resulting clusters. However, most current…

Clustering is considered a non-supervised learning setting, in which the goal is to partition a collection of data points into disjoint clusters. Often a bound $k$ on the number of clusters is given or assumed by the practitioner. Many…