In this paper, we present a tool for the semantic categorization and clustering of opendomain named entities (NEs) and common nouns (CNs), the Categorization And Clustering Tool for User-defined Semantic classes, or CACTUS. The tool performs either of the two tasks, using Hearst-style (Hearst, 1992) search queries with a web search engine: assignment of NEs/CNs to user-provided semantic classes...

Semantic similarity detection mainly relies on the availability of laboriously curated ontologies, as well supervised and unsupervised neural embedding models. In this paper, we present two domain-specific sentence models trained a natural language requirements dataset in order to derive embeddings specific software engineering domain. We use cosine-similarity measures both these The result exp...

Collection of documents annotated with semantic entities and relationships are crucial resources to support development and evaluation of text mining solutions for the biomedical domain. Here I present an overview of 36 corpora and show an analysis on the semantic annotations they contain. Annotations for entity types were classified into six semantic groups and an overview on the semantic enti...

Zero-Shot Learning (ZSL) learns models for recognizing new classes. One of the main challenges in ZSL is domain discrepancy caused by category inconsistency between training and testing data. Domain adaptation most intuitive way to address this challenge. However, existing techniques cannot be directly applied into due disjoint label space source target domains. This work proposes Transferrable...

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In typical setting, the classification loss forces segmentation model to greedily learn representations that capture inter-class variations in order determine decision (class) boundary. Due domain-shift, this boundary is unaligned target domain, resul...

To further reduce the cost of semi-supervised domain adaptation (SSDA) labeling, a more effective way is to use active learning (AL) annotate selected subset with specific properties. However, tasks are always addressed in two interactive aspects: transfer and enhancement discrimination, which requires data be both uncertain under model diverse feature space. Contrary classification tasks, it u...