This paper proposes a novel hierarchical learning strategy to deal with the data sparseness problem in semantic relation extraction by modeling the commonality among related classes. For each class in the hierarchy either manually predefined or automatically clustered, a discriminative function is determined in a top-down way. As the upper-level class normally has much more positive training ex...

Large-scale knowledge graphs, such as DBpedia, Wikidata, or YAGO, can be enhanced by relation extraction from text, using the data in the knowledge graph as training data, i.e., using distant supervision. While most existing approaches use language-specific methods (usually for English), we present a language-agnostic approach that exploits background knowledge from the graph instead of languag...

We present the Vancouver Event and Relation System for Extraction (VERSE)1 as a competing system for three subtasks of the BioNLP Shared Task 2016. VERSE performs full event extraction including entity, relation and modification extraction using a feature-based approach. It achieved the highest F1-score in the Bacteria Biotope (BB3) event subtask and the third highest F1-score in the Seed Devel...

This paper presents an unsupervised relation extraction algorithm, which induces relations between entity pairs by grouping them into a “natural” number of clusters based on the similarity of their contexts. Stability-based criterion is used to automatically estimate the number of clusters. For removing noisy feature words in clustering procedure, feature selection is conducted by optimizing a ...

In this paper, we present a novel approach for relation extraction using only term pairs as the input without textual features. We aim to build a single joint space for each relation which is then used to produce relation specific term embeddings. The proposed method fits particularly well for domains in which similar arguments are often associated with similar relations. It can also handle the...

Cognitive computing systems require human labeled data for evaluation, and often for training. The standard practice used in gathering this data minimizes disagreement between annotators, and we have found this results in data that fails to account for the ambiguity inherent in language. We have proposed the CrowdTruth method for collecting ground truth through crowdsourcing, that reconsiders t...

We present an approach for ontology driven extraction of relations from texts aimed mainly to produce enriched semantic annotations for the Semantic Web. The approach exploits linguistic and empirical strategies, by means of a pipeline method involving processes such as a parser, part-of-speech tagger, named entity recognition system, and pattern-based classification, and resources including on...

Previous studies on temporal relation extraction focus on mining sentence-level information or enforcing coherence on different temporal relation types among various event mentions in the same sentence or neighboring sentences, largely ignoring those discourse-level temporal relations in nonadjacent sentences. In this paper, we propose a discourse-level global inference model to mine those temp...

Experiments are reported that investigate the effect of various source document representations on the accuracy of the sentence extraction phase of a multidocument summarisation task. A novel representation is introduced based on generic relation extraction (GRE), which aims to build systems for relation identification and characterisation that can be transferred across domains and tasks withou...

Relations between entities in text have been widely researched in the natural language processing and informationextraction communities. The region connecting a pair of entities (in a parsed sentence) is often used to construct kernels or feature vectors that can recognize and extract interesting relations. Such regions are useful, but they can also incorporate unnecessary distracting informati...