Relation extraction aims to extract semantic relationships between two specified named entities in a sentence. Because sentence often contains several entity pairs, neural network is easily bewildered when learning relation representation without position and information about the considered pair. In this paper, instead of an abstract from raw inputs, task-related indicators are designed enable...

Semantic relation extraction aims to extract relation instances from natural language texts. In this paper, we propose a semantic relation extraction approach based on simple relation templates that determine relation types and their arguments. We attempt to reduce semantic drift of the arguments by using named entity models as semantic constraints. Experimental results indicate that our approa...

Most existing relation extraction models make predictions for each entity pair locally and individually, while ignoring implicit global clues available in the knowledge base, sometimes leading to conflicts among local predictions from different entity pairs. In this paper, we propose a joint inference framework that utilizes these global clues to resolve disagreements among local predictions. W...

Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few seed instances of the target relation type we want to extract but we also have a large amount of labeled instances of other relation types. Observing that different relation types can share certain common structures, we p...

The IDEX system is a prototype of an interactive dynamic Information Extraction (IE) system. A user of the system expresses an information request for a topic description which is used for an initial search in order to retrieve a relevant set of documents. On basis of this set of documents unsupervised relation extraction and clustering is done by the system. The results of these operations can...

One of the core aims of semantic search is to directly present users with information instead of lists of documents. Various entity-oriented tasks have been or are being considered, including entity search and related entity finding. In the context of digital libraries for computational humanities, we consider another task, network extraction: given an input entity and a document collection, ex...

Previous work on relation extraction has focussed on identifying relationships between entities that occur in the same sentence (intra-sentential relations) rather than between entities in different sentences (inter-sentential relations) despite previous research having shown that intersentential relations commonly occur in information extraction corpora. This paper describes a SVM-based approa...

We propose a static relation extraction task to complement biomedical information extraction approaches. We argue that static relations such as part-whole are implicitly involved in many common extraction settings, define a task setting making them explicit, and discuss their integration into previously proposed tasks and extraction methods. We further identify a specific static relation extrac...

While relation extraction has traditionally been viewed as a task relying solely on textual data, recent work has shown that by taking as input existing facts in the form of entity-relation triples from both knowledge bases and textual data, the performance of relation extraction can be improved significantly. Following this new paradigm, we propose a tensor decomposition approach for knowledge...

Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. However, previous models are not effective or ignore to model this property. In this work, to ef...