Our goal in this paper is to investigate the effectiveness of relation extraction techniques for the slot-filling task. We discuss two relation extraction systems. YRES follows the traditional paradigm in relation extraction, where a system takes advantage of available examples for each relation to be extracted. On the other hand, SONEX follows the open relation extraction paradigm, where the r...

Sentence simplification for relation extraction Machine learning based relation extraction requires large annotated corpora to take into account the variability in the expression of relations. To deal with this problem, we propose a method for simplifying sentences, i.e. for reducing the syntactic variability of the relations. Simplification requires the annotation of a small corpus, which will...

We propose a framework to improve the performance of distantly-supervised relation extraction, by jointly learning to solve two related tasks: concept-instance extraction and relation extraction. We further extend this framework to make a novel use of document structure: in some small, wellstructured corpora, sections can be identified that correspond to relation arguments, and distantly-labele...

Relation extraction suffers from a performance loss when a model is applied to out-of-domain data. This has fostered the development of domain adaptation techniques for relation extraction. This paper evaluates word embeddings and clustering on adapting feature-based relation extraction systems. We systematically explore various ways to apply word embeddings and show the best adaptation improve...

To overcome the problem of not having enough manually labeled relation instances for supervised relation extraction methods, in this paper we propose a label propagation (LP) based semi-supervised learning algorithm for relation extraction task to learn from both labeled and unlabeled data. Evaluation on the ACE corpus showed when only a few labeled examples are available, our LP based relation...

OBJECTIVE To create an end-to-end system to identify temporal relation in discharge summaries for the 2012 i2b2 challenge. The challenge includes event extraction, timex extraction, and temporal relation identification. DESIGN An end-to-end temporal relation system was developed. It includes three subsystems: an event extraction system (conditional random fields (CRF) name entity extraction a...

This paper describes our submission for the ScienceIE shared task (SemEval2017 Task 10) on entity and relation extraction from scientific papers. Our model is based on the end-to-end relation extraction model of Miwa and Bansal (2016) with several enhancements such as semi-supervised learning via neural language models, character-level encoding, gazetteers extracted from existing knowledge base...

Relation extraction is a challenging task in natural language processing. Syntactic features are recently shown to be quite effective for relation extraction. In this paper, we generalize the state of the art syntactic convolution tree kernel introduced by Collins and Duffy. The proposed generalized kernel is more flexible and customizable, and can be conveniently utilized for systematic genera...

Semantic relation extraction between entities plays key role in many applications in natural language processing and understanding, information retrieval, text summarizing, etc. These application require an understanding of the semantic relations between entities. We present a comprehensive review of various aspects of the entity relation extraction task. We also present a review of relation ex...