Abstract | ||
---|---|---|
We present an approach for extracting relations between named entities from natural language documents. The approach is based solely on shallow linguistic processing, such as tokenization, sentence splitting, part-of-speech tagging, and lemmatization. It uses a combination of kernel functions to integrate two different information sources: (i) the whole sentence where the relation appears, and (ii) the local contexts around the interacting entities. We present the results of experiments on extracting five different types of relations from a dataset of newswire documents and show that each information source provides a useful contribution to the recognition task. Usually the combined kernel significantly increases the precision with respect to the basic kernels, sometimes at the cost of a slightly lower recall. Moreover, we performed a set of experiments to assess the influence of the accuracy of named-entity recognition on the performance of the relation-extraction algorithm. Such experiments were performed using both the correct named entities (i.e., those manually annotated in the corpus) and the noisy named entities (i.e., those produced by a machine learning-based named-entity recognizer). The results show that our approach significantly improves the previous results obtained on the same dataset. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1145/1322391.1322393 | TSLP |
Keywords | Field | DocType |
sentence splitting,information source,basic kernel,named-entity recognition,kernel methods,named-entity recognizer,combined kernel,kernel function,different type,different information source,relation extraction,automatic named-entity recognition,recognition task,information extraction,kernel method,natural language,machine learning | Tokenization (data security),Pattern recognition,Deep linguistic processing,Computer science,Tree kernel,Information extraction,Artificial intelligence,Natural language processing,Kernel method,Named-entity recognition,Sentence,Relationship extraction | Journal |
Volume | Issue | ISSN |
5 | 1 | 1550-4875 |
Citations | PageRank | References |
10 | 0.58 | 24 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Claudio Giuliano | 1 | 488 | 33.00 |
Alberto Lavelli | 2 | 615 | 55.37 |
Lorenza Romano | 3 | 406 | 22.15 |