Using Local Alignments for Relation Recognition
This addresses the problem of improving relation extraction accuracy for information extraction tasks, particularly in biomedical domains, but is incremental as it builds on existing kernel methods.
The paper tackles relation recognition in text by integrating structural similarity with semantic relatedness using local alignment kernels, achieving promising results that outperform baselines on biomedical corpora and match state-of-the-art on general datasets.
This paper discusses the problem of marrying structural similarity with semantic relatedness for Information Extraction from text. Aiming at accurate recognition of relations, we introduce local alignment kernels and explore various possibilities of using them for this task. We give a definition of a local alignment (LA) kernel based on the Smith-Waterman score as a sequence similarity measure and proceed with a range of possibilities for computing similarity between elements of sequences. We show how distributional similarity measures obtained from unlabeled data can be incorporated into the learning task as semantic knowledge. Our experiments suggest that the LA kernel yields promising results on various biomedical corpora outperforming two baselines by a large margin. Additional series of experiments have been conducted on the data sets of seven general relation types, where the performance of the LA kernel is comparable to the current state-of-the-art results.