Background | classifier is trained first to distinguish between relation instances and non-relation instances. |
Cluster Feature Selection | Table 4 simplifies a relation instance as a three tuple <Context, M], M2> where the Context includes the Before, Between and After from the |
Experiments | previous research, we used in experiments the nwire (newswire) and bnews (broadcast news) genres of the data containing 348 documents and 4374 relation instances . |
Experiments | The non-relation instances generated were about 8 times more than the relation instances . |
Experiments | The unbalanced distribution of relation instances and non-relation instances remains as an obstacle for pushing the performance of relation extraction to the next level. |
Feature Based Relation Extraction | At the lexical level, a relation instance can be seen as a sequence of tokens which form a five tuple <Before, M], Between, M2, After>. |
Feature Based Relation Extraction | Specifically, we first train a binary classifier to distinguish between relation instances and non-relation instances. |
Feature Based Relation Extraction | Then rather than using the thresholded output of this binary classifier as training data, we use only the annotated relation instances to train a multi-class classifier for the 7 relation types. |
Introduction | In contrast, the kernel based method does not explicitly extract features; it designs kernel functions over the structured sentence representations (sequence, dependency or parse tree) to capture the similarities between different relation instances (Zelenko et al., 2003; Bunescu and Mooney, 2005a; Bunescu and Mooney, 2005b; Zhao and Grishman, 2005; Zhang et al., 2006; Zhou et al., 2007; Qian et al., 2008). |
Introduction | The assumption is that even if the word soldier may never have been seen in the annotated Employment relation instances , other words which share the same cluster membership with soldier such as president and ambassador may have been observed in the Employment instances. |
Declarative Constraints | diversity in the discovered relation types by restricting the number of times a single word can serve as either an indicator or part of the argument of a relation instance . |
Introduction | First, the model’s generative process encourages coherence in the local features and placement of relation instances . |
Results | To incorporate training examples in our model, we simply treat annotated relation instances as observed variables. |
Results | For finance, it takes at least 10 annotated documents (corresponding to roughly 130 annotated relation instances ) for the CRF to match the semi-supervised model’s performance. |
Results | For earthquake, using even 10 annotated documents (about 71 relation instances ) is not sufficient to match our model’s performance. |
Background: Never-Ending Language Learner | As in other information extraction systems, the category and relation instances extracted by NELL contain polysemous and synonymous noun phrases. |
Discussion | Both extracting more relation instances and adding new relations to the ontology will improve synonym res- |
Introduction | The main input to ConceptResolver is a set of extracted category and relation instances over noun phrases, like person(:c1) and ceoOf(:c1, :52), produced by running NELL. |