In this paper we try to improve Information Extraction in legal texts by creating a legal Named Entity Recognizer, Classifier and Linker. With this tool, we can identify relevant parts of texts and connect them to a structured knowledge representation, the LKIF ontology. More interestingly, this tool has been developed with relatively little effort, by mapping the LKIF ontology to the YAGO ontology and through it, taking advantage of the mentions of entities in the Wikipedia. These mentions are used as manually annotated examples to train the Named Entity Recognizer, Classifier and Linker. We have evaluated the approach on holdout texts from the Wikipedia and also on a small sample of judgments of the European Court of Human Rights, resulting in a very good performance, i.e., around 80% F-measure for different levels of granularity. We present an extensive error analysis to direct further developments, and we expect that this approach can be successfully ported to other legal subdomains, represented by different ontologies.

No abstract

In this paper, we present a Wikipediabased approach to develop resources for the legal domain. We establish a mapping between a legal domain ontology, LKIF (Hoekstra et al., 2007), and a Wikipediabased ontology, YAGO (Suchanek et al., 2007), and through that we populate LKIF. Moreover, we use the mentions of those entities in Wikipedia text to train a specific Named Entity Recognizer and Classifier. We find that this classifier works well in the Wikipedia, but, as could be expected, performance decreases in a corpus of judgments of the European Court of Human Rights. However, this tool will be used as a preprocess for human annotation.We resort to a technique called curriculum learning aimed to overcome problems of overfitting by learning increasingly more complex concepts. However, we find that in this particular setting, the method works best by learning from most specific to most general concepts, not the other way round.

This work explores the use of word embeddings as features for Spanish verb sense disambiguation (VSD). This type of learning technique is nameddisjoint semisupervised learning: an unsupervised algorithm (i.e. the word embeddings) is trained on unlabeled data separately as a first step, and then its results are used by a supervised classifier. In this work we primarily focus on two aspects of VSD trained with unsupervised word representations. First, we show how the domain where the word embeddings are trained affects the performance of the supervised task. A specific domain can improve the results if this domain is shared with the domain of the supervised task, even if the word embeddings are trained with smaller corpora. Second, we show that the use of word embeddings can help the model generalize when compared to not using word embeddings. This means embeddings help by decreasing the model tendency to overfit.

No abstract