Entailment recognition is a primary generic task in natural language inference, whose focus is to detect whether the meaning of one expression can be inferred from the meaning of the other. Accordingly, many NLP applications would benefit from high coverage knowledgebases of paraphrases and entailment rules. To this end, learning such knowledgebases from the Web is especially appealing due to its huge size as well as its highly heterogeneous content, allowing for a more scalable rule extraction of various domains. However, the scalability of state-of-the-art entailment rule acquisition approaches from the Web is still limited. We present a fully unsupervised learning algorithm for Webbased extraction of entailment relations. We focus on increased scalability and generality with respect to prior work, with the potential of a large-scale Web-based knowledgebase. Our algorithm takes as its input a lexical-syntactic template and searches the Web for syntactic templates that participate in an entailment relation with the input template. Experiments show promising results, achieving performance similar to a state-of-the-art unsupervised algorithm, operating over an offline corpus, but with the benefit of learning rules for different domains with no additional effort. Input templateLearned templates

No abstract

No abstract

This paper discusses in detail the design and implementation phases during the creation of the Bulgarian HPSG-based treebank (BulTreeBank). First, the interconnection of the HPSG language model, the linguistic parameters of the annotation scheme and the underlying formalism is considered. Then, the architecture of their implementation is described with respect to the interface compatibility between two software tools: the CLaRK System and the TRALE System. Also some innovative strategies are introduced concerning two problems: the HPSG grammar application to a less-processed language like Bulgarian and the controlling mechanisms over the manual annotation work.