Abstract 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 Web-based 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.

We describe a system for real-time detection of security and crisis events from online news in three Balkan languages: Turkish, Romanian and Bulgarian.The system classifies the events according to a finegrained event type set.It extracts structured information from news reports, by using a blend of keyword matching and finite-state grammars for entity recognition.We apply a multilingual methodology for the development of the system's language resources, based on adaptation of language-independent grammars and on weakly-supervised learning of lexical resources.Detailed performance evaluation proves that the approach is effective in developing real-world semantic processing applications for relatively less-resourced languages.

This paper describes ongoing work to construct a knowledge base of politically motivated violent events (PMVE) consisting of a domain ontology and of instance data accessible via a browser and visualization interface. The instance data is semi-automatically extracted from news articles gathered by the online news monitoring system of the European Commission (EMM). There are important interrelations in seemingly unrelated violent events recorded in online news articles scattered through the Web. This information can essentially be re-discovered by gathering and mapping it to a well defined, logical model. This knowledgebase can then deploy an inference mechanism resulting in the discovery of hidden relationships and facts.

Answer Validation is an emerging topic in Question Answering, where open domain systems are often required to rank huge amounts of candidate answers. We present a novel approach to answer validation based on the intuition that the amount of implicit knowledge which connects an answer to a question can be quantitatively estimated by exploiting the redundancy of Web information. Experiments carried out on the TREC-2001 judged-answer collection show that the approach achieves a high level of performance (i.e. 81% success rate). The simplicity and the efficiency of this approach make it suitable to be used as a module in Question Answering systems.