Open Information Extraction (IE) is the task of extracting assertions from massive corpora without requiring a pre-specified vocabulary. This paper shows that the output of state-ofthe-art Open IE systems is rife with uninformative and incoherent extractions. To overcome these problems, we introduce two simple syntactic and lexical constraints on binary relations expressed by verbs. We implemen...

Several problems exist with traditional HMM based approaches for Web information extraction (IE) due to the lack of consideration on Web-specific features. To address this issue we present a Generalized Hidden Markov Model (GHMM) that extends HMMs by making use of Web-specific information for Web IE. In GHMM based approach, Web content blocks instead of terms are used as basic extraction unit. ...

Named entities create serious problems for state-of-the-art commercial machine translation (MT) systems and often cause translation failures beyond the local context, affecting both the overall morphosyntactic well-formedness of sentences and word sense disambiguation in the source text. We report on the results of an experiment in which MT input was processed using output from the named entity...

We describe here some of the research underlying the development of KANI (Knowledge Associates for Novel Intelligence), a hybrid system that combines large scale information extraction (IE) with knowledge representation (KR). The combination of these two technologies raises numerous research problems, such as an evaluation and understanding of the requirements that KR puts on IE and vice-versa,...

Information extraction (IE) is the process of automatically extracting structured pieces of information from unstructured or semi-structured text documents. Classical problems in information extraction include named-entity recognition (identifying mentions of persons, places, organizations, etc.) and relationship extraction (identifying mentions of relationships between such named entities). We...

Problems and requirements regarding integration of methods and tools across phases of the software-development life cycle are discussed. Information engineering (IE) methodology and I-CASE (integrated CASE) tools supporting IE claim to have an integrated view across major stages of enterprise-wide information-system development: information strategy planning, business area analysis, system desi...

With the extensive amount of textual data flowing through social media platforms, the interest in Information Extraction (IE) on such textual data has increased. Named Entity Recognition (NER) is one of the basic problems of IE. State-of-the-art solutions for NER face an adaptation problem to informal texts from social media platforms. In this study, we addressed this generalization problem wit...