OPEN INFORMATION EXTRACTION FROM THE WEB

Proceedings of EACL '99 The GENIA project: corpus-based knowledge acquisition and information extraction from genome research papers Nigel Collier, Hyun Seok Park, Norihiro Ogata Yuka Tateishi, Chikashi Nobata, Tomoko Ohta Tateshi Sekimizu, Hisao Imai, Katsutoshi Ibushi,[r]

tance, as a result of an increase in the number ofpublicly available archives and a realization of thecommercial value of the available data. One as-pect of information extraction (IE) is the retrievalof documents. Another aspect is that of identify-ing words fr[r]

of bond-issue (Ciravegna et el., 1999). The eval- uation will consider both quality and quantity of terms and development time of the whole lexicon. One of the issues that we are currently investi- gating is that of choosing the correct set of field labels from DDC[r]

The mapper requires comparable corpora aligned in the document level as input. NERA2 compares each NE from the source language to each NE from the target language using cognate based methods. It also uses a GIZA++ format statistical dictionary to map NEs con[r]

ful to capture verb arguments, which may be con-nected by long-distance dependency paths. How-ever, current semantic parsers such as the ASSERT are not able to recognize support verb construc-tions such as “X conducted an attack on Y” under the verb frame “attack” (Pradhan et al. 2004)[r]

in comparison to handcrafted resources or man-ual examination of the leading search engine re-sults. Hence a promising direction would be touse our approach in combination with Wikipediadata and with additional manually created attributerich sources such as Web tables, to achieve th[r]

its synonym is present. Matching the article sub-ject, however, is more involved.Matching Primary Entities: In order to matchshorthand terms like “MIT” with more completenames, the matcher uses an ordered set of heuris-tics like those of (Wu and Weld, 2007; Nguyen etal., 2007):• Full m[r]

quired knowledge bases and from web services.In this paper we describe the current status ofthe SmartWeb Ontology-Based Annotation(SOBA) system. SOBA automatically populatesa knowledge base by information extraction fromsoccer match reports as available on the