Named Entity Recognition for Astronomy Literature

Proceedings of the 2006 Australasian Language Technology Workshop (ALTW2006), pages 59–66. Named Entity Recognition for Astronomy Literature Tara Murphy and Tara McIntosh and James R. Curran School of Information Technologies University of Sydney NSW 2006, Australia {tm,tara,james}@it.usyd.edu.au Abstract We present a system for named entity recognition (ner) in astronomy jour- nal articles. We have developed this system on a ne corpus comprising ap- proximately 200,000 words of text from astronomy articles. These have been manually annotated with ∼40 entity types of interest to astronomers. We report on the challenges involved in extracting the corpus, defining en- tity classes and annotating scientific text. We investigate which features of an existing state-of-the-art Maximum Entropy approach perform well on as- tronomy text. Our system achieves an F-score of 87.8%. 1 Introduction Named entity recognition (ner) involves as- signing broad semantic categories to entity ref- erences in text. While many of these cate- gories do in fact refer to named entities, e.g. person and location, others are not proper nouns, e.g. date and money. However, they are all syntactically and/or semantically dis- tinct and play a key role in Information Ex- traction (ie). ner is also a key component of Question Answering (qa) systems (Hirschman and Gaizauskas, 2001). State-of-the-art qa systems often have custom-built ner compo- nents with finer-grained categories than exist- ing corpora (Harabagiu et al., 2000). For ie and qa systems, generalising entity references to broad semantic categories allows shallow ex- traction techniques to identify entities of inter- est and the relationships between them. Another recent trend is to move beyond the traditional domain of newspaper text to other corpora. In particular, there is increasing in- terest in extracting information from scientific documents, such as journal articles, especially in biomedicine (Hirschman et al., 2002). A key step in this process is understanding the entities of interest to scientists and build- ing models to identify them in text. Unfor- tunately, existing models of language perform very badly on scientific text even for the cate- gories which map directly between science and newswire, e.g. person. Scientific entities of- ten have more distinctive orthographic struc- ture which is not exploited by existing models. In this work we identify entities within as- tronomical journal articles. The astronomy domain has several advantages: firstly, it is representative of the physical sciences; sec- ondly, the majority of papers are freely avail- able in a format that is relatively easy to ma- nipulate (LATEX); thirdly, there are many in- teresting entity types to consider annotating; finally, there are many databases of astronom- ical objects that we will eventually exploit as gazetteer information. After reviewing comparable named entity corpora, we discuss aspects of astronomy that make it challenging for nlp. We then describe the corpus collection and extraction process, define the named entity categories and present some examples of interesting cases of ambigu- ity that come up in astronomical text. Finally, we describe experiments with re- training an existing Maximum Entropy tag- ger for astronomical named entities. Interest- ingly, some feature …

Content truncated to 500 words