GlossExtractor System

A GlossExtractor System is an Automatic Glossary Generation System that is based on a definitional sentence classification system.

• Context:
  • It was first developed by Navigli & Velardi (2007).
  • …
• Example(s):
  • GlossExtractor DE System.
  • …
• Counter-Example(s):
  • TermExtractor System,
  • OntoLearn System.
• See: Definitional Sentence Generation System, Automated Definitional Sentence Extraction Task, Bootstrapping Algorithm, Terminology Extraction System, Taxonomy Learning System, Question-Answering System, Semantic Search System.

---

---

References

2007a

• (Navigli & Velardi, 2007) ⇒ Roberto Navigli, and Paola Velardi. (2007). “GlossExtractor: A Web Application to Automatically Create a Domain Glossary.” In: Proceedings of the 10th Congress of the Italian Association for Artificial Intelligence (AI*IA 2007). doi:10.1007/978-3-540-74782-6_30
  • QUOTE: We describe a web application, GlossExtractor, that receives in input the output of a terminology extraction web application, TermExtractor, or a user-provided terminology, and then searches several repositories (on-line glossaries, web documents, user-specified web pages) for sentences that are candidate definitions for each of the input terms. Candidate definitions are then filtered using statistical indicators and machine-learned regular patterns. Finally, the user can inspect the acquired definitions and perform an individual or group validation. The validated glossary is then downloaded in one of several formats.

2007b

• (Navigli & Velardi, 2007) ⇒ Roberto Navigli, and Paola Velardi (2007, September). "GlossExtractor: A Web Application to Automatically Create a Domain Glossary". In: Congress of the Italian Association for Artificial Intelligence (pp. 339-349). Springer, Berlin, Heidelberg.
  • QUOTE: Figure 1 shows the basic steps of the glossary extraction algorithm. The input to the system a list $T$ of terms, for which a glossary has to be learned. Possibly, this list is the result of a previous terminology extraction process.

    The first phase is candidate extraction: for each term, definition sentences are searched first, in on-line glossaries, then, in on-line documents. Simple, manually defined regular expressions are used to extract the candidate definition sentences.

Figure 1: The glossary extraction algorithm.

---