GATE 2 - IGR Review Report

This report reviews the last three years of work on GATE, a General Architecture for Text Engineering, under EPSRC grant GM/M31699. GATE is an infrastructure for support of human language computation work, based on an extendable component model and delivered with a range of free components for common language processing tasks. This project has extended and redeveloped the successful version 1 of GATE, which was used in many R&D projects, PhDs and MScs, for teaching and for a number of commercial applications [Maynard et al. 00].

[1]  Kalina Bontcheva,et al.  Architectural elements of language engineering robustness , 2002, Natural Language Engineering.

[2]  Fredrik Olsson,et al.  Experiences of Language Engineering Algorithm Reuse , 2000, LREC.

[3]  Tony McEnery,et al.  EMILLE, A 67-Million Word Corpus of Indic Languages: Data Collection, Mark-up and Harmonisation , 2002, LREC.

[4]  Kalina Bontcheva,et al.  Using a text engineering framework to build an extendable and portable IE-based summarisation system , 2002, ACL 2002.

[5]  Kalina Bontcheva,et al.  A Unicode-based Environment for Creation and Use of Language Resources , 2002, LREC.

[6]  Kalina Bontcheva,et al.  Adapting a Robust Multi-genre NE System for Automatic Content Extraction , 2002, AIMSA.

[7]  Yorick Wilks,et al.  Software Infrastructure for Natural Language Processing , 1997, ANLP.

[8]  Yorick Wilks,et al.  GATE: an environment to support research and development in natural language engineering , 1996, Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence.

[9]  Y. Wilks,et al.  A General Architecture for Text Engineering (gate) { a New Approach to Language Engineering R&d a General Architecture for Text Engineering (gate) | a New Approach to Language Engineering R&d a E G T , 1995 .

[10]  Kalina Bontcheva,et al.  Access to Multimedia Information through Multisource and Multilanguage Information Extraction , 2002, NLDB.

[11]  Kalina Bontcheva,et al.  Shallow Methods for Named Entity Coreference Resolution , 2002 .

[12]  Kalina Bontcheva,et al.  A Survey of Uses of GATE , 2000 .

[13]  Yorick Wilks,et al.  Experience with a Language Engineering Architecture: Three Years of GATE , 1999 .

[14]  Yorick Wilks,et al.  How feasible is the reuse of grammars for Named Entity Recognition? , 2002, LREC.

[15]  Kalina Bontcheva,et al.  A Light-weight Approach to Coreference Resolution for Named Entities in Text , 2002 .

[16]  Kalina Bontcheva,et al.  Extracting Information for Automatic Indexing of Multimedia Material , 2002, LREC.

[17]  Kalina Bontcheva,et al.  Developing reusable and robust language processing components for information systems using GATE , 2002, Proceedings. 13th International Workshop on Database and Expert Systems Applications.

[18]  Yorick Wilks,et al.  Uniform language resource access and distribution , 1998 .

[19]  Yorick Wilks,et al.  Sense Tagging and Language Engineering , 1998, ECAI.

[20]  Hamish Cunningham,et al.  GATE-a General Architecture for Text Engineering , 1996, COLING.

[21]  Kalina Bontcheva,et al.  Using GATE as an Environment for Teaching NLP , 2002, ACL 2002.

[22]  Kalina Bontcheva,et al.  Experience using GATE for NLP R&D , 2000, COLING 2000.

[23]  Yorick Wilks,et al.  Named Entity Recognition from Diverse Text Types , 2001 .

[24]  Yorick Wilks,et al.  Information Extraction: Beyond Document Retrieval , 1998, Int. J. Comput. Linguistics Chin. Lang. Process..

[25]  Yorick Wilks,et al.  New Methods, Current Trends and Software Infrastructure for NLP , 1996, ArXiv.

[26]  Kalina Bontcheva,et al.  Software Infrastructure for Language Resources: a Taxonomy of Previous Work and a Requirements Analysis , 2000, LREC.

[27]  Hamish Cunningham,et al.  A definition and short history of Language Engineering , 1999, Natural Language Engineering.

[28]  Diana Maynard,et al.  JAPE: a Java Annotation Patterns Engine , 2000 .