论文信息 - Relational Learning Assisted Construction of Rule Base for Indian Language NER

Relational Learning Assisted Construction of Rule Base for Indian Language NER

We present Inductive Logic Programming (ILP) based techniques for automatically extracting rules for Named Entity Recognition (NER) from tagged corpora and background knowledge. Results using WARMR (Luc Dehaspe and Luc De Raedt 1997) and TILDE (Hendrik Blockeel and Luc De Raedt 1998) to learn rules for named entities of Hindi 1 and Marathi 2 show that the ILP approach has two advantages over hand-crafting the NER rules: (i) the development time reduces by a factor of 120 compared to a linguist doing the entire rule development, and (ii) a complete and consistent view of all significant patterns in the data at the level of abstraction specified through the mode declarations prevails in the learned rules.

[1] Ganesh Ramakrishnan,et al. Learning Decision Lists with Known Rules for Text Mining , 2008, IJCNLP.

[2] James S. Aitken. Learning Information Extraction Rules: An Inductive Logic Programming approach , 2002, ECAI.

[3] Luc De Raedt,et al. Mining Association Rules in Multiple Relations , 1997, ILP.

[4] Stephen Muggleton,et al. Inductive Logic Programming , 2011, Lecture Notes in Computer Science.

[5] Stephen Soderland,et al. Learning Information Extraction Rules for Semi-Structured and Free Text , 1999, Machine Learning.

[6] Douglas E. Appelt,et al. FASTUS: A Finite-state Processor for Information Extraction from Real-world Text , 1993, IJCAI.

[7] Ralph Grishman,et al. Message Understanding Conference- 6: A Brief History , 1996, COLING.

[8] Kalina Bontcheva,et al. GATE: an Architecture for Development of Robust HLT applications , 2002, ACL.

[9] Dan Roth,et al. Relational Learning via Propositional Algorithms: An Information Extraction Case Study , 2001, IJCAI.

[10] Raymond J. Mooney,et al. Relational Learning of Pattern-Match Rules for Information Extraction , 1999, CoNLL.

[11] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[12] Luc De Raedt,et al. Top-down induction of logical decision trees , 1997 .