MulTiSEX - A Multi-language Timex Sequential Extractor

In this paper we present a light-weighted Machine Learning based approach to the recognition and semantic classification of temporal expressions in different languages. We applied the proposed approach to English, Italian and Spanish with limited porting efforts. The experimental results show that our system produces state-of-the-art performance on all the corpora used and in some cases outperforms available systems.

Authors

• Stefan Rigo
• Alberto Lavelli

Keywords

• Semantics
• Accuracy
• Pattern matching
• Context
• Computer architecture
• Training
• Tagging
• Temporal Expression
• Limited Efforts
• Brackets
• Temporal Information
• 10-fold Cross-validation
• Question Answering
• Exact Match
• Postage
• Feature Engineering
• Adverbs
• Lexical Items
• Conditional Random Field
• Named Entity Recognition
• Italian Data
• Spanish Data
• Reference Benchmark
• Lexical Database
• Natural Language Processing
• Temporal Processing
• Temporal Expressions
• Machine Learning