Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Structured Named Entity Retrieval in Audio Broadcast News
CBMI '09 Proceedings of the 2009 Seventh International Workshop on Content-Based Multimedia Indexing
Hi-index | 0.00 |
In this paper we propose an efficient approach to perform named entities retrieval (NER) using their hierarchical structure in transcribed speech documents. The NER task consists of identifying and classifying every word in a document into some predefined categories such as person name, locations, organizations, and dates. Usually the classical NER systems use generative approaches to learn models considering only the words characteristics (word context). In this work we show that NER is also sensitive to syntactic and semantic contexts. For this reason, we introduce an extension of conditional random fields (CRFs) approach to consider multiple contexts. We present an adaptation of the text-approach to the automatic speech recognition (ASR) outputs. Experimental results show that the proposed approach outperformed a CRFs simple application. Our experiments are done using ESTER 2 campaign data. The proposed approach is ranked in 4th position in ESTER 2 participating sites, it achieves a significant relative improvement of 18% in slot rate error (SER) measure over HMMs method.