Voting Between Multiple Data Representations for Text Chunking

77 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Natural Language Processing (Almost) from Scratch (2011, methodology): “System Accuracy Shen et al. (2007) 97.”
Deep multi-task learning with low level tasks supervised at lower layers (2016, background): “Previous work in NLP on cascaded learning such as Shen and Sarkar (2005) suggests there is some-times a natural order among the different tasks: some tasks may beneﬁt more from other tasks, than the other way around.”
Bidirectional LSTM-CRF Models for Sequence Tagging (2015, methodology): “More recent is (Shen and Sarkar, 2005) which obtained 95.23% accuracy with a voting classiﬁer scheme, where each classiﬁer is trained on different tag representations ( IOB , IOE , etc.).”
Design Challenges and Misconceptions in Named Entity Recognition (2009, background): “Related works include voting between several representation schemes (Shen and Sarkar, 2005), lex-icalizing the schemes (Molina and Pla, 2002) and automatically searching for best encoding (Edward, 2007).”
Multi-Task Cross-Lingual Sequence Tagging from Scratch (2016, background): “Currently, however, the best results on speciﬁc sequence-tagging tasks are usually achieved by approaches that target only one speciﬁc task, either POS tagging (Søgaard, 2011; Toutanova et al., 2003), chunking (Shen and Sarkar, 2005), or NER (Luo et al., 2015; Pas-sos et al., 2014).”