The Second International Chinese Word Segmentation Bakeoff

By Thomas Emerson. International Joint Conference on Natural Language Processing, 2005

332 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/65e90d9f6754d32db464f635e7fdec672fad9ccf

How researchers see this paper

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

1. Jie Yang
2. Yoav Goldberg
3. Zhao Hai
4. Yue Zhang
5. Fei Dong
6. Fengshun Xiao
7. Chunhui Lu
8. Stephen Clark

Citations in the corpus

• Lattice-Based Transformer Encoder for Neural Machine Translation (2019, methodology): “For Zh-En task, we followed Su et al. (2017) to use the toolkit 2 to train segmenters on PKU, MSR (Emerson, 2005), and CTB corpora (Xue et al., 2005), then we generated word lattices with different segmented training data.”
• Max-Margin Tensor Neural Network for Chinese Word Segmentation (2014, methodology): “It was proposed by Hinton (1986) and has been a research hot spot for more than twenty years (Bengio et al.”
• Syntactic Processing Using the Generalized Perceptron and Beam Search (2011, methodology): “Fourtraining and testing corpora were used in the second bakeoff (Emerson 2005), including the Academia Sinica corpus (AS), the Hong Kong City University Corpus (CU), the Peking University Corpus (PK), and the Microsoft Research Corpus (MR).”
• Neural Word Segmentation with Rich Pretraining (2017, methodology): “The standard word precision, recall and F1 measure (Emerson, 2005) are used to evaluate segmentation performances.”
• Self-attention Based Prosodic Boundary Prediction for Chinese Speech Synthesis (2019, methodology): “Besides, the MSR training set of SIGHAN Bakeoff 2005 [19] which contains more than 80,000 sentences is used as extra corpus for model pretraining in system SA-MTL-P.”
• Multi-task Domain Adaptation for Sequence Tagging (2016, unknown): “This re-sults in four datasets: news CWS data comes from the SIGHAN 2005 shared task ( SighanCWS ) (Emerson, 2005), news NER data comes from the SIGHAN 2006 shared task ( SighanNER ) (Levow, 2006), social CWS data ( WeiboSeg ) created by Zhang et al. (2013), and social NER data ( Wei-boNER )…”
• The Third International Chinese Language Processing Bakeoff: Word Segmentation and Named Entity Recognition (2006, methodology): “We found strong results in both tasks as well as continuing challenges.”