\parinterval 图\ref{fig:3.3-5}展示了一个具体的例子，有一个可见状态序列T F F T，假设初始隐含状态是A，图中线上的概率值是对应的转移概率与发射概率的乘积，比如图中隐含状态A开始，下一个隐含状态是A 且可见状态是F 的概率是0.45，下一个隐含状态是B 且可见状态是F的概率是0.55。图中可以看出，由于有较大的值，当可见状态序列为T F F T时，隐马尔可夫计算出的最有可能的隐含状态序列为A A A A。但是如果对训练集进行统计可能会发现，当可见序列为T F F T 时，对应的隐含状态是A A A A的概率可能是比较大的，但也可能是比较小的。这个例子中出现预测偏差的主要原因是：由于比其他状态转移概率要大得多，隐含状态的预测一直停留在状态A。
\parinterval 图\ref{fig:3.3-5}展示了一个具体的例子，有一个可见状态序列$T F F T$，假设初始隐含状态是$A$，图中线上的概率值是对应的转移概率与发射概率的乘积，比如图中隐含状态$A$开始，下一个隐含状态是$A$且可见状态是$F$的概率是0.45，下一个隐含状态是$B$且可见状态是$F$的概率是0.55。图中可以看出，由于有较大的值，当可见状态序列为$T F F T$时，隐马尔可夫计算出的最有可能的隐含状态序列为$A A A A$。但是如果对训练集进行统计可能会发现，当可见序列为$T F F T$ 时，对应的隐含状态是$A A A A$的概率可能是比较大的，但也可能是比较小的。这个例子中出现预测偏差的主要原因是：由于比其他状态转移概率要大得多，隐含状态的预测一直停留在状态$A$。
title ={On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes},
author ={Ng, Andrew Y and Jordan, Michael I},
pages ={841--848},
year ={2002}
author = {Andrew Y. Ng and
Michael I. Jordan},
title = {On Discriminative vs. Generative Classifiers: {A} comparison of logistic
regression and naive Bayes},
pages = {841--848},
publisher = {{MIT} Press},
year = {2001},
}
@proceedings{huang2008advanced,
title = {Coling 2008: Advanced Dynamic Programming in Computational Linguistics: Theory, Algorithms and Applications - Tutorial notes},
@inproceedings{huang2008coling,
author = {Huang, Liang},
title = {Coling 2008: Advanced Dynamic Programming in Computational Linguistics: Theory, Algorithms and Applications-Tutorial notes},
year = {2008},
address = {Manchester, UK},
publisher = {Coling 2008 Organizing Committee},
publisher = {International Conference on Computational Linguistics},
}
@book{aho1972theory,
author = {Alfred V. Aho and
Jeffrey D. Ullman},
title = {The theory of parsing, translation, and compiling. 2: Compiling},
publisher = {Prentice-Hall},
author = {Aho, Alfred V and
Ullman, Jeffrey D},
title = {The theory of parsing, translation, and compiling},
publisher = {Prentice-Hall Englewood Cliffs, NJ},
year = {1973},
}
...
...
@@ -874,7 +877,7 @@
author={Rau, Lisa F},
pages={29--30},
year={1991},
organization={IEEE Computer Society}
publisher={IEEE Conference on Artificial Intelligence Application},
}
@article{张小衡1997中文机构名称的识别与分析,
...
...
@@ -887,11 +890,16 @@
year={1997},
}
@article{lample2016neural,
title={Neural architectures for named entity recognition},
author={Lample, Guillaume and Ballesteros, Miguel and Subramanian, Sandeep and Kawakami, Kazuya and Dyer, Chris},
journal={arXiv preprint arXiv:1603.01360},
year={2016}
@inproceedings{lample2016neural,
author = {Guillaume Lample and
Miguel Ballesteros and
Sandeep Subramanian and
Kazuya Kawakami and
Chris Dyer},
title = {Neural Architectures for Named Entity Recognition},
pages = {260--270},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@article{Baum1966Statistical,
...
...
@@ -912,7 +920,6 @@
number={1},
pages={164--171},
year={1970},
publisher={JSTOR}
}
@article{1977Maximum,
...
...
@@ -926,19 +933,13 @@
@article{1967Error,
title={Error bounds for convolutional codes and an asymptotically optimum decoding algorithm},
author={ Viterbi, Andrew J. },
journal={IEEE Trans.informat.theory},
journal={IEEE Transactions on Information Theory},
volume={13},
number={2},
pages={260-269},
year={1967},
}
@article{lafferty2001conditional,
title={Conditional random fields: Probabilistic models for segmenting and labeling sequence data},
author={Lafferty, John and McCallum, Andrew and Pereira, Fernando CN},
year={2001}
}
@article{harrington2013机器学习实战,
title={机器学习实战},
author={Harrington, Peter},
...
...
@@ -951,41 +952,36 @@
author = {Brants, Thorsten},
month = apr,
year = {2000},
address = {Seattle, Washington, USA},
publisher = {Association for Computational Linguistics},
doi = {10.3115/974147.974178},
pages = {224--231},
}
@inproceedings{tsuruoka-tsujii-2005-chunk,
title = {Chunk Parsing Revisited},
author = {Tsuruoka, Yoshimasa and
Tsujii, Jun{'}ichi},
author = {Yoshimasa Tsuruoka and
Jun'ichi Tsujii},
month = oct,
year = {2005},
address = {Vancouver, British Columbia},
publisher = {Association for Computational Linguistics},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {133--140},
}
@inproceedings{li-etal-2003-news-oriented,
title = {News-Oriented Automatic {C}hinese Keyword Indexing},
title = {News-Oriented Automatic Chinese Keyword Indexing},
author = {Li, Sujian and
Wang, Houfeng and
Yu, Shiwen and
Xin, Chengsheng},
month = jul,
year = {2003},
address = {Sapporo, Japan},
publisher = {Association for Computational Linguistics},
doi = {10.3115/1119250.1119263},
publisher = {Annual Meeting of the Association for Computational Linguistics},
pages = {92--97},
}
@article{2015Bidirectional,
title={Bidirectional LSTM-CRF Models for Sequence Tagging},
author={ Huang, Zhiheng and Xu, Wei and Yu, Kai },
journal={Computer ence},
journal={CoRR},
year={2015},
}
...
...
@@ -1000,10 +996,13 @@
}
@inproceedings{vzukov2018named,
title={Named entity recognition with parallel recurrent neural networks},
author={{\v{Z}}ukov-Gregori{\v{c}}, Andrej and Bachrach, Yoram and Coope, Sam},
pages={69--74},
year={2018}
author = {Andrej Zukov Gregoric and
Yoram Bachrach and
Sam Coope},
title = {Named Entity Recognition With Parallel Recurrent Neural Networks},
pages = {69--74},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2018},
}
@article{Li2020A,
...
...
@@ -1016,29 +1015,196 @@
year={2020},
}
@article{devlin2018bert,
@article{devlin2019bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
journal={arXiv preprint arXiv:1810.04805},
year={2018}
}
@article{conneau2019unsupervised,
title={Unsupervised cross-lingual representation learning at scale},
author={Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin},
journal={arXiv preprint arXiv:1911.02116},
year={2019}
year={2019},
pages = {4171--4186},
journal = {Annual Meeting of the Association for Computational Linguistics},
}
@inproceedings{conneau2019unsupervised,
author = {Alexis Conneau and
Kartikay Khandelwal and
Naman Goyal and
Vishrav Chaudhary and
Guillaume Wenzek and
Francisco Guzm{\'{a}}n and
Edouard Grave and
Myle Ott and
Luke Zettlemoyer and
Veselin Stoyanov},
title = {Unsupervised Cross-lingual Representation Learning at Scale},
pages = {8440--8451},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2020},
}
@book{chomsky1993lectures,
title={Lectures on government and binding: The Pisa lectures},
author={Chomsky, Noam},
number={9},
year={1993},
publisher={Walter de Gruyter}
}
@inproceedings{DBLP:conf/acl/SennrichHB16a,
author = {Rico Sennrich and
Barry Haddow and
Alexandra Birch},
title = {Neural Machine Translation of Rare Words with Subword Units},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2016},
}
@article{刘挺1998最大概率分词问题及其解法,
title={最大概率分词问题及其解法},
author={刘挺 and 吴岩 and 王开铸},
journal={哈尔滨工业大学学报},
number={06},
pages={37-41},
year={1998},
}
@article{丁洁2010基于最大概率分词算法的中文分词方法研究,
title={基于最大概率分词算法的中文分词方法研究},
author={丁洁},
journal={科技信息},
number={21},
pages={I0075--I0075},
year={2010}
}
@book{1995University,
title = {University of Sheffield: Description of the LaSIE-II system as used for MUC-7},
author = {Kevin Humphreys and
Robert J. Gaizauskas and
Saliha Azzam and
Charles Huyck and
Brian Mitchell and
Hamish Cunningham and
Yorick Wilks},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1995},
}
@inproceedings{krupka1998isoquest,
title={IsoQuest Inc.: Description of the NetOwl™ Extractor System as Used for MUC-7},
author={Krupka, George and Hausman, Kevin},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year={1998}
}
@inproceedings{DBLP:conf/muc/BlackRM98,
author = {William J. Black and
Fabio Rinaldi and
David Mowatt},
title = {{FACILE:} Description of the {NE} System Used for {MUC-7}},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {1998},
}
@article{1996Hidden,
title={Hidden Markov models.},
author={ Eddy, Sean R },
journal={Current Opinion in Structural Biology},
volume={6},
number={3},
pages={361-5},
year={1996},
}
@inproceedings{lafferty2001conditional,
author = {John D. Lafferty and
Andrew McCallum and
Fernando C. N. Pereira},
title = {Conditional Random Fields: Probabilistic Models for Segmenting and
Labeling Sequence Data},
pages = {282--289},
publisher = {proceedings of the Eighteenth International Conference on Machine
Learning},
year = {2001},
}
@book{kapur1989maximum,
title={Maximum-entropy models in science and engineering},
author={Kapur, Jagat Narain},
year={1989},
publisher={John Wiley \& Sons}
}
@article{1998Support,
title={Support vector machines},
author={Hearst, Marti A. and Dumais, Susan T and Osuna, Edgar and Platt, John and Scholkopf, Bernhard},
journal={IEEE Intelligent Systems \& Their Applications},
volume={13},
number={4},
pages={18-28},
year={1998},
}
@article{2011Natural,
title={Natural Language Processing (almost) from Scratch},
author={ Collobert, Ronan and Weston, Jason and Bottou, Léon and Karlen, Michael and Kavukcuoglu, Koray and Kuksa, Pavel },
journal={Journal of Machine Learning Research},
volume={12},
number={1},
pages={2493-2537},
year={2011},
}
@book{manning2008introduction,
title={Introduction to information retrieval},
author={Manning, Christopher D and Sch{\"u}tze, Hinrich and Raghavan, Prabhakar},
year={2008},
publisher={Cambridge university press}
}
@article{berger1996maximum,
title={A maximum entropy approach to natural language processing},
author={Berger, Adam and Della Pietra, Stephen A and Della Pietra, Vincent J},
journal={Computational linguistics},
volume={22},
number={1},
pages={39--71},
year={1996}
}
@article{mitchell1996m,
title={Machine Learning},
author={Mitchell, Tom},
journal={McCraw Hill},
year={1996}
}
@inproceedings{DBLP:conf/acl/OchN02,
author = {Franz Josef Och and
Hermann Ney},
title = {Discriminative Training and Maximum Entropy Models for Statistical
Machine Translation},
pages = {295--302},
publisher = {Annual Meeting of the Association for Computational Linguistics},
year = {2002},
}
@incollection{mohri2008speech,
title={Speech recognition with weighted finite-state transducers},
author={Mohri, Mehryar and Pereira, Fernando and Riley, Michael},
pages={559--584},
year={2008},
publisher={Springer}
}
@article{bellman1966dynamic,
title={Dynamic programming},
author={Bellman, Richard},
journal={Science},
volume={153},
number={3731},
pages={34--37},
year={1966},
publisher={American Association for the Advancement of Science}
