Shallow parsing with conditional random fields
Open accessAbstract
Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the development of standard evaluation datasets and extensive comparison among methods. We show here how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model. Improved training methods based on modern optimization algorithms were critical in achieving these results. We present extensive comparisons between models and training methods that confirm and strengthen previous results on shallow parsing and training methods for maximum-entropy models.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Hierarchical models can model a state using a number of substates in which the duration of the state is a convolution of geometric distributions.
“Hierarchical models can model a state using a number of substates in which the duration of the state is a convolution of geometric distributions [18].”
From Activity recognition using semi-Markov models on real world smart home datasets (2010) · cites this paper as [18]
The Introduction mentions multilevel Markov models, and §4.2 describes paired chunk tags in a CRF. Neither passage addresses substates or a state-duration distribution; searches for the claimed convolution of geometric distributions and for hierarchical models with substates found no supporting passage in our copy. Page numbers were not available. (LLM, conf=0.73)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 26
- S. Abney, R. E. Schapire, and Y. Singer. Boosting applied to tagging and PP attachment. In Proc. EMNLP-VLC, New Brunswick, New Jersey, 1999. ACL.
- A. L. Berger, S. A. Della Pietra, and V. J. Della Pietra. A maxi- mum entropy approach to natural language processing. Com- putational Linguistics, 22(1), 1996.
- L. Bottou. Une Approche théorique de l'Apprentissage Con- nexionniste: Applications à la Reconnaissance de la Parole. PhD thesis, Université de Paris XI, 1991.
- M. Collins. Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algo- rithms. In Proc. EMNLP 2002. ACL, 2002.
- M. Collins and N. Duffy. New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron. In Proc. 40th ACL, 2002.
- J. N. Darroch and D. Ratcliff. Generalized iterative scaling for log-linear models. The Annals of Mathematical Statistics, 43 (5):1470-1480, 1972.
- S. Della Pietra, V. Della Pietra, and J. Lafferty. Inducing fea- tures of random fields. IEEE PAMI, 19(4):380-393, 1997.
- D. Freitag and A. McCallum. Information extraction with HMM structures learned by stochastic optimization. In Proc. AAAI 2000, 2000.
- S. Geman and M. Johnson. Dynamic programming for parsing and estimation of stochastic unification-based grammars. In Proc. 40th ACL, 2002.
- L. Gillick and S. Cox. Some statistical issues in the compairson of speech recognition algorithms. In International Confer- ence on Acoustics Speech and Signal Processing, volume 1, pages 532-535, 1989.
- T. Kudo and Y. Matsumoto. Chunking with support vector ma- chines. In Proc. NAACL 2001. ACL, 2001.
- J. Lafferty, A. McCallum, and F. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling se- quence data. In Proc. ICML-01, pages 282-289, 2001.
- R. Malouf. A comparison of algorithms for maximum entropy parameter estimation. In Proc. CoNLL-2002, 2002.
- A. McCallum, D. Freitag, and F. Pereira. Maximum entropy Markov models for information extraction and segmentation. In Proc. ICML 2000, pages 591-598, Stanford, California, 2000.
- J. Nocedal and S. J. Wright. Numerical Optimization. Springer, 1999.
- V. Punyakanok and D. Roth. The use of classifiers in sequential inference. In NIPS 13, pages 995-1001. MIT Press, 2001.
- L. A. Ramshaw and M. P. Marcus. Text chunking using transformation-based learning. In Proc. Third Workshop on Very Large Corpora. ACL, 1995.
- A. Ratnaparkhi. A maximum entropy model for part-of-speech tagging. In Proc. EMNLP, New Brunswick, New Jersey, 1996. ACL.
- A. Ratnaparkhi. A linear observed time statistical parser based on maximum entropy models. In C. Cardie and R. Weischedel, editors, EMNLP-2. ACL, 1997.
- S. Riezler, T. H. King, R. M. Kaplan, R. Crouch, J. T. Maxwell III, and M. Johnson. Parsing the Wall Street Journal using a lexical-functional grammar and discriminative esti- mation techniques. In Proc. 40th ACL, 2002.
- E. F. T. K. Sang. Memory-based shallow parsing. Journal of Machine Learning Research, 2:559-594, 2002.
- B. Taskar, P. Abbeel, and D. Koller. Discriminative probabilis- tic models for relational data. In Eighteenth Conference on Uncertainty in Artificial Intelligence, 2002.
- E. F. Tjong Kim Sang and S. Buchholz. Introduction to the CoNLL-2000 shared task: Chunking. In Proc. CoNLL-2000, pages 127-132, 2000.
- H. Wallach. Efficient training of conditional random fields. In Proc. 6th Annual CLUK Research Colloquium, 2002.
- A. Yeh. More accurate tests for the statistical significance of result differences. In COLING-2000, pages 947-953, Saar- bruecken, Germany, 2000.
- T. Zhang, F. Damerau, and D. Johnson. Text chunking based on a generalization of winnow. Journal of Machine Learning Research, 2:615-637, 2002.
Cited by
Sorted by citations
Savova, G. K., Masanz, J. J., Ogren, P. V., Zheng, J., Sohn, S., Kipper-Schuler, K. C., & Chute, C. G. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2009.001560 · Cited by 1,967 · see citing works
Natural language processing: state of the art, current trends and challenges
Khurana, D., Koli, A., Khatter, K., & Singh, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13428-4 · Cited by 1,823 · see citing works
Domain adaptation with structural correspondence learning
Blitzer, J., McDonald, R., & Pereira, F. (2006) · Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06 · doi:10.3115/1610075.1610094 · Cited by 1,543 · see citing works
Self-citationConditional random fields for activity recognition
Vail, D. L., Veloso, M. M., & Lafferty, J. D. (2007) · Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems · doi:10.1145/1329125.1329409 · Cited by 357 · see citing works
Structured prediction models for RNN based sequence labeling in clinical text
Jagannatha, A., & yu, H. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1082 · Cited by 215 · see citing works
Activity recognition using semi-Markov models on real world smart home datasets
van Kasteren, T. L. M., Englebienne, G., & Kröse, B. J. A. (2010) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-2010-0070 · Cited by 131 · see citing works
- Authors
- Sha, F., & Pereira, F.
- Affiliations
- University of Pennsylvania (US)
- Venue
- Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03
- Published
- 2003
- Volume
- 1
- Pages
- 134-141
- OpenAlex
- W2156515921
- Cited by
- 1,246
- References
- 0
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 7 · 2023: 11 · 2022: 10 · 2021: 22 · 2020: 25 · 2019: 28 · 2018: 44 · 2017: 46 · 2016: 54 · 2015: 51 · 2014: 82 · 2013: 89 · 2012: 91
- FWCI
- 48.26
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- shallow parsing, conditional random fields, sequence labeling, noun phrase chunking, maximum entropy model
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
