Early results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-Enhanced Lexicons
By Andrew McCallum, Wei Li. 2003
1,369 citations recorded by the source corpus.
Models for many natural language tasks benefit from the flexibility to use overlapping, non-independent features. For example, the need for labeled data can be drastically reduced by taking advantage of domain knowledge in the form of word lists, part-of-speech tags, character n-grams, and capitalization patterns. While it is difficult to capture such inter-dependent features with a generative probabilistic model, conditionally-trained models, such as conditional maximum entropy models, handle them well. There has been significant work with such models for greedy sequence modeling in NLP (Ratnaparkhi, 1996; Borthwick et al., 1998).
Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing, Information Extraction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Percy Liang
- Jianfeng Gao
- Christopher D. Manning
- Yoshua Bengio
- Luke S. Zettlemoyer
- Noah A. Smith
- Graham Neubig
In Molecular Biology
- Christopher D. Manning
- Percy Liang
- Phil Blunsom
- Bill MacCartney
- Noah A. Smith
- Trevor Cohn
- Andrew McCallum
- Shaodian Zhang
In Natural Language Processing
- Christopher D. Manning
- Mohit Bansal
- Percy Liang
- Noah A. Smith
- Graham Neubig
- Jianfeng Gao
- Luke S. Zettlemoyer
- Yejin Choi
In Information Extraction
- Ronan Collobert
- Christopher D. Manning
- Percy Liang
- Jason Eisner
- Xiao Li
- Daniel Klein
- Claire Cardie
- Jason Aaron Edward Weston
Citations in the corpus
- Natural Language Processing (Almost) from Scratch (2011, methodology): “CRFs have been widely used in the NLP world, such as for POS tagging (Lafferty et al., 2001), chunking (Sha and Pereira, 2003), NER (McCallum and Li, 2003) or SRL (Cohn and Blunsom, 2005).”
- Applying Conditional Random Fields to Japanese Morphological Analysis (2004, methodology): “Note that our formulation of CRFs is different from the widely-used formulations (e.g., (Sha and Pereira, 2003; McCallum and Li, 2003; Peng et al., 2004; Pinto et al., 2003; Peng and McCallum, 2004)).”
- Distribution Matching for Transduction (2009, background): “Conditional random fields (CRFs) [9] are considered to be the stateof-the-art framework for this sequential labeling problem [11].”
- Interactive Information Extraction with Constrained Conditional Random Fields (2004, positive): “CRFs have been shown to perform well on information extraction tasks (McCallum & Li 2003; Pinto et al. 2003; McCallum 2003; Sha & Pereira 2003), and are well-suited for interactive information extraction since the confi dence of the labels can be estimated and there is a natural scheme for…”
- Semi-Supervised Learning for Natural Language (2005, methodology): “. . . . . . . . . . . . . . . . . . . . . . . . . 18 2.1.3 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 2.1.4 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 2.1.5 Existing methods . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.2 Named-entit”
- Multimodal Learning for Web Information Extraction (2017, methodology): “For example, conditional random field (CRF) can be used for named entity recognition (NER) where CRF models are trained and then applied to extract sets of named entities such as Person, Location and Organization [16].”
- Deep Learning for Efficient Discriminative Parsing (2011, background): “, 2001), and CRFs had great success in NLP (Sha and Pereira, 2003; McCallum and Li, 2003; Cohn and Blunsom, 2005).”
- Sequence Classification Restricted Boltzmann Machines With Gated Units (2020, background): “M ODELING sequences is an important research topic with a variety of applications, ranging from natural language processing [1], [2] to computer vision [3].”
- Hidden Conditional Random Fields for Gesture Recognition (2006, background): “A Markov assumption may still be enforced in the state sequence, allowing inference to be performed efficiently using dynamic programming.”
- Effects of Semantic Features on Machine Learning-Based Drug Name Recognition Systems: Word Embeddings vs. Manually Constructed Dictionaries (2015, background): “It has been widely applied to a large number of Natural Language Processing (NLP) tasks such as named entity recognition [45], shallow parsing [46], and Chinese word segmentation [47] and has shown good performances on these tasks.”
- Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts (2013, methodology): “With sequence labeling models like Hidden Markov Models (HMMs) and Conditional Random Fields (CRFs), the two tasks could be jointly handled taking advantage of the Markov property which models transitions between labels [15,16].”
- Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets (2004, background): “Such models are well suited to sequence analysis, and CRFs in particular have been shown to be useful in part-of-speech tagging (Lafferty et al., 2001), shallow parsing (Sha and Pereira, 2003), and named entity recognition for newswire data (McCallum and Li, 2003).”