Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network

By Kristina Toutanova, Daniel Klein, Christopher D. Manning, Yoram Singer. 2003

3,644 citations recorded by the source corpus.

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features. Using these ideas together, the resulting tagger gives a 97.24% accuracy on the Penn Treebank WSJ, an error reduction of 4.4% on the best previous single automatically learned tagging result.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing, Model Architectures

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

In Molecular Biology

In Natural Language Processing

In Model Architectures

Citations in the corpus

Recurrent Neural Network Grammars (2016, background): “, 2015); they are predicted for English with the Stanford Tagger (Toutanova et al., 2003) and Chinese with Marmot (Mueller et al.”
COCO-Stuff: Thing and Stuff Classes in Context (2016, methodology): “We use a Part-OfSpeech (POS) tagger [54] to automatically detect nouns.”
node2vec: Scalable Feature Learning for Networks (2016, methodology): “The labels represent the Part-ofSpeech (POS) tags inferred using the Stanford POS-Tagger [32].”
Natural Language Processing (Almost) from Scratch (2011, methodology): “..A standard benchmark setup is described in detail by Toutanova 2 arXiv Natural Language Processing (almost) from Scratch Task Benchmark Dataset Training set Test set (#tokens) (#tokens) (#tags) POS Toutanova et al. (2003) WSJ sections 0{18 sections 22{24 ( 45 ) ( 912,344 ) ( 129,654 ) Chunking CoN”
VQA: Visual Question Answering (2015, positive): “We cast this comparison in terms of nouns, verbs, and adjectives by extracting all words from the caption data (MS COCO captions for real images and captions collected by us for abstract scenes) using the Stanford part-of-speech (POS)6 tagger (Toutanova et al. 2003).”
The Stanford CoreNLP Natural Language Processing Toolkit (2014, methodology): “…model using a CRF sequence tagger (Finkel et al., 2005). pos Labels tokens with their part-of-speech (POS) tag, using a maximum entropy POS tagger (Toutanova et al., 2003). lemma Generates the lemmas (base forms) for all tokens in the annotation. gender Adds likely gender information to names.…”
12-in-1: Multi-Task Vision and Language Representation Learning (2019, methodology): “To measure the overlap in visual concepts between a question q j and reference r k , we count overlapping nouns and adjectives (identified using a part-of-speech tagger [47]) and denote this d(q j , r (i) k ).”
Movie Description (2016, methodology): “mer toolbox (Toutanova et al. 2003), then we compute the frequency of stemmed words in the corpora.”
Semantic Parsing via Paraphrasing (2014, methodology): “We run all questions through the Stanford CoreNLP pipeline (Toutanova and Manning, 2003; Finkel et al., 2005; Klein and Manning, 2003).”
Deep Biaffine Attention for Neural Dependency Parsing (2016, methodology): “For the English PTB-SD datasets, we use POS tags generated from the Stanford POS tagger (Toutanova et al., 2003); for the Chinese PTB dataset we use gold tags; and for the CoNLL 09 dataset we use the provided predicted tags.”
A Fast and Accurate Dependency Parser using Neural Networks (2014, methodology): “For English, we follow the standard splits of (Toutanova et al., 2003) with ten-way jackkniﬁng of the training data (accuracy ≈ 97 .”
Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks (2017, methodology): “Toutanova et al. (2003) report an accuracy of 97.24% on the test set.”
Transition-Based Dependency Parsing with Stack Long Short-Term Memory (2015, methodology): “8 The part-of-speech tags are predicted by using the Stanford Tagger (Toutanova et al., 2003) with an accuracy of 97.3%.”
Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research (2015, methodology): “We tagged all words in the dataset corpus using the Standford Part-Of-Speech (POS) tagger toolbox [19].”
Coherent Multi-sentence Video Description with Variable Level of Detail (2014, methodology): “We assign part-of-speech (POS) tags to the collected descriptions and the ones provided by TACoS using the Stanford POS tagger [23].”
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language (2015, methodology): “We used gold POS-tags for newswire, and predicted POS-tags (using Stanford tagger (Toutanova et al., 2003)) in Wikipedia.”