Part of Speech Tagging Using a Network of Linear Separators
By Dan Roth, Dmitry Zelenko. 1998
We present an architecture and an on-line learning algorithm and apply it to the problem of part-of-speech tagging. The architecture presented, SNOW, is a network of linear separators in the feature space, utilizing the Winnow update algorithm.Multiplicative weight-update algorithms such as Winnow have been shown to have exceptionally good behavior when applied to very high dimensional problems, and especially when the target concepts depend on only a small subset of the features in the feature space. In this paper we describe an architecture that utilizes this mistake-driven algorithm for multi-class prediction-selecting the part of speech of a word. The experimental analysis presented here provides more evidence to that these algorithms are suitable for natural language problems.The algorithm used is an on-line algorithm: every example is used by the algorithm only once, and is then discarded. This has significance in terms of efficiency, as well as quick adaptation to new contexts.We present an extensive experimental study of our algorithm under various conditions; in particular, it is shown that the algorithm performs comparably to the best known algorithms for POS.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Dan Roth
- Ashish Sabharwal
- Daniel Khashabi
- Tushar Khot
- Hannaneh Hajishirzi
- Peter Clark
- Chitta Baral
- Subhro Roy
Citations in the corpus
- Reasoning about Quantities in Natural Language (2015, methodology): “Part of speech tags: we use the Illinois POS Tagger (Roth and Zelenko, 1998).”
- Question Answering as Global Reasoning Over Semantic Abstractions (2018, background): “• Sequence or labels for sequence of tokens; for example Lemma and POS (Roth and Zelenko 1998).”
- Design Challenges and Misconceptions in Named Entity Recognition (2009, methodology): “Surprisingly, the greedy policy performs well, this phenmenon was also observed in the POS tagging task (Toutanova et al., 2003; Roth and Zelenko, 1998).”
- CogCompNLP: Your Swiss Army Knife for NLP (2018, background): “In Figure 4 we do not show any results on SPACYsince unlike other tools, in SPACY we did not find a clean-cut way to study individual modules in isolation, In order to com- pare other tools with SPACY we perform another experiment where all the systems annotate Tokenizing, Sentence Splitting, POS ta”
- The effects of part–of–speech tagging on text–to–speech synthesis for resource–scarce languages (2010, background): “The Winnow algorithm [51, 63] performs this learning:”
- Have things changed now?: an empirical study of bug characteristics in modern open source software (2006, methodology): “We use several different classifier learning methods, including support vector machine(SVM) [37], Winnow, Perceptron, and Naive Bayes [33].”
- Sentiment analysis using product review data (2015, background): “In natural language processing, part-of-speech (POS) taggers [29-31] have been developed to classify words based on their parts of speech.”