Name Tagging with Word Clusters and Discriminative Training

By Scott Miller, Jethran Guinness, Alex Zamanian. 2004

321 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Extraction

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, methodology): “The induced word representation has been used with success in a wide variety of NLP tasks, including POS (Schütze, 1995), NER (Miller et al., 2004; Ratinov and Roth, 2009), or parsing (Koo et al.”
Domain Adaptation with Structural Correspondence Learning (2006, methodology): “We chose to compare with ASO because it consistently outperforms cotraining (Blum and Mitchell, 1998) and clustering methods (Miller et al., 2004).”
Design Challenges and Misconceptions in Named Entity Recognition (2009, methodology): “In this work, we analyze a simple technique of using word clusters generated from unlabeled text, which has been shown to improve performance of dependency parsing (Koo et al., 2008), Chinese word segmentation (Liang, 2005) and NER (Miller et al., 2004).”
Word Representations: A Simple and General Method for Semi-Supervised Learning (2010, methodology): “This technique was used by a variety of researchers (Miller et al., 2004; Liang, 2005; Koo et al., 2008; Ratinov & Roth, 2009; Huang & Yates, 2009).”
Joint Event Extraction via Structured Prediction with Global Features (2013, background): “Brown clusters that are learned from ACE English corpus (Brown et al., 1992; Miller et al., 2004; Sun et al., 2011).”
Simple, robust, scalable semi-supervised learning via expectation regularization (2007, methodology): “Instead of using data clustering directly to position the decision boundary, other methods pre-cluster unlabeled data, and use these clusters as features for supervised training on the labeled data (Miller et al., 2004).”
An Introduction to Conditional Random Fields (2010, unknown): “[90].”
Recognizing Named Entities in Tweets (2011, methodology): “Miller et al. (2004) use word clusters (Brown et al., 1992) learned from unlabeled text, resulting in a performance improvement of NER.”
Improved Relation Extraction with Feature-Rich Compositional Embedding Models (2015, background): “Embedding features have improved many tasks, including NER, chunking, dependency parsing, semantic role labeling, and relation extraction (Miller et al., 2004; Turian et al., 2010; Koo et al., 2008; Roth and Woodsend, 2014; Sun et al., 2011; Plank and Moschitti, 2013; Nguyen and Grishman, 2014).”
Interactive Feature Space Construction using Semantic Information (2009, background): “Although effective approaches along this vein have been shown to induce more accurate classi-ﬁers (Boggess et al., 1991; Miller et al., 2004; Li and Roth, 2005), naive approaches may instead result in higher sample complexity due to increased ambiguity introduced through these semantic resources.”
Neural Network Methods for Natural Language Processing (2017, background): “Self-normalizing aproaches, such as noise-contrastive estimation (NCE) [Mnih and Teh, 2012, Vaswani et al., 2013] or adding normalizing term to the training objective [Devlin et al., 2014]. e NCE approach improves training time performance by replacing the cross-entropy objective with a collection ”
Semi-supervised Relation Extraction with Large-scale Word Clustering (2011, methodology): “The idea of using word clusters as features in discriminative learning was pioneered by Miller et al. (2004), who augmented name tagging training data with hierarchical word clusters generated by the Brown clustering algorithm (Brown et al., 1992) from a large unlabeled corpus.”
Tailoring Continuous Word Representations for Dependency Parsing (2014, methodology): “…derived from unlabeled text have proven useful for many NLP tasks, e.g., part-of-speech (POS) tagging (Huang et al., 2014), named entity recognition (Miller et al., 2004), chunking (Turian et al., 2010), and syntactic parsing (Koo et al., 2008; Finkel et al., 2008; T¨ackstr¨om et al., 2012).”
Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features (2014, methodology): “To resolve this conﬂict, we integrate the debinariza-tion process into the parsing process, i.e., when a (Collins and Koo, 2005) Semi-supervised word cluster features have been successfully applied to many NLP tasks (Miller et al., 2004; Koo et al., 2008; Zhu et al., 2013).”