Simple Semi-supervised Dependency Parsing

By Terry Koo, Xavier Carreras, Michael Collins. 2008

502 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

In Information Extraction

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, methodology): “, 2004; Ratinov and Roth, 2009), or parsing (Koo et al., 2008).”
A Fast and Accurate Dependency Parser using Neural Networks (2014, methodology): “For this reason, techniques for introducing higher-support features such as word class features have also been very successful in improving parsing performance (Koo et al., 2008).”
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations (2016, background): “Modern approaches to dependency parsing can be broadly categorized into graph-based and transition-based parsers (Kübler et al., 2008).”
Self-Training PCFG Grammars with Latent Annotations Across Languages (2009, background): “There are other successful semi-supervised training approaches for dependency parsing, such as (Koo et al., 2008; Wang et al., 2008), and it would be interesting to investigate how they could be applied to constituency parsing.”
Lexicon Infused Phrase Embeddings for Named Entity Resolution (2014, background): “This process produces a hierarchical clustering of the word types in the corpus, and these clusterings have been found useful in many applications (Ratinov and Roth, 2009; Koo et al., 2008; Miller et al., 2004).”
Polyglot: Distributed Word Representations for Multilingual NLP (2013, background): “Dependency parsing and other NLP tasks have been shown to benefit from such a large unannotated corpus (Koo et al., 2008), and a variety of unsupervised feature learning methods have been shown to unilaterally improve the performance of supervised learning tasks (Turian et al.”
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).”
Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space (2014, methodology): “In comparison to Brown clusters, the vector embeddings have the advantages of substantially better scalability in their training, and intriguing potential for their continuous and multi-dimensional interrelations.”
Natural Language Processing with Small Feed-Forward Networks (2017, background): “Bloom Mapped Word Clusters It is well known that word clusters can be powerful features in linear models for a variety of tasks (Koo et al., 2008; Turian et al., 2010).”
Coreference Semantics from Web Features (2012, methodology): “Recent previous work has used clustering information to improve the performance of supervised NLP tasks such as NER and dependency parsing (Koo et al., 2008; Lin and Wu, 2009).”
Ambiguity-aware Ensemble Training for Semi-supervised Dependency Parsing (2014, methodology): “Previously, unlabeled data is explored to derive useful local-context features such as word clusters (Koo et al., 2008), subtree frequencies (Chen et al., 2009; Chen et al., 2013), and word co-occurrence counts (Zhou et al., 2011; Bansal and Klein, 2011).”
A Joint Model for Entity Analysis: Coreference, Typing, and Linking (2014, methodology): “…on capitalization, presence of numbers, sufﬁxes, etc.), 4) word shape (based on the pattern of uppercase and lowercase letters, digits, and punctuation), 5) Brown cluster preﬁxes of length 4, 6, 10, 20 using the clusters from Koo et al. (2008), and 6) common bigrams of word shape and word identity.”
Transition-based Dependency Parsing with Rich Non-local Features (2011, background): “…parser of Huang and Sagae (2010) (row ‘H&S10’), and graph-based models including MSTParser (McDonald and Pereira, 2006), the baseline feature parser of Koo et al. (2008) (row ‘K08 baeline’), and the two models of Koo and Collins (2010) ing the highest attachment score reported for a…”
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters (2013, background): “Previous work has shown that unlabeled text can be used to induce unsupervised word clusters which can improve the performance of many supervised NLP tasks (Koo et al., 2008; Turian et al., 2010; Täckström et al., 2012, inter alia).”
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).”
Fast and Accurate Shift-Reduce Constituent Parsing (2013, methodology): “Word clusters are regarded as lexical intermediaries for dependency parsing (Koo et al., 2008) and POS tagging (Sun and Uszkoreit, 2012).”