Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers

By André F. T. Martins, Miguel B. Almeida, Noah A. Smith. 2013

191 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 Natural Language Processing

Citations in the corpus

Findings of the 2016 Conference on Machine Translation (2016, methodology): “The following external resources were used: part-of-speech tags and extra syntactic dependency information obtained with TurboTagger and TurboParser (Martins et al., 2013), trained on the Penn Treebank (for English) and on the version of the German TIGER corpus used in the SPMRL shared task (Seddah ”
What’s in an Embedding? Analyzing Word Embeddings through Multilingual Evaluation (2015, methodology): “For English, automatically labeled data was obtained by tagging and parsing a subset of the English Wikipedia dump provided by Al-Rfou et al. (2013) using TurboTagger and TurboParser (Martins et al., 2013).”
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations (2016, background): “The different systems and the numbers reported from them are taken from: ZhangNivre11: (Zhang and Nivre, 2011); Martins13: (Martins et al., 2013); Weiss15 (Weiss et al., 2015); Pei15: (Pei et al., 2015); Dyer15 (Dyer et al., 2015); Ballesteros16 (Ballesteros et al., 2016); LeZuidema14 (Le and Zuidem”
Easy-First Dependency Parsing with Hierarchical Tree LSTMs (2016, background): “The different systems and the numbers reported from them are taken from: ZhangNivre11: (Zhang and Nivre, 2011); Martins13: (Martins et al., 2013); Weiss15 (Weiss et al.”
Stack-Pointer Networks for Dependency Parsing (2018, background): ““Best Published” includes the most accurate parsers in term of UAS among Koo et al. (2010), Martins et al. (2011), Martins et al. (2013), Lei et al. (2014), Zhang et al. (2014), Zhang and McDonald (2014), Pitler and McDonald (2015), and Cheng et al. (2016). in McDonald and Nivre (2011).”
Unbabel’s Participation in the WMT16 Word-Level Translation Quality Estimation Shared Task (2016, methodology): “Our second recurrent model uses both recurrent and convolutional components, along with POS tags obtained from TurboTagger for both target and aligned source words.”
Learning What’s Easy: Fully Differentiable Neural Easy-First Taggers (2017, methodology): “• A feature-based linear model (TurboTagger, Martins et al. (2013)).”
Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser (2016, methodology): “The distilled model performs almost as well as the ensemble consensus and much better than (i) a strong LSTM FOG parser trained using the conventional Hamming cost function, (ii) recently published strong LSTM FOG parsers (Kiperwasser and Goldberg, 2016; Wang and Chang, 2016), and (iii) many higher-”
The Inside-Outside Recursive Neural Network model for Dependency Parsing (2014, methodology): “We ﬁrst compare the mixture reranker using the ∞ -order model against the state-of-the-art dependency parser TurboParser (with the full mode) (Martins et al., 2013) on PTB-U-23.”
Structured Training for Neural Network Transition-Based Parsing (2015, background): “McClosky et al. (2006) and Huang and Harper (2009) showed that iteratively re-training a single model (“self-training”) can be used to improve parsers in certain settings; Petrov et al.”
Transforming Dependency Structures to Logical Forms for Semantic Parsing (2016, background): “In recent years, there have been signiﬁcant advances in developing fast and accurate dependency parsers for many languages (McDonald et al., 2005; Nivre et al., 2007; Martins et al., 2013, inter alia ).”