Guided Learning for Bidirectional Sequence Classification

By Libin Shen, Giorgio Satta, Aravind K. Joshi. 2007

203 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

Natural Language Processing (Almost) from Scratch (2011, methodology): “(2003) 800 64 Shen et al. (2007) 2200 833 SENNA 32 4”
Search-based structured prediction (2009, neutral): “One answer, akin to the learned search order method (Shen et al. 2007) would be to simply allow”
Bidirectional LSTM-CRF Models for Sequence Tagging (2015, background): “…compared the performance of LSTM networks based models for se-Table (Gimenez and Marquez, 2004) 97.16 No Bidirectional perceptron learning (Shen et al., 2007) 97.33 No Semi-supervised condensed nearest neighbor 97.50 Yes (Soegaard, 2011) CRFs with structure regularization (Sun, 2014)…”
Learning What’s Easy: Fully Differentiable Neural Easy-First Taggers (2017, methodology): “…decoders have been used in POS tagging (Tsuruoka and Tsujii, 2005; Ma et al., 2013), dependency parsing (Goldberg and Elhadad, 2010), and coreference resolution (Stoyanov and Eisner, 2012), being related to cyclic dependency networks and guided learning (Toutanova et al., 2003; Shen et al., 2007).”
Towards Understanding Situated Natural Language (2010, unknown): “The intuition in Figure 3 rather suggests us to use a greedy “order-free” inference process (Shen et al., 2007): we label the word we are most conﬁdent in (possibly the least ambiguous, which can be in any position in the sentence) and then use the known features of that concept to help label the…”
Practical Very Large Scale CRFs (2010, result): “test) data, which compares favorably with some of the best results for this task (for instance (Toutanova et al., 2003; Shen et al., 2007; Suzuki and Isozaki, 2008)).”
Structure Regularization for Structured Prediction (2014, methodology): “The POS-Tagging task is a highly competitive task, with many methods proposed, and the best report (without using extra resources) until now is achieved by using a bidirectional learning model in [13],9 with the accuracy 97.”
Discriminative Syntax-Based Word Ordering for Text Generation (2015, unknown): “The use of perceptron learning to improve search has been proposed in guided learning for easy-ﬁrst search (Shen, Satta, and Joshi 2007) and LaSO (Daum´e and Marcu 2005).”
Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics? (2011, background): “At first glance, current part-of-speech taggers work rapidly and reliably, with per-token accuracies of slightly over 97% [1–4].”
An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing (2010, methodology): “The model is trained using a variant of the structured perceptron (Collins, 2002), similar to the algorithm of (Shen et al., 2007; Shen and Joshi, 2008).”
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting (2017, background): “The POS tagging task is a well-known benchmark task, with the accuracy reports from 97.2% to 97.4% (Toutanova et al., 2003; Sun, 2014; Shen et al., 2007; Tsuruoka et al., 2011; Collobert et al., 2011; Huang et al., 2015).”
Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections (2011, background): “Supervised part-of-speech (POS) taggers, for example, approach the level of inter-annotator agreement (Shen et al., 2007, 97.3% accuracy for English).”
Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition (2014, background): “23% (Shen et al., 2007) 97.”
Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data (2008, methodology): “The development data and test data were obtained from system dev. test additional resources JESS-CM (CRF/HMM) 97.3597.401G-word unlabeled data (Shen et al., 2007) 97.2897.33– (Toutanova et al., 2003)97.1597.24crude company name detector [sup.”