Deep Learning for Efficient Discriminative Parsing

By Ronan Collobert. 2011

193 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

Grammar as a Foreign Language (2014, methodology): “To avoid complex inference methods, Collobert (2011) propose a recurrent neural network where parse trees are decomposed into a stack of indepennt levels.”
Natural Language Processing (Almost) from Scratch (2011, background): “Florian et al. (2003) presented the best system at the NER CoNLL 2003 challenge, with 88.”
A Fast and Accurate Dependency Parser using Neural Networks (2014, background): “There have been a number of recent uses of deep learning for constituency parsing (Collobert, 2011; Socher et al., 2013).”
Deep Learning: Methods and Applications (2014, background): “More recent work reported in [61] further developed a fast, purely discriminative approach for parsing based on the deep recurrent convolutional architecture.”
From machine learning to machine reasoning (2011, methodology): “Deep learning is therefore intimately related to multi-task learning (Caruana, 1997.)”
Polyglot: Distributed Word Representations for Multilingual NLP (2013, background): “The system they built, SENNA, offers part of speech tagging, chunking, named entity recognition, semantic role labeling and dependency parsing (Collobert, 2011).”
A Model of Coherence Based on Distributed Sentence Representation (2014, background): “Word embeddings {e} are borrowed from Senna (Collobert et al., 2011; Collobert, 2011).”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, neutral): “More recent work reported in [206] further developed a fast purely discriminative approach for parsing based on the deep recurrent convolutional architecture called Graph Transformer Network.”
Big Data: Deep Learning for financial sentiment analysis (2018, background): “In [43] a deep convolutional neural network is proposed that exploits the character-to sentence-level information to perform sentiment analysis of short texts.”
State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, background): “Furthermore, they demonstrated the transfer learning capability of deep architectures through the SENNA system [59] to share representations across various NLP tasks such as named-entity recognition, learning language models, chunking, part-of-speech tagging, semantic role-labeling, and so forth.”
#TagSpace: Semantic Embeddings from Hashtags (2014, background): “, 2011) and parsing (Collobert, 2011).”
Weakly Supervised Energy-Based Learning for Action Segmentation (2019, methodology): “Our CDFL extends the loss used for training of the Graph Transformer Network (GTN) [15, 13, 2, 5].”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, background): “levels in a fixed way, in a recursive network it is possible to let the data decide which parts of the input should be combined with which part, which can be exploited for example to parse natural language or scenes (Collobert, 2011; Socher et al., 2011).”
Deep Learning for Chinese Word Segmentation and POS Tagging (2013, methodology): “Several works have investigated how to use deep learning for NLP applications (Bengio et al., 2003; Collobert et al., 2011; Collobert, 2011; Socher et al., 2011).”
Unsupervised Morphology Induction Using Word Embeddings (2015, methodology): “…2007; Mikolov and Zweig, 2012), paraphrase detection (Socher et al., 2011a), sentiment analysis (Socher et al., 2011b), discriminative parsing (Collobert, 2011), as well as similar tasks involving larger units such as documents (Glorot et al., 2011; Huang et al., 2012; Le and Mikolov, 2014).”
Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts (2014, methodology): “The backpropagation algorithm is a natural choice to efficiently compute gradients of network architectures such as the one proposed in this work (Lecun et al., 1998; Collobert, 2011).”
Factor-based Compositional Embedding Models (2014, background): “They have been successfully applied to a range of NLP tasks, including syntax [2, 4, 5] and semantics [6, 7, 8].”
Boosting Named Entity Recognition with Neural Character Embeddings (2015, methodology): “Taking the log, we arrive at the following conditional log-probability: log p ( [t]N1 |[w]N1 , θ ) = S ( [w]N1 , [t] N 1 , θ ) −log ∑ ∀[u]N1 ∈TN eS([w] N 1 ,[u] N 1 ,θ) (4) The log-likelihood in Equation 4 can be computed efficiently using dynamic programming (Collobert, 2011).”
Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks (2016, background): “We also tried a variant of the LSTM model, gated recurrent units (Cho et al., 2014), but the results were generally lower than LSTM. word vectors pretrained with GloVe on Twitter (Pennington et al., 2014) for MRDA and SwDA, as these choices yielded the best results among all publicly available word2”
Learning Character-level Representations for Part-of-Speech Tagging (2014, methodology): “The log-likelihood in Equation 7 can be computed efficiently using dynamic programming (Collobert, 2011).”