Transition-Based Dependency Parsing with Stack Long Short-Term Memory

By Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, Noah A. Smith. 2015

818 citations recorded by the source corpus.

This work was sponsored in part by the U. S. Army Research Laboratory and the U. S. Army Research Office/nunder contract/grant number W911NF-10-1-0533, and in part by NSF CAREER grant IIS-1054319./nMiguel Ballesteros is supported by the European Commission under the contract numbers FP7-ICT-610411 (project MULTISENSOR) and H2020-RIA-645012 (project KRISTINA).

Subfields: Natural Language Processing

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

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations (2015, background): “Other recent papers have proposed RNN-like architectures with new ways of reading, storing and updating information to improve their capacity to learn algorithmic or syntactic patterns (Joulin & Mikolov, 2015; Dyer et al., 2015; Grefenstette et al., 2015).”
Learning to Transduce with Unbounded Memory (2015, background): “We begin by describing the operations and dynamics of a neural Stack, before showing how to modify it to act as a Queue, and extend it to act as a DeQue.”
Neural Architectures for Named Entity Recognition (2016, methodology): “Following Dyer et al. (2015), we use stack LSTMs to compute a fixed dimensional embedding of each of these, and take a concatenation of these to obtain the full algorithm state.”
Data Recombination for Neural Semantic Parsing (2016, methodology): “…new “recombinant” examples, which we use to train a sequence-to-sequence RNN. have made swift inroads into many structured prediction tasks in NLP, including machine translation (Sutskever et al., 2014; Bahdanau et al., 2014) and syntactic parsing (Vinyals et al., 2015b; Dyer et al., 2015).”
Deep Biaffine Attention for Neural Dependency Parsing (2016, background): “…and a conditional random ﬁeld loss objective to allow the parser to “undo” previous actions once it ﬁnds evidence that they may have been incorrect; and Dyer et al. (2015) and (Kuncoro et al., 2016) instead use LSTMs to represent the stack and buffer, getting state-of-the-art performance by…”
Relational inductive biases, deep learning, and graph networks (2018, background): “…computers and how they transfer information between each other, such as persistent slotted storage, registers, memory I/O controllers, stacks, and queues (e.g. Dyer et al., 2015; Grefenstette et al., 2015; Joulin and Mikolov, 2015; Sukhbaatar et al., 2015; Kurach et al., 2016; Graves et al., 2016).”
Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “[135] proposed stack-LSTMs to model arbitrarily long history.”
Deriving Neural Architectures from Sequence and Graph Kernels (2017, background): “Dyer et al. (2015; 2016) recently introduced a recursive neural model for transition-based language modeling and parsing.”
Sentence-State LSTM for Text Representation (2018, background): “LSTM encoders have since been explored for other tasks, including syntactic parsing (Dyer et al., 2015), text classiﬁcation (Yang et al., 2016) and machine reading (Hermann et al., 2015).”
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, methodology): “One of the most popular and attractive approaches is to use tree-structured recursive neural networks (Socher et al., 2013; Le and Zuidema, 2014; Dyer et al., 2015), including stacking them on top of a sequential BiLSTM (Miwa and Bansal, 2016).”
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF (2016, background): “An elegant solution whose effectiveness has been proven by previous work (Dyer et al., 2015) is bi-directional LSTM (BLSTM).”
Globally Normalized Transition-Based Neural Networks (2016, positive): “Our results also signiﬁcantly outperform the LSTM-based approaches of Dyer et al. (2015) and”
Recurrent Dropout without Memory Loss (2016, background): “…from sentence classiﬁcation (Wang et al., 2015; Irsoy and Cardie, 2014; Liu et al., 2015) and various tagging problems (Dyer et al., 2015) to language modelling (Kim et al., 2015; Zhang et al., 2015), text generation (Zhang and Lapata, 2014) and sequence-to-sequence prediction tasks (Sutskever…”
Tree-Structured Composition in Neural Networks without Tree-Structured Architectures (2015, background): “Our results engage with those of Vinyals et al. (2014) and Dyer et al. (2015), who ﬁnd that sequence models can learn to recognize syntactic structure in natural language, at least when trained on explicitly syntactic tasks.”