The Stanford Typed Dependencies Representation
By Marie-Catherine de Marneffe, Christopher D. Manning. 2008
1,022 citations recorded by the source corpus.
This paper examines the Stanford typed dependencies representation, which was designed to provide a straightforward description of grammatical relations for any user who could benefit from automatic text understanding. For such purposes, we argue that dependency schemes must follow a simple design and provide semantically contentful information, as well as offer an automatic procedure to extract the relations. We consider the underlying design principles of the Stanford scheme from this perspective, and compare it to the GR and PARC representations. Finally, we address the question of the suitability of the Stanford scheme for parser evaluation.
Subfields: Artificial Intelligence, Information Extraction, Computational Linguistics & Semantics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Christopher D. Manning
- Yejin Choi
- Jianfeng Gao
- Percy Liang
- Luke S. Zettlemoyer
- Hannaneh Hajishirzi
- Yoav Goldberg
In Information Extraction
- Yoav Goldberg
- Gregory F. Coppola
- Sanda M. Harabagiu
- Daniel Klein
- Jacob Andreas
- Marcus Rohrbach
- Trevor Darrell
- Omer Levy
In Computational Linguistics & Semantics
- Yoav Goldberg
- Gregory F. Coppola
- Daniel Klein
- Eduard H. Hovy
- Jacob Andreas
- Marcus Rohrbach
- Trevor Darrell
- Christopher D. Manning
Citations in the corpus
- Neural Module Networks (2015, methodology): “Here we evaluate on the VQA dataset [3].”
- Learning to Compose Neural Networks for Question Answering (2016, methodology): “In this work, syntactic structure is provided by the Stanford dependency parser (De Marneffe and Manning, 2008).”
- SciTaiL: A Textual Entailment Dataset from Science Question Answering (2018, background): “Also edges from P to objects beginning with a preposition (e.g., “through a system of tubes”) are labeled with the corresponding preposition9 (e.g., through) similar to the collapsed dependencies (de Marneffe and Manning 2008).”
- Choosing Linguistics over Vision to Describe Images (2012, positive): “We use “collapsed-ccprocessed-dependencies” which is intended to be more useful for relation extraction task (Marneffe and Manning 2008), as dependencies involving prepositions and conjuncts are collapsed to reflect direct relation between content words.”
- Dependency-Based Word Embeddings (2014, methodology): “For DEPS, the corpus was tagged with parts-of-speech using the Stanford tagger (Toutanova et al., 2003) and parsed into labeled Stanford dependencies (de Marneffe and Manning, 2008) using an implementation of the parser described in (Goldberg and Nivre, 2012).”
- Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing (2015, methodology): “Iterative Parameter Mixing for Distributed Optimization McDonald et al. (2010) study a perceptron-based (see §2.”
- Process Model Generation from Natural Language Text (2011, neutral): “The Stanford Parser also produces 55 different Stanford Dependencies [12].”
- Reporting bias and knowledge acquisition (2013, background): “(It s sufficient to consider it a more logically formalized set of interpretive rules than the later Stanford Dependencies [8, 9], leading to generic knowledge similar to that targeted by systems subsequent to Knext, such as NELL [5].)”
- Deep Compositional Question Answering with Neural Module Networks (2015, background): “measure : Attention → Label FC ReLU Softmax yesFC A measurement module measure[c] takes an attention alone and maps it to a distribution over labels.”
- Automatic extraction of relations between medical concepts in clinical texts (2011, methodology): “We use the Stanford dependency parser [12] to determine this path.”
- Visual question answering: A survey of methods and datasets (2016, methodology): “The parsing of the question is a crucial step, which is performed with the Standford dependency parser [13] which basically identifies grammatical relations between parts of the sentence.”
- Graph-Structured Representations for Visual Question Answering (2016, methodology): “The question is processed with the Stanford dependency parser [7], which outputs the following.”