Generating Typed Dependency Parses from Phrase Structure Parses

By Marie-Catherine de Marneffe, Bill MacCartney, Christopher D. Manning. 2006

2,671 citations recorded by the source corpus.

This paper describes a system for extracting typed dependency parses of English sentences from phrase structure parses. In order to capture inherent relations occurring in corpus texts that can be critical in real-world applications, many NP relations are included in the set of grammatical relations used. We provide a comparison of our system with Minipar and the Link parser. The typed dependency extraction facility described here is integrated in the Stanford Parser, available for download.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Deep Fragment Embeddings for Bidirectional Image Sentence Mapping (2014, methodology): “king down both images and sentences into fragments and reason about their (latent) alignment. In particular, we propose to detect objects as image fragments and use sentence dependency tree relations [1] as sentence fragments (Figure 2). Fragment-Level Objective. In previous related work [20, 21], N”
Grounded Compositional Semantics for Finding and Describing Images with Sentences (2014, methodology): “We use the collapsed tree formalism of the Stanford dependency parser (de Marneffe et al., 2006).”
Parsing Algebraic Word Problems into Equations (2015, methodology): “We use the Stanford Dependency Parser in CoreNLP 3.4 (De Marneffe et al., 2006) to obtain syntactic information used for grounding and feature computation.”
Learning to Solve Arithmetic Word Problems with Verb Categorization (2014, methodology): “A RIS applies the Stanford dependency parser, named entity recognizer and coreference resolution system to the problem text (de Marneffe et al., 2006; Finkel et al., 2005; Raghunathan et al., 2010).”
Unsupervised Learning from Narrated Instruction Videos (2015, methodology): “ject relations. A direct object relation dis a pair composed of a verb and its direct object complement, such as “remove tire”, extracted from the dependency parser of the input transcribed narration [7]. We denote the set of all direct object relations extracted from all narrations as D. The cardin”
The Stanford CoreNLP Natural Language Processing Toolkit (2014, methodology): “…parse Provides full syntactic analysis, including both constituent and dependency representation, based on a probabilistic parser (Klein and Manning, 2003; de Marneffe et al., 2006). sentiment Sentiment analysis with a compositional model over trees using deep learning (Socher et al., 2013).”
Learning to Automatically Solve Algebra Word Problems (2014, methodology): “For example, the word “chemist” 2In our experiments these are generated using the Stanford parser (de Marneffe et al., 2006) might indicate a template like the one seen in Figure 4.”
Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation (2011, methodology): “We have built an automatic SDC extractor that uses the Stanford dependencies, which are extracted using the Stanford Parser (de Marneffe, MacCartney, and Manning, 2006).”
Designing and Interpreting Probes with Control Tasks (2019, methodology): “We convert the PTB constituency trees to the Stanford Dependencies formalism (de Marneffe et al., 2006) for our dependency edge prediction task.”
Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task (2017, background): “Potential answers were neighbors and neighbors-of-neighbors in a dependency parse of the sentence (Stanford dependency parser; De Marneffe et al., 2006), and input to the classiﬁer was the predicate, question verb, question string, and dependency relation be-tween the predicate and the potential…”
Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks (2015, methodology): “To do this, we use the Stanford parser (Marneffe et al., 2006) to detect whether the target stock is a subject of the keyword or not.”
Where to Look: Focus Regions for Visual Question Answering (2015, methodology): “ to yield a 600-dimensional vector, but since the word2vec representation is not sparse, averaging several words may muddle the representation. We improve the representation using the Stanford Parser [5] to bin the question into additional separate semantic bins. The ﬁrst bin captures the type of qu”
Globally Normalized Transition-Based Neural Networks (2016, background): “Empirically, Weiss et al. (2015) achieves the best performance, even though their model keeps the parameters of the locally normalized neural network fixed and only trains a perceptron that uses the activations as features.”
Cyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modeling for Policy and Decision Making (2015, methodology): “Instead, we implemented the Stanford Lexical Parser, along with a context-free lexical parsing model, to extract typed dependencies within the tweet text (Marneffe et al., 2006).”