MaltParser: A language-independent system for data-driven dependency parsing

By Joakim Nivre, Johan Hall, Jens Nilsson, Atanas Chanev, Gülşen Eryiğit, Sandra Kübler, Svetoslav Marinov, Erwin Marsi. 2007

915 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/206348bcd5f13c341ea8d120754f328bb55c93f7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Transforming Dependency Structures to Logical Forms for Semantic Parsing (2016, background): “In recent years, there have been signiﬁcant advances in developing fast and accurate dependency parsers for many languages (McDonald et al., 2005; Nivre et al., 2007; Martins et al., 2013, inter alia ).”
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016, methodology): “As a preprocessing step, pseudo-projectivization of the syntactic trees (Nivre et al., 2007) was used, which allowed an accurate conversion of even the non-projective syntactic trees into syntactic transitions.”
Modeling Newswire Events using Neural Networks for Anomaly Detection (2014, methodology): “We perform (Nivre et al., 2007) on the sentences in the training data used in the ﬁrst phase of training to obtain the head words of the semantic arguments.”
IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP (2020, methodology): “(2017) conducted a comparative evaluation over models trained using off-the-shelf tools such as MaltParser (Nivre et al., 2005) on 2,098 annotated sentences from the news domain.”
A Neural Probabilistic Structured-Prediction Method for Transition-Based Natural Language Processing (2017, unknown): “1 (Nivre et al., 2007) Section 4 (Zhang and Nivre, 2011)”
That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets (2015, methodology): “• Dependency Triples: to better understand the deeper syntactic dependencies of keywords in tweets, we have also extracted typed dependency triples (e.g., nsubj(hate,I)) using the MaltParser (Nivre et al., 2007).”
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting (2017, methodology): “For the transition-based dependency parsing task, existing approaches typically can achieve the UAS score from 91.4 to 91.5 (Zhang & Clark, 2008; Nivre et al., 2007; Huang & Sagae, 2010).”
Parallel Data, Tools and Interfaces in OPUS (2012, methodology): “, 2007) and MaltParser (Nivre et al., 2007) and pre-trained models for various languages.”
The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies (2008, background): “…to the systems participating in the open challenge: named-entity labels as in the CoNLL-2003 Shared Task (Tjong Kim San and De Meulder, 2003) and from the BBN Wall Street Journal Entity Corpus, 2 WordNet supersense tags, and the output of an off-the-shelf dependency parser (Nivre et al., 2007b).”
The CoNLL 2007 Shared Task on Dependency Parsing (2007, methodology): “The parser of McDonald and Pereira (2006) had been applied to English, Czech and Danish, and the parser of Nivre et al. (2007) to ten different languages.”
The Effect of Syntactic Representation on Semantic Role Labeling (2008, unknown): “MaltParser is an incremental greedy classiﬁer-based parser based on SVMs, while the LTH parser and MSTParser use exact edge-factored search with a linear model trained using online margin-based structure learning.”
TectoMT: Modular NLP Framework (2010, unknown): “1 [4].”
A Natural Proof System for Natural Language (2017, unknown): “The transformation procedure starts from the initial dependency 5McDonald et al. (2005); Nivre et al. (2007); Martins et al. (2013); Manning et al. (2014) inter alia.”
Discriminative Improvements to Distributional Sentence Similarity (2013, methodology): “We consider two distributional feature sets: FEAT 1 , which includes unigrams; and FEAT 2 , which also includes bigrams and unlabeled dependency pairs obtained from MaltParser (Nivre et al., 2007).”