Dependency parsing online

Dependency parsing online DEFAULT

Stanford Parser

Your query

My dog also likes eating sausage.










(ROOT (S (NP (PRP$ My) (NN dog)) (ADVP (RB also)) (VP (VBZ likes) (S (VP (VBG eating) (NP (NN sausage))))) (. .)))

Universal dependencies

nmod:poss(dog-2, My-1) nsubj(likes-4, dog-2) advmod(likes-4, also-3) root(ROOT-0, likes-4) xcomp(likes-4, eating-5) obj(eating-5, sausage-6)

Universal dependencies, enhanced

nmod:poss(dog-2, My-1) nsubj(likes-4, dog-2) advmod(likes-4, also-3) root(ROOT-0, likes-4) xcomp(likes-4, eating-5) obj(eating-5, sausage-6)


Tokens: 7
Time: 0.033 s
Parser: englishPCFG.ser.gz

Back to parser home
Last updated 2016-09-12

Valid XHTML 1.0 Strict


Software > Stanford Parser

About | Citing | Questions | Download | Included Tools | Extensions | Release history | Sample output | Online | FAQ


A natural language parser is a program that works out the grammatical structure of sentences, for instance, which groups of words go together (as "phrases") and which words are the subject or object of a verb. Probabilistic parsers use knowledge of language gained from hand-parsed sentences to try to produce the most likely analysis of new sentences. These statistical parsers still make some mistakes, but commonly work rather well. Their development was one of the biggest breakthroughs in natural language processing in the 1990s. You can try out our parser online.

Package contents

This package is a Java implementation of probabilistic natural language parsers, both highly optimized PCFG and lexicalized dependency parsers, and a lexicalized PCFG parser. The original version of this parser was mainly written by Dan Klein, with support code and linguistic grammar development by Christopher Manning. Extensive additional work (internationalization and language-specific modeling, flexible input/output, grammar compaction, lattice parsing, k-best parsing, typed dependencies output, user support, etc.) has been done by Roger Levy, Christopher Manning, Teg Grenager, Galen Andrew, Marie-Catherine de Marneffe, Bill MacCartney, Anna Rafferty, Spence Green, Huihsin Tseng, Pi-Chuan Chang, Wolfgang Maier, and Jenny Finkel.

The lexicalized probabilistic parser implements a factored product model, with separate PCFG phrase structure and lexical dependency experts, whose preferences are combined by efficient exact inference, using an A* algorithm. Or the software can be used simply as an accurate unlexicalized stochastic context-free grammar parser. Either of these yields a good performance statistical parsing system. A GUI is provided for viewing the phrase structure tree output of the parser.

As well as providing an English parser, the parser can be and has been adapted to work with other languages. A Chinese parser based on the Chinese Treebank, a German parser based on the Negra corpus and Arabic parsers based on the Penn Arabic Treebank are also included. The parser has also been used for other languages, such as Italian, Bulgarian, and Portuguese.

The parser provides Universal Dependencies (v1) and Stanford Dependencies output as well as phrase structure trees. Typed dependencies are otherwise known grammatical relations. This style of output is available only for English and Chinese. For more details, please refer to the Stanford Dependencies webpage and the Universal Dependencies v1 documentation. (See also the current Universal Dependencies documentation, but we are yet to update to it.).

Shift-reduce constituency parser

As of version 3.4 in 2014, the parser includes the code necessary to run a shift reduce parser, a much faster constituent parser with competitive accuracy. Models for this parser are linked below.

Neural-network dependency parser

In version 3.5.0 (October 2014) we released a high-performance dependency parser powered by a neural network. The parser outputs typed dependency parses for English and Chinese. The models for this parser are included in the general Stanford Parser models package.

Dependency scoring

The package includes a tool for scoring of generic dependency parses, in a class . This tool measures scores for dependency trees, doing F1 and labeled attachment scoring. The included usage message gives a detailed description of how to use the tool.

Usage notes

The current version of the parser requires Java 8 or later. (You can also download an old version of the parser, version 1.4, which runs under JDK 1.4, version 2.0 which runs under JDK 1.5, version 3.4.1 which runs under JDK 1.6, but those distributions are no longer supported.) The parser also requires a reasonable amount of memory (at least 100MB to run as a PCFG parser on sentences up to 40 words in length; typically around 500MB of memory to be able to parse similarly long typical-of-newswire sentences using the factored model).

The parser is available for download, licensed under the GNU General Public License (v2 or later). Source is included. The package includes components for command-line invocation, a Java parsing GUI, and a Java API.

The download is a 261 MB zipped file (mainly consisting of included grammar data files). If you unpack the zip file, you should have everything needed. Simple scripts are included to invoke the parser on a Unix or Windows system. For another system, you merely need to similarly configure the classpath.


The parser code is dual licensed (in a similar manner to MySQL, etc.). Open source licensing is under the full GPL, which allows many free uses. For distributors of proprietary software, commercial licensing is available. (Fine print: The traditional (dynamic programmed) Stanford Parser does part-of-speech tagging as it works, but the newer constituency and neural network dependency shift-reduce parsers require pre-tagged input. For convenience, we include the part-of-speech tagger code, but not models with the parser download. However, if you want to use these parsers under a commercial license, then you need a license to both the Stanford Parser and the Stanford POS tagger. Or you can get the whole bundle of Stanford CoreNLP.) If you don't need a commercial license, but would like to support maintenance of these tools, we welcome gift funding: use this form and write "Stanford NLP Group open source software" in the Special Instructions.

Citing the Stanford Parser

The main technical ideas behind how these parsers work appear in these papers. Feel free to cite one or more of the following papers or people depending on what you are using. Since the parser is regularly updated, we appreciate it if papers with numerical results reflecting parser performance mention the version of the parser being used!

For the neural-network dependency parser:
Danqi Chen and Christopher D Manning. 2014. A Fast and Accurate Dependency Parser using Neural Networks. Proceedings of EMNLP 2014
For the Compositional Vector Grammar parser (starting at version 3.2):
Richard Socher, John Bauer, Christopher D. Manning and Andrew Y. Ng. 2013. Parsing With Compositional Vector Grammars. Proceedings of ACL 2013
For the Shift-Reduce Constituency parser (starting at version 3.2):
This parser was written by John Bauer. You can thank him and cite the web page describing it: . You can also cite the original research papers of others mentioned on that page.
For the PCFG parser (which also does POS tagging):
Dan Klein and Christopher D. Manning. 2003. Accurate Unlexicalized Parsing. Proceedings of the 41st Meeting of the Association for Computational Linguistics, pp. 423-430.
For the factored parser (which also does POS tagging):
Dan Klein and Christopher D. Manning. 2003. Fast Exact Inference with a Factored Model for Natural Language Parsing. In Advances in Neural Information Processing Systems 15 (NIPS 2002), Cambridge, MA: MIT Press, pp. 3-10.
For the Universal Dependencies representation:
Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg, Jan Hajič, Christopher D. Manning, Ryan McDonald, Slav Petrov, Sampo Pyysalo, Natalia Silveira, Reut Tsarfaty, and Daniel Zeman. 2016. Universal Dependencies v1: A Multilingual Treebank Collection. In LREC 2016.
For the English Universal Dependencies converter and the enhanced English Universal Dependencies representation:
Sebastian Schuster and Christopher D. Manning. 2016. Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks. In LREC 2016.
For the (English) Stanford Dependencies representation:
Marie-Catherine de Marneffe, Bill MacCartney and Christopher D. Manning. 2006. Generating Typed Dependency Parses from Phrase Structure Parses. In LREC 2006.
For the German parser:
Anna Rafferty and Christopher D. Manning. 2008. Parsing Three German Treebanks: Lexicalized and Unlexicalized Baselines. In ACL Workshop on Parsing German.
For the Chinese Parser:
Roger Levy and Christopher D. Manning. 2003. Is it harder to parse Chinese, or the Chinese Treebank?ACL 2003, pp. 439-446.
For the Chinese Stanford Dependencies:
Pi-Chuan Chang, Huihsin Tseng, Dan Jurafsky, and Christopher D. Manning. 2009. Discriminative Reordering with Chinese Grammatical Relations Features. In Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation.
For the Arabic parser:
Spence Green and Christopher D. Manning. 2010. Better Arabic Parsing: Baselines, Evaluations, and Analysis. In COLING 2010.
For the French parser:
Spence Green, Marie-Catherine de Marneffe, John Bauer, and Christopher D. Manning. 2010. Multiword Expression Identification with Tree Substitution Grammars: A Parsing tour de force with French.. In EMNLP 2011.
For the Spanish parser:
Most of the work on Spanish was by Jon Gauthier. There is no published paper, but you can thank him and/or cite this webpage:

Questions about the parser?

  1. If you're new to parsing, you can start by running the GUI to try out the parser. Scripts are included for linux ( and Windows (lexparser-gui.bat).
  2. Take a look at the Javadoc package documentation and class documentation. (Point your web browser at the file in the included directory and navigate to those items.)
  3. Look at the parser FAQ for answers to common questions.
  4. If none of that helps, please see our email guidelines for instructions on how to reach us for further assistance.


Extensions: Packages by others using the parser


  • tydevi Typed Dependency Viewer that makes a picture of the Stanford Dependencies analysis of a sentence. By Bernard Bou.
  • DependenSee A Dependency Parse Visualisation Tool that makes pictures of Stanford Dependency output. By Awais Athar. (GitHub)
  • GATE plug-in. By the GATE Team (esp. Adam Funk).
  • GrammarScope grammatical relation browser. GUI, especially focusing on grammatical relations (typed dependencies), including an editor. By Bernard Bou.


  • PHP-Stanford-NLP. Supports POS Tagger, NER, Parser. By Anthony Gentile (agentile).



.NET / F# / C#


  • If you use Homebrew, you can install the Stanford Parser with:

Release history

Version 4.2.02020-11-17Retrain English models with treebank fixesarabic  chinese  english  french  german  spanish
Version 4.0.02020-05-22Model tokenization updated to UDv2.0arabic  chinese  english  french  german  spanish
Version 3.9.22018-10-17Updated for compatibilityarabic  chinese  english  french  german  spanish
Version 3.9.12018-02-27new French and Spanish UD models, misc. UD enhancements, bug fixesarabic  chinese  english  french  german  spanish
Version 3.8.02017-06-09Updated for compatibilityarabic  chinese  english  french  german  spanish
Version 3.7.02016-10-31new UD modelsarabic  chinese  english  french  german  spanish
Version 3.6.02015-12-09Updated for compatibilitychinese  english  french  german  spanish
Version 3.5.22015-04-20Switch to universal dependenciesshift reduce parser models
Version 3.5.12015-01-29Dependency parser fixes and model improvementsshift reduce parser models
Version 3.5.02014-10-31Upgrade to Java 8; add neural-network dependency parsershift reduce parser models
Version 3.4.12014-08-27Add Spanish modelsshift reduce parser models
Version 3.42014-06-16Shift-reduce parser, dependency improvements, French parser uses CC tagsetshift reduce parser models
Version 3.3.12014-01-04English dependency "infmod" and "partmod" combined into "vmod", other minor dependency improvements
Version 3.3.02013-11-12English dependency "attr" removed, other dependency improvements, imperative training data added
Version 3.2.02013-06-20New CVG based English model with higher accuracy
Version 2.0.52013-04-05Dependency improvements, -nthreads option, ctb7 model
Version 2.0.42012-11-12Improved dependency code extraction efficiency, other dependency changes
Version 2.0.32012-07-09Minor bug fixes
Version 2.0.22012-05-22Some models now support training with extra tagged, non-tree data
Version 2.0.12012-03-09Caseless English model included, bugfix for enforced tags
Version 2.02012-02-03Threadsafe!
Version 1.6.92011-09-14Improved recognition of imperatives, dependencies now explicitely include a root, parser knows osprey is a noun
Version 1.6.82011-06-19New French model, improved foreign language models, bug fixes
Version 1.6.72011-05-18Minor bug fixes.
Version 1.6.62011-04-20Internal code and API changes (ArrayLists rather than Sentence; use of CoreLabel objects) to match tagger and CoreNLP.
Version 1.6.52010-11-30Further improvements to English Stanford Dependencies and other minor changes
Version 1.6.42010-08-20More minor bug fixes and improvements to English Stanford Dependencies and question parsing
Version 1.6.32010-07-09Improvements to English Stanford Dependencies and question parsing, minor bug fixes
Version 1.6.22010-02-26Improvements to Arabic parser models, and to English and Chinese Stanford Dependencies
Version 1.6.12008-10-26Slightly improved Arabic and German parsing, and Stanford Dependencies
Version 1.62007-08-19Added Arabic, k-best PCCFG parsing; improved English grammatical relations
Version 1.5.12006-06-11Improved English and Chinese grammatical relations; fixed UTF-8 handling
Version 1.52005-07-21Added grammatical relations output; fixed bugs introduced in 1.4
Version 1.42004-03-24Made PCFG faster again (by FSA minimization); added German support
Version 1.32003-09-06Made parser over twice as fast; added tokenization options
Version 1.22003-07-20Halved PCFG memory usage; added support for Chinese
Version 1.12003-03-25Improved parsing speed; included GUI, improved PCFG grammar
Version 1.02002-12-05Initial release

Sample input and output

The parser can read various forms of plain text input and can output various analysis formats, including part-of-speech tagged text, phrase structure trees, and a grammatical relations (typed dependency) format. For example, consider the text:

The following output shows part-of-speech tagged text, then a context-free phrase structure grammar representation, and finally a typed dependency representation. All of these are different views of the output of the parser.

The/DT strongest/JJS rain/NN ever/RB recorded/VBN in/IN India/NNP shut/VBD down/RP the/DT financial/JJ hub/NN of/IN Mumbai/NNP ,/, snapped/VBD communication/NN lines/NNS ,/, closed/VBD airports/NNS and/CC forced/VBD thousands/NNS of/IN people/NNS to/TO sleep/VB in/IN their/PRP$ offices/NNS or/CC walk/VB home/NN during/IN the/DT night/NN ,/, officials/NNS said/VBD today/NN ./. .))) det(rain-3, The-1) amod(rain-3, strongest-2) nsubj(shut-8, rain-3) nsubj(snapped-16, rain-3) nsubj(closed-20, rain-3) nsubj(forced-23, rain-3) advmod(recorded-5, ever-4) partmod(rain-3, recorded-5) prep_in(recorded-5, India-7) ccomp(said-40, shut-8) prt(shut-8, down-9) det(hub-12, the-10) amod(hub-12, financial-11) dobj(shut-8, hub-12) prep_of(hub-12, Mumbai-14) conj_and(shut-8, snapped-16) ccomp(said-40, snapped-16) nn(lines-18, communication-17) dobj(snapped-16, lines-18) conj_and(shut-8, closed-20) ccomp(said-40, closed-20) dobj(closed-20, airports-21) conj_and(shut-8, forced-23) ccomp(said-40, forced-23) dobj(forced-23, thousands-24) prep_of(thousands-24, people-26) aux(sleep-28, to-27) xcomp(forced-23, sleep-28) poss(offices-31, their-30) prep_in(sleep-28, offices-31) xcomp(forced-23, walk-33) conj_or(sleep-28, walk-33) dobj(walk-33, home-34) det(night-37, the-36) prep_during(walk-33, night-37) nsubj(said-40, officials-39) root(ROOT-0, said-40) tmod(said-40, today-41)

This output was generated with the command:

  1. Big jim quiver
  2. Amazon dubai delivery
  3. Stratham nh bmw
  4. Rigid body blender

Dependency Parsing

Table of contents


Provides a fast syntactic dependency parser. We generate three dependency-based outputs, as follows: basic, uncollapsed dependencies, saved in BasicDependenciesAnnotation; enhanced dependencies saved in EnhancedDependenciesAnnotation; and enhanced++ dependencies in EnhancedPlusPlusDependenciesAnnotation. Most users of our parser will prefer the latter representation.

This is a separate annotator for a direct dependency parser. These parsers require prior part-of-speech tagging. If you need constituency parses then you should look at the annotator.

Property nameAnnotator class nameGenerated Annotation
depparseDependencyParseAnnotatorBasicDependenciesAnnotation, EnhancedDependenciesAnnotation, EnhancedPlusPlusDependenciesAnnotation


Option nameTypeDefaultDescription
depparse.modelfile, classpath, or URLedu/stanford/nlp/models/parser/nndep/english_UD.gzDependency parsing model to use. There is no need to explicitly set this option, unless you want to use a different parsing model than the default. By default, this is set to the UD parsing model included in the stanford-corenlp-models JAR file.

Training a model

Here is an example command for training your own model. In this example we will train a French dependency parser.

  • UD train/dev/test data for a variety of languages can be found here
  • There are many places to find word embedding data, in this example Facebook fastText embeddings are being used, they are found here
  • Note that you need a tokenizer for your language that matches the tokenization of the UD training files, you may have to reprocess the files to match the tokenizing you plan to use
  • Likewise, if you use the setting, you will have to have POS tags that match the UD training data
  • The amount of RAM necessary to train the model may vary depending on various factors

More information

For details about the dependency software, see this page. For more details about dependency parsing in general, see this page.

Copyright © 2020 Stanford NLP Group.

What is Dependency Parsing and Parts of Speech Tag visualization using spaCy

Minimum-Spanning Tree Parser

The future of MSTParser

A SourceForge project has been started by Jason Baldrige and Ryan McDonald to make it easier to add new features to the parser. A new version of the parser will be available soon from that site.

MSTParser (v0.2)

This is the parser described in the following papers:

  1. Multilingual Dependency Parsing with a Two-Stage Discriminative Parser
    R. McDonald, K. Lerman, and F. Pereira
    Tenth Conference on Computational Natural Language Learning (CoNLL-X)    (2006)
  2. Online Learning of Approximate Dependency Parsing Algorithms
    R. McDonald and F. Pereira
    11th Conference of the European Chapter of the Association for Computational Linguistics: EACL 2006  81-88  (2006)
  3. Non-projective Dependency Parsing using Spanning Tree Algorithms
    R. McDonald, F. Pereira, K. Ribarov, and J. Haji\v{c}
    Proceedings of HLT/EMNLP 2005    (2005)
  4. Online Large-Margin Training of Dependency Parsers
    R. McDonald, K. Crammer, and F. Pereira
    43rd Annual Meeting of the Association for Computational Linguistics (ACL 2005)    (2005)

The parser is implemented in Java. The README file describes usage, input and output formats.

Version history

Version 0.2
uses second-order edge features (see reference 4 above).
Version 0.1
has the ability to produce typed (or labeled) trees.



  • What character encoding does the parser use?
    It is hard coded for Unicode (UTF8) in correspondence with theCoNLL-X shared task. You cangrep "UTF8" and replace all occurances with whatever encoding you want.
  • Can the parser use CoNLL-X input format?
    Not yet. However, I have include some easy to use python scripts to convertbetween CoNLL and MSTParser formats. They are in the scripts directory.
  • Can the parser produce non-tree dependency graphs?
    Not yet. This will be part of the next release.
  • Is the edge labeler any good?
    This is somewhat complicated. The parser currently jointly predicts dependenciesand labels at once. This is nice since it allows the information from bothdecisions to simultaneously be used. However, the labeler is forced to obeyany locality constraints of the dependency parser (single edge or pairs of edges).I have found that it is often better to have a post-processing edge labeler thatcan have a larger scope for features. It is not difficult to create this andany classifier can be used. I suggest MALLET.I will make a post-processing labeler available in the next version.


Research supported by the National Science Foundation under grants EIA-0205448 (Mining the Bibliome) and IIS 0428193(Machine Learning for Sequences and Structured Data).


Parsing online dependency

Dependency parsing

Dependency parsing is the task of extracting a dependency parse of a sentence that represents its grammatical structure and defines the relationships between “head” words and words, which modify those heads.


Relations among the words are illustrated above the sentence with directed, labeled arcs from heads to dependents (+ indicates the dependent).

Penn Treebank

Models are evaluated on the Stanford Dependency conversion (v3.3.0) of the Penn Treebank with predicted POS-tags. Punctuation symbols are excluded from the evaluation. Evaluation metrics are unlabeled attachment score (UAS) and labeled attachment score (LAS). UAS does not consider the semantic relation (e.g. Subj) used to label the attachment between the head and the child, while LAS requires a semantic correct label for each attachment.Here, we also mention the predicted POS tagging accuracy.

ModelPOSUASLASPaper / SourceCode
Label Attention Layer + HPSG + XLNet (Mrini et al., 2019)97.397.4296.26Rethinking Self-Attention: Towards Interpretability for Neural ParsingOfficial
ACE + fine-tune (Wang et al., 2020)-97.2095.80Automated Concatenation of Embeddings for Structured PredictionOfficial
HPSG Parser (Joint) + XLNet (Zhou et al, 2020)97.397.2095.72Head-Driven Phrase Structure Grammar Parsing on Penn TreebankOfficial
Second-Order MFVI + BERT (Wang et al., 2020)-96.9195.34Second-Order Neural Dependency Parsing with Message Passing and End-to-End TrainingOfficial
CVT + Multi-Task (Clark et al., 2018)97.7496.6195.02Semi-Supervised Sequence Modeling with Cross-View TrainingOfficial
CRF Parser (Zhang et al., 2020)-96.1494.49Efficient Second-Order TreeCRF for Neural Dependency ParsingOfficial
Second-Order MFVI (Wang et al., 2020)-96.1294.47Second-Order Neural Dependency Parsing with Message Passing and End-to-End TrainingOfficial
Left-to-Right Pointer Network (Fernández-González and Gómez-Rodríguez, 2019)97.396.0494.43Left-to-Right Dependency Parsing with Pointer NetworksOfficial
Graph-based parser with GNNs (Ji et al., 2019)97.395.9794.31Graph-based Dependency Parsing with Graph Neural Networks
Deep Biaffine (Dozat and Manning, 2017)97.395.7494.08Deep Biaffine Attention for Neural Dependency ParsingOfficial
jPTDP (Nguyen and Verspoor, 2018)97.9794.5192.87An improved neural network model for joint POS tagging and dependency parsingOfficial
Andor et al. (2016)97.4494.6192.79Globally Normalized Transition-Based Neural Networks
Distilled neural FOG (Kuncoro et al., 2016)97.394.2692.06Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
Distilled transition-based parser (Liu et al., 2018)97.394.0592.14Distilling Knowledge for Search-based Structured PredictionOfficial
Weiss et al. (2015)97.4493.9992.05Structured Training for Neural Network Transition-Based Parsing
BIST transition-based parser (Kiperwasser and Goldberg, 2016)97.393.991.9Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature RepresentationsOfficial
Arc-hybrid (Ballesteros et al., 2016)97.393.5691.42Training with Exploration Improves a Greedy Stack-LSTM Parser
BIST graph-based parser (Kiperwasser and Goldberg, 2016)97.393.191.0Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature RepresentationsOfficial

Universal Dependencies

The focus of the task is learning syntactic dependency parsers that can work in a real-world setting, starting from raw text, and that can work over many typologically different languages, even low-resource languages for which there is little or no training data, by exploiting a common syntactic annotation standard. This task has been made possible by the Universal Dependencies initiative (UD,, which has developed treebanks for 60+ languages with cross-linguistically consistent annotation and recoverability of the original raw texts.

Participating systems will have to find labeled syntactic dependencies between words, i.e. a syntactic head for each word, and a label classifying the type of the dependency relation. In addition to syntactic dependencies, prediction of morphology and lemmatization will be evaluated. There will be multiple test sets in various languages but all data sets will adhere to the common annotation style of UD. Participants will be asked to parse raw text where no gold-standard pre-processing (tokenization, lemmas, morphology) is available. Data preprocessed by a baseline system (UDPipe, was provided so that the participants could focus on improving just one part of the processing pipeline. The organizers believed that this made the task reasonably accessible for everyone.

The following results are just for references:

Cross-lingual zero-shot parsing is the task of inferring the dependency parse of sentences from one language without any labeled training trees for that language.

Universal Dependency Treebank

Models are evaluated against the Universal Dependency Treebank v2.0. For each of the 6 target languages, models can use the trees of all other languages and English and are evaluated by the UAS and LAS on the target. The final score is the average score across the 6 target languages. The most common evaluation setup is to use gold POS-tags.

Unsupervised dependency parsing is the task of inferring the dependency parse of sentences without any labeled training data.

Penn Treebank

As with supervised parsing, models are evaluated against the Penn Treebank. The most common evaluation setup is to use gold POS-tags as input and to evaluate systems using the unlabeled attachment score (also called ‘directed dependency accuracy’).

Go back to the README

20 - 2 The Dependency Parsing Problem (Part 1)

Stanford NLP: dependency tree results different between online and offline versions

I wanted to parse the following example using the Stanford Core NLP suite using the dependency parser:

I have parsed this sentence using the:

The online generated result is correct while the other one is not.

Can anybody help me understand why are the results different considering also that the online version is as old as 2016 and the downloaded version is since 2020? I would like to have the same results using the downloaded version as with the online version.

Can anybody help me understand the difference?


I have also tried using the version of core nlp - received the same result.

I have also copied the English model inside the folder with no difference.

asked Aug 3 '20 at 16:01

Jacob KriegJacob Krieg

2,5941010 gold badges6363 silver badges117117 bronze badges


You will also be interested:

Well, it's hard to compare. They are completely different. But this evening is special for me. For me too - answered Mikhail.

194 195 196 197 198