Package edu.stanford.nlp.parser.lexparser

This package contains implementations of three probabilistic parsers for natural language text.

See: Description

Package edu.stanford.nlp.parser.lexparser Description

This package contains implementations of three probabilistic parsers for natural language text. There is an accurate unlexicalized probabilistic context-free grammar (PCFG) parser, a probabilistic lexical dependency parser, and a factored, lexicalized probabilistic context free grammar parser, which does joint inference over the product of the first two parsers. The parser supports various languages and input formats. For English, for most purposes, we now recommend just using the unlexicalized PCFG. With a well-engineered grammar (as supplied for English), it is fast, accurate, requires much less memory, and in many real-world uses, lexical preferences are unavailable or inaccurate across domains or genres and the unlexicalized parser will perform just as well as a lexicalized parser. However, the factored parser will sometimes provide greater accuracy on English through knowledge of lexical dependencies. Moreover, it is considerably better than the PCFG parser alone for most other languages (with less rigid word order), including German, Chinese, and Arabic. The dependency parser can be run alone, but this is usually not useful (its accuracy is much lower). The output of the parser can be presented in various forms, such as just part-of-speech tags, phrase structure trees, or dependencies, and is controlled by options passed to the TreePrint class.


The factored parser and the unlexicalized PCFG parser are described in:

The factored parser uses a product model, where the preferences of an unlexicalized PCFG parser and a lexicalized dependency parser are combined by a third parser, which does exact search using A* outside estimates (which are Viterbi outside scores, precalculated during PCFG and dependency parsing of the sentence).

We have been splitting up the parser into public classes, but some of the internals are still contained in the file

The class LexicalizedParser provides an interface for either training a parser from a treebank, or parsing text using a saved parser. It can be called programmatically, or the commandline main() method supports many options.

The parser has been ported to multiple languages. German, Chinese, and Arabic grammars are included. The first publication below documents the Chinese parser. The German parser was developed for and used in the second paper (but the paper contains very little detail on it).

The grammatical relations output of the parser is presented in:

End user usage


You need Java 1.6+ installed on your system, and java in your PATH where commands are looked for.

You need a machine with a fair amount of memory. Required memory depends on the choice of parser, the size of the grammar, and other factors like the presence of numerous unknown words To run the PCFG parser on sentences of up to 40 words you need 100 MB of memory. To be able to handle longer sentences, you need more (to parse sentences up to 100 words, you need 400 MB). For running the Factored Parser, 600 MB is needed for dealing with sentences up to 40 words. Factored parsing of sentences up to 200 words requires around 3GB of memory. Training a new lexicalized parser requires about 1500m of memory; much less is needed for training a PCFG.

For just parsing text, you need a saved parser model (grammars, lexicon, etc.), which can be represented either as a text file or as a binary (Java serialized object) representation, and which can be gzip compressed. A number are provided contained in the supplied stanford-parser-$VERSION-models.jar file in the distributed version, and can be accessed from there by having this jar file on your CLASSPATH and specifying them via a classpath entry such as: edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz. (Stanford NLP people can also find the grammars in the directory /u/nlp/data/lexparser.) Other available grammars include englishFactored.ser.gz for English, and chineseFactored.ser.gz for Chinese.

You need the parser code and grammars accessible. This can be done by having the supplied jar files on your CLASSPATH. The examples below assume you are in the parser distribution home directory. From there you can set up the classpath with the command-line argument -cp "*" (or perhaps -cp "*;" on certain versions of Windows). Then if you have some sentences in testsent.txt (as plain text), the following commands should work.

Command-line parsing usage

Parsing a local text file:

java -mx100m -cp "*" edu.stanford.nlp.parser.lexparser.LexicalizedParser edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz testsent.txt

Parsing a document over the web:

java -mx100m -cp "*" edu.stanford.nlp.parser.lexparser.LexicalizedParser -maxLength 40 edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz

Note the -maxLength flag: this will set a maximum length sentence to parse. If you do not set one, the parser will try to parse sentences up to any length, but will usually run out of memory when trying to do this. This is important with web pages with text that may not be real sentences (or just with technical documents that turn out to have 300 word sentences). The parser just does very rudimentary stripping of HTML tags, and so it'll work okay on plain text web pages, but it won't work adequately on most complex commercial script-driven pages. If you want to handle these, you'll need to provide your own preprocessor, and then to call the parser on its output.

The parser will send parse trees to stdout and other information on what it is doing to stderr, so one commonly wants to direct just stdout to an output file, in the standard way.

Other languages: Chinese

Parsing a Chinese sentence (in the default input encoding for Chinese of GB18030 - note you'll need the right fonts to see the output correctly):

java -mx100m -cp "*" edu.stanford.nlp.parser.lexparser.LexicalizedParser -tLPP edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams edu/stanford/nlp/models/lexparser/chinesePCFG.ser.gz chinese-onesent

or for Unicode (UTF-8) format files:

java -mx100m -cp "*"edu.stanford.nlp.parser.lexparser.LexicalizedParser -tLPP edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams -encoding UTF-8 edu/stanford/nlp/models/lexparser/chinesePCFG.ser.gz chinese-onesent-utf

For Chinese, the package includes two simple word segmenters. One is a lexicon-based maximum match segmenter, and the other uses the parser to do Hidden Markov Model-based word segmentation. These segmentation methods are okay, but if you would like a high quality segmentation of Chinese text, you will have to segment the Chinese by yourself as a preprocessing step. The supplied grammars assume that Chinese input has already been word-segmented according to Penn Chinese Treebank conventions. Choosing Chinese with -tLPP edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams makes space-separated words the default tokenization. To do word segmentation within the parser, give one of the options -segmentMarkov or -segmentMaxMatch.

Other languages

The parser also supports other languages including German and French.

Command-line options

The program has many options. The most useful end-user option is -maxLength n which determines the maximum length sentence that the parser will parser. Longer sentences are skipped, with a message printed to stderr.

Input formatting and tokenization options

The parser supports many different input formats: tokenized/not, sentences/not, and tagged/not.

The input may be tokenized or not, and users may supply their own tokenizers. The input is by default assumed to not be tokenized; if the input is tokenized, supply the option -tokenized. If the input is not tokenized, you may supply the name of a tokenizer class with -tokenizer tokenizerClassName; otherwise the default tokenizer (edu.stanford.nlp.processor.PTBTokenizer) is used. This tokenizer should perform well over typical plain newswire-style text.

The input may have already been split into sentences or not. The input is by default assumed to be not split; if sentences are split, supply the option -sentences delimitingToken, where the delimiting token may be any string. As a special case, if the delimiting token is "newline" the parser will assume that each line of the file is a sentence.

Simple XML can also be parsed. The main method does not incorporate an XML parser, but one can fake certain simple cases with the -parseInside regex which will only parse the tokens inside elements matched by the regular expression regex. These elements are assumed to be pure CDATA. If you use -parseInside s, then the parser will accept input in which sentences are marked XML-style with <s> ... </s> (the same format as the input to Eugene Charniak's parser).

Finally, the input may be tagged or not. If it is tagged, the program assumes that words and tags are separated by a non-whitespace separating character such as '/' or '_'. You give the option -tagSeparator tagSeparator to specify tagged text with a tag separator. You also need to tell the parser to use a different tokenizer, using the flags -tokenizerFactory edu.stanford.nlp.process.WhitespaceTokenizer -tokenizerMethod newCoreLabelTokenizerFactory

You can see examples of many of these options in the test directory. As an example, you can parse the example file with partial POS-tagging with this command:

java edu.stanford.nlp.parser.lexparser.LexicalizedParser -maxLength 20 -sentences newline -tokenized -tagSeparator / -tokenizerFactory edu.stanford.nlp.process.WhitespaceTokenizer -tokenizerMethod newCoreLabelTokenizerFactory englishPCFG.ser.gz pos-sentences.txt

There are some restrictions on the interpretation of POS-tagged input:

For the examples in pos-sentences.txt:

  1. This sentence is parsed correctly with no tags given.
  2. So it is also parsed correctly telling the parser butter is a verb.
  3. You get a different worse parse telling it butter is a noun.
  4. You get the same parse as 1. with all tags correctly supplied.
  5. It won't accept can as a VB, but does accept butter as a noun, so you get the same parse as 3.
  6. People can butter can be an NP.
  7. Most words can be NN, but not common function words like their, with, a.

Note that if the program is reading tags correctly, they aren't printed in the sentence it says it is parsing. Only the words are printed there.

Output formatting options

You can set how sentences are printed out by using the -outputFormat format option. The native and default format is as trees are formatted in the Penn Treebank, but there are a number of other useful options:

You can get each sentence printed in multiple formats by giving a comma-separated list of formats. See the TreePrint class for more information on available output formats and options.

Programmatic usage

LexicalizedParser can be easily called within a larger application. It implements a couple of useful interfaces that provide for simple use: edu.stanford.nlp.parser.ViterbiParser and edu.stanford.nlp.process.Function. The following simple class shows typical usage:

import java.util.*;
import edu.stanford.nlp.ling.*;
import edu.stanford.nlp.trees.*;
import edu.stanford.nlp.parser.lexparser.LexicalizedParser;

class ParserDemo {
  public static void main(String[] args) {
    LexicalizedParser lp = LexicalizedParser.loadModel("edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz");
    lp.setOptionFlags(new String[]{"-maxLength", "80", "-retainTmpSubcategories"});

    String[] sent = { "This", "is", "an", "easy", "sentence", "." };
    List<CoreLabel> rawWords = Sentence.toCoreLabelList(sent);
    Tree parse = lp.apply(rawWords);

    TreebankLanguagePack tlp = new PennTreebankLanguagePack();
    GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
    GrammaticalStructure gs = gsf.newGrammaticalStructure(parse);
    List<TypedDependency> tdl = gs.typedDependenciesCCprocessed();

    TreePrint tp = new TreePrint("penn,typedDependenciesCollapsed");

In a usage such as this, the parser expects sentences already tokenized according to Penn Treebank conventions. For arbitrary text, prior processing must be done to achieve such tokenization (the main method of LexicalizedParser provides an example of doing this). The example shows how most command-line arguments can also be passed to the parser when called programmatically. Note that using the -retainTmpSubcategories option is necessary to get the best results in the typed dependencies output recognizing temporal noun phrases ("last week", "next February").

Some code fragments which include tokenization using Penn Treebank conventions follows:

import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.objectbank.TokenizerFactory;
import edu.stanford.nlp.process.CoreLabelTokenFactory;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.process.PTBTokenizer;
import edu.stanford.nlp.parser.lexparser.LexicalizedParser;

LexicalizedParser lp = LexicalizedParser.loadModel("englishPCFG.ser.gz");
lp.setOptionFlags(new String[]{"-outputFormat", "penn,typedDependenciesCollapsed", "-retainTmpSubcategories"});
TokenizerFactory<CoreLabel> tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");

public Tree processSentence(String sentence) {
    List<CoreLabel> rawWords = tokenizerFactory.getTokenizer(new StringReader(sentence)).tokenize();
    Tree bestParse = lp.parseTree(rawWords);
    return bestParse;

Writing and reading trained parsers to and from files

A trained parser consists of grammars, a lexicon, and option values. Once a parser has been trained, it may be written to file in one of two formats: binary serialized Java objects or human readable text data. A parser can also be quickly reconstructed (either programmatically or at the command line) from files containing a parser in either of these formats.

The binary serialized Java objects format is created using standard tools provided by the package, and is not text, and not human-readable. To train and then save a parser as a binary serialized objects file, use a command line invocation of the form:

java -mx1500m edu.stanford.nlp.parser.lexparser.LexicalizedParser -train trainFilePath [fileRange] -saveToSerializedFile outputFilePath

The text data format is human readable and modifiable, and consists of four sections, appearing in the following order:

Each section is headed by a line consisting of multiple asterisks (*) and the name of the section. Note that the file format does not support rules of arbitrary arity, only binary and unary rules. To train and then save a parser as a text data file, use a command line invocation of the form:

java -mx1500m edu.stanford.nlp.parser.lexparser.LexicalizedParser -train trainFilePath start stop -saveToTextFile outputFilePath

To parse a file with a saved parser, either in text data or serialized data format, use a command line invocation of the following form:

java -mx500m edu.stanford.nlp.parser.lexparser.LexicalizedParser parserFilePath test.txt

A Note on Text Grammars

If you want to use the text grammars in another parser and duplicate our performance, you will need to know how we handle the POS tagging of rare and unknown words:

For additional information

For more information, you should next look at the Javadocs for the LexicalizedParser class. In particular, the main method of that class documents more precisely a number of the input preprocessing options that were presented chattily above.

Dan Klein, Christopher Manning, Roger Levy, Teg Grenager, Galen Andrew

Stanford NLP Group