Parsing/uuparser

From Nordic Language Processing Laboratory
Revision as of 12:22, 20 December 2018 by Nivre (talk | contribs) (Predicting with a pre-trained parsing model)
Jump to: navigation, search

The Uppsala Parser

The Uppsala Parser is a neural transition-based dependency parser based on bist-parser by Eli Kiperwasser and Yoav Goldberg and developed primarily in the context of the CoNLL shared tasks on universal dependency parsing in 2017 and 2018. The Uppsala Parser is publicly available at https://github.com/UppsalaNLP/uuparser. Note that the version installed here may exhibit some slight differences, designed to improve ease of use.

Using the Uppsala Parser on Abel

  • Log into Abel
  • Activate the NLPL module repository:
module use -a /projects/nlpl/software/modulefiles/
  • Load the most recent version of the uuparser module:
module load nlpl-uuparser

Training a parsing model

To train a set of parsing models on treebanks from Universal Dependencies (v2.2 or later):

uuparser --include [languages to include denoted by their treebank id] --outdir my-output-directory

For example:

uuparser --include "sv_talbanken en_partut ru_syntagrus" --outdir ~/experiments

will train separate models on UD Swedish-Talbanken, UD English-ParTUT and UD Russian-SynTagRus and store the results in the experiments folder in your home directory. To train a single multi-treebank model on all training sets, simply add the --multiling flag.

Model selection is included in the training process by default; that is, at each epoch the current model is evaluated on the UD dev data, and at the end of training the best performing model for each language is selected.

Predicting with a pre-trained parsing model

To predict on UD test data with the models trained above:

uuparser --include "sv_talbanken en_partut ru_syntagrus" --outdir ~/experiments --predict

If you trained a single multi-treebank model, the flag --multiling should be added at prediction time too.

Options

The parser has numerous options to allow you to fine-control its behaviour. For a full list, type

uuparser --help | less

We recommend you set the --dynet-mem option to a larger number when running the full training procedure on larger treebanks. Commonly used values are 5000 and 10000 (in MB). Dynet is the neural network library on which the parser is built.

Note that due to random initialization and other non-deterministic elements in the training process, you will not obtain the same results even when training twice under exactly the same circumstances (e.g. languages, number of epochs etc.). To ensure identical results between two runs, we recommend setting the --dynet-seed option to the same value both times (e.g. --dynet-seed 123456789) and adding the --use-default-seed flag. This ensures that Python's random number generator and Dynet both produce the same sequence of random numbers.

Training a multilingual parsing model

Our parser supports multilingual parsing, that is a single parsing model for one or more languages. To train a multilingual model for the three languages in the examples above, we simply add the --multilingual flag when training

uuparser --include "sv en ru" --outdir ~/experiments --multiling --dynet-mem 5000

In this case, instead of creating three separate models in the language-specific subdirectories within ~/experiments, a single model will be created directly in this folder. Predicting on test data is then as easy as:

uuparser --include "sv en ru" --outdir ~/experiments --multiling --dynet-mem 5000 --predict

Note that if you want to have different output directories for training and predicting, the --modeldir option can be specified when predicting to tell the parser where the pre-trained model can be found.

Segmentation

In the above examples, we assume pre-segmented input data already in the CONLL-U format. If your input is raw text, we recommend using UDPipe to segment first. The UDPipe module can be loaded using module load nlpl-udpipe and then run by typing udpipe at the command line, see below.