The techniques behind the parser are described in the paper Easy-First Dependency Parsing with Hierarchical Tree LSTMs. Further materials could be found here.

• Python 2.7 interpreter
• PyCNN library

The software requires having a training.conll and development.conll files formatted according to the CoNLL data format.

To train a parsing model with for either parsing architecture type the following at the command prompt:

python src/parser.py --outdir [results directory] --train training.conll --dev development.conll [--extrn path_to_external_embeddings_file]

We use the same external embedding used in Transition-Based Dependency Parsing with Stack Long Short-Term Memory which can be downloaded from the authors github repository and directly here.

Note 1: The reported test result is the one matching the highest development score.

Note 2: The parser calculates (after each iteration) the accuracies excluding punctuation symbols by running the eval.pl script from the CoNLL-X Shared Task and stores the results in directory specified by the --outdir.

Note 3: The external embeddings parameter is optional and could be omitted.

The command for parsing a test.conll file formatted according to the CoNLL data format with a previously trained model is:

python src/parser.py --predict --outdir [results directory] --test test.conll [--extrn extrn.vectors] --model [trained model file] --params [param file generate during training]

The parser will store the resulting conll file in the out directory (--outdir).

If you make use of this software for research purposes, we'll appreciate citing the following:

@article{DBLP:journals/tacl/KiperwasserG16a,
    author    = {Eliyahu Kiperwasser and
                Yoav Goldberg},
    title     = {Easy-First Dependency Parsing with Hierarchical Tree LSTMs},
    journal   = {{TACL}},
    volume    = {4},
    pages     = {445--461},
    year      = {2016},
    url       = {https://transacl.org/ojs/index.php/tacl/article/view/798},
    timestamp = {Tue, 09 Aug 2016 14:51:09 +0200},
    biburl    = {http://dblp.uni-trier.de/rec/bib/journals/tacl/KiperwasserG16a},
    bibsource = {dblp computer science bibliography, http://dblp.org}
}

This software is released under the terms of the Apache License, Version 2.0.

For questions and usage issues, please contact [email protected]

Eliyahu Kiperwasser

Yoav Goldberg