o Ni @sdZddlmZddlmZddlmZddlZddlZddlm Z dZ dZ dZ d Zd Zd Zd Zgd ZddZGddde jjZGddde jjZdS)zwordnet dataset.)absolute_import)division)print_functionNaWordNet Release 3.0 This software and database is being provided to you, the LICENSEE, by Princeton University under the following license. By obtaining, using and/or copying this software and database, you agree that you have read, understood, and will comply with these terms and conditions.: Permission to use, copy, modify and distribute this software and database and its documentation for any purpose and without fee or royalty is hereby granted, provided that you agree to comply with the following copyright notice and statements, including the disclaimer, and that the same appear on ALL copies of the software, database and documentation, including modifications that you make for internal use or for distribution. WordNet 3.0 Copyright 2006 by Princeton University. All rights reserved. THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT- ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS. The name of Princeton University or Princeton may not be used in advertising or publicity pertaining to distribution of the software and/or database. Title to copyright in this software, database and any associated documentation shall at all times remain with Princeton University and LICENSEE agrees to preserve same. a@article{10.1145/219717.219748, author = {Miller, George A.}, title = {WordNet: A Lexical Database for English}, year = {1995}, issue_date = {Nov. 1995}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, volume = {38}, number = {11}, issn = {0001-0782}, url = {https://doi.org/10.1145/219717.219748}, doi = {10.1145/219717.219748}, journal = {Commun. ACM}, month = nov, pages = {39--41}, numpages = {3} } zWordNet is a large lexical database of English. Nouns, verbs, adjectives and adverbs are grouped into sets of cognitive synonyms (synsets), each expressing a distinct concept. Synsets are interlinked by means of conceptual-semantic and lexical relations. a.This WORDNET TENSOR DATA consists of a collection of triplets (synset, relation_type, triplet) extracted from WordNet 3.0 (http://wordnet.princeton.edu). This data set can be seen as a 3-mode tensor depicting ternary relationships between synsets. See https://everest.hds.utc.fr/doku.php?id=en:transe. a.@incollection{NIPS2013_5071, title = {Translating Embeddings for Modeling Multi-relational Data}, author = {Bordes, Antoine and Usunier, Nicolas and Garcia-Duran, Alberto and Weston, Jason and Yakhnenko, Oksana}, booktitle = {Advances in Neural Information Processing Systems 26}, editor = {C. J. C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K. Q. Weinberger}, pages = {2787--2795}, year = {2013}, publisher = {Curran Associates, Inc.}, url = {http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf} } ziSame as WN18 but fixes test leakage through inverse relations. See https://github.com/TimDettmers/ConvE. a~@inproceedings{dettmers2018conve, Author = {Dettmers, Tim and Pasquale, Minervini and Pontus, Stenetorp and Riedel, Sebastian}, Booktitle = {Proceedings of the 32th AAAI Conference on Artificial Intelligence}, Title = {Convolutional 2D Knowledge Graph Embeddings}, Url = {https://arxiv.org/abs/1707.01476}, Year = {2018}, pages = {1811--1818}, Month = {February} } ) _also_see_derivationally_related_form _has_part _hypernym_instance_hypernym_member_meronym_member_of_domain_region_member_of_domain_usage _similar_to_synset_domain_topic_of _verb_groupcCsli}tjj|}|D]}|d\}}}t||d||<q Wdn1s+wYtt|dS)N )name definition) relationssynsets)tfiogfileGFilestripsplitdict _RELATIONS)synset_definitions_pathrfline synset_idrrr!T/home/ubuntu/.local/lib/python3.10/site-packages/tensorflow_datasets/text/wordnet.py_make_wn18_metadata{s r#cs4eZdZdZfddZeddZddZZS) WordnetConfigzConfiguration for `Wordnet`.cs&||_||_tt|j|||ddS)N)r descriptionversion) _citation _path_prefixsuperr$__init__)selfr path_prefixr%citationr& __class__r!r"r*s   zWordnetConfig.__init__cCsdt|jgS)N )join _CITATIONr'r+r!r!r"r-szWordnetConfig.citationcCsD||j}tj||jdtj||jdtj||jdfS)Nz train.txtz valid.txtztest.txt)rospathr1r()r+dl_pathsroot_dirr!r!r" get_pathss zWordnetConfig.get_paths) __name__ __module__ __qualname____doc__r*propertyr-r8 __classcell__r!r!r.r"r$s   r$c @sfeZdZdZedejddee e j ddedde ee j ddgZd d Zd d Zd dZdS)WordnetzBuilder for WordNet dataset.WN18 wordnet-mlj12zwordnet-mlj12-z0.1.0)rr,r%r-r&WN18RRc CsLtjj|ttjtjtjtjdd|jjtj t t ddS)Nlhsrelationrhszhttps://wordnet.princeton.edu/)license)builderr%featureshomepager-metadataredistribution_info) tfdscore DatasetInfo _DESCRIPTIONrJ FeaturesDictTextbuilder_configr- MetadataDictr_LICENSEr3r!r!r"_infosz Wordnet._infocCs|ddd}tj|ddd}|jjt||j |\}}}t j j t j jt|ddt j j t j jt|ddt j j t j jt|ddgS) zReturns SplitGenerators.zJhttps://everest.hds.utc.fr/lib/exe/fetch.php?media=en:wordnet-mlj12.tar.gzz=https://github.com/TimDettmers/ConvE/raw/master/WN18RR.tar.gz)r@rBr@rAzwordnet-mlj12-definitions.txt) triplets_path)r gen_kwargs)download_and_extractr4r5r1inforLupdater#rTr8rNrOSplitGeneratorSplitTRAINr VALIDATIONTEST)r+ dl_managerr6r train_pathval_path test_pathr!r!r"_split_generatorss,zWordnet._split_generatorsccsntjj|%}t|D]\}}|d\}}}||||dfVq WddS1s0wYdS)zYields examples.rrDN)rrrr enumeraterr)r+rXrirrErFrGr!r!r"_generate_exampless"zWordnet._generate_examplesN)r9r:r;r<r$r4r5r1_WN18_DESCRIPTION_WN18_CITATIONrNrOVersion_WN18RR_DESCRIPTION_WN18RR_CITATIONBUILDER_CONFIGSrWrfrir!r!r!r"r?s(    r?)r< __future__rrrr4 tensorflowrtensorflow_datasets.public_api public_apirNrVr2rQrjrkrmrnrr#rO BuilderConfigr$GeneratorBasedBuilderr?r!r!r!r"s$