B `B@sddlmZddlmZddlmZmZejfddZ ddZ dd Z efd d Z efd d Z efddZefddZeefddZeefddZddZejeedddfddZejeedddfddZdS) ) PorterStemmer)wordnet)chainproductcCs0tt||}tt||}||fS)a Takes in string inputs for hypothesis and reference and returns enumerated word lists for each of them :param hypothesis: hypothesis string :type hypothesis: str :param reference: reference string :type reference: str :preprocess: preprocessing method (default str.lower) :type preprocess: method :return: enumerated words list :rtype: list of 2D tuples, list of 2D tuples )list enumeratesplit) hypothesis reference preprocesshypothesis_listreference_listrJ/home/dcms/DCMS/lib/python3.7/site-packages/nltk/translate/meteor_score.py_generate_enumssrcCst||\}}t||S)a matches exact words in hypothesis and reference and returns a word mapping based on the enumerated word id between hypothesis and reference :param hypothesis: hypothesis string :type hypothesis: str :param reference: reference string :type reference: str :return: enumerated matched tuples, enumerated unmatched hypothesis tuples, enumerated unmatched reference tuples :rtype: list of 2D tuples, list of 2D tuples, list of 2D tuples )r _match_enums)r r r r rrr exact_match"srcCsg}xtt|dddD]x}xrtt|dddD]X}||d||dkr8|||d||df||d||dfPq8WqW|||fS)aQ matches exact words in hypothesis and reference and returns a word mapping between enum_hypothesis_list and enum_reference_list based on the enumerated word id. :param enum_hypothesis_list: enumerated hypothesis list :type enum_hypothesis_list: list of tuples :param enum_reference_list: enumerated reference list :type enum_reference_list: list of 2D tuples :return: enumerated matched tuples, enumerated unmatched hypothesis tuples, enumerated unmatched reference tuples :rtype: list of 2D tuples, list of 2D tuples, list of 2D tuples Nr)rangelenappendpop)enum_hypothesis_listenum_reference_list word_matchijrrrr4s rcsfdd|D}fdd|D}t||\}tdkrLttngtdkrhttngttfdd|}ttfdd|}|||fS)a  Stems each word and matches them in hypothesis and reference and returns a word mapping between enum_hypothesis_list and enum_reference_list based on the enumerated word id. The function also returns a enumerated list of unmatched words for hypothesis and reference. :param enum_hypothesis_list: :type enum_hypothesis_list: :param enum_reference_list: :type enum_reference_list: :param stemmer: nltk.stem.api.StemmerI object (default PorterStemmer()) :type stemmer: nltk.stem.api.StemmerI or any class that implements a stem method :return: enumerated matched tuples, enumerated unmatched hypothesis tuples, enumerated unmatched reference tuples :rtype: list of 2D tuples, list of 2D tuples, list of 2D tuples cs"g|]}|d|dfqS)rr)stem).0 word_pair)stemmerrr bsz$_enum_stem_match..cs"g|]}|d|dfqS)rr)r)rr )r!rrr"fsrcs |dkS)Nrr)x)enum_unmat_hypo_listrrvz"_enum_stem_match..cs |dkS)Nrr)r#)enum_unmat_ref_listrrr%zr&)rrrzipfilter)rrr!Zstemmed_enum_list1Zstemmed_enum_list2rr)r$r'r!r_enum_stem_matchNsr*cCst||\}}t|||dS)a[ Stems each word and matches them in hypothesis and reference and returns a word mapping between hypothesis and reference :param hypothesis: :type hypothesis: :param reference: :type reference: :param stemmer: nltk.stem.api.StemmerI object (default PorterStemmer()) :type stemmer: nltk.stem.api.StemmerI or any class that implements a stem method :return: enumerated matched tuples, enumerated unmatched hypothesis tuples, enumerated unmatched reference tuples :rtype: list of 2D tuples, list of 2D tuples, list of 2D tuples )r!)rr*)r r r!rrrrr stem_matchsr+cCsg}xtt|dddD]}ttdd|||dD||dh}xbtt|dddD]H}||d|krl|||d||df||||fPqlWqW|||fS)a Matches each word in reference to a word in hypothesis if any synonym of a hypothesis word is the exact match to the reference word. :param enum_hypothesis_list: enumerated hypothesis list :param enum_reference_list: enumerated reference list :param wordnet: a wordnet corpus reader object (default nltk.corpus.wordnet) :type wordnet: WordNetCorpusReader :return: list of matched tuples, unmatched hypothesis list, unmatched reference list :rtype: list of tuples, list of tuples, list of tuples NrcSsg|]}dd|DqS)cSs&g|]}|ddkr|qS)_r)namefind)rZlemmarrrr"sz5_enum_wordnetsyn_match...)Zlemmas)rZsynsetrrrr"sz*_enum_wordnetsyn_match..rr)rrsetrZsynsetsunionrr)rrrrrZhypothesis_synsrrrr_enum_wordnetsyn_matchs r1cCst||\}}t|||dS)a Matches each word in reference to a word in hypothesis if any synonym of a hypothesis word is the exact match to the reference word. :param hypothesis: hypothesis string :param reference: reference string :param wordnet: a wordnet corpus reader object (default nltk.corpus.wordnet) :type wordnet: WordNetCorpusReader :return: list of mapped tuples :rtype: list of tuples )r)rr1)r r rrrrrrwordnetsyn_matchs r2cCsVt||\}}}t|||d\}}}t|||d\}}}t|||ddd||fS)ap Aligns/matches words in the hypothesis to reference by sequentially applying exact match, stemmed match and wordnet based synonym match. in case there are multiple matches the match which has the least number of crossing is chosen. Takes enumerated list as input instead of string input :param enum_hypothesis_list: enumerated hypothesis list :param enum_reference_list: enumerated reference list :param stemmer: nltk.stem.api.StemmerI object (default PorterStemmer()) :type stemmer: nltk.stem.api.StemmerI or any class that implements a stem method :param wordnet: a wordnet corpus reader object (default nltk.corpus.wordnet) :type wordnet: WordNetCorpusReader :return: sorted list of matched tuples, unmatched hypothesis list, unmatched reference list :rtype: list of tuples, list of tuples, list of tuples )r!)rcSs|dS)Nrr)Zwordpairrrrr%r&z$_enum_allign_words..)key)rr*r1sorted)rrr!rZ exact_matchesZ stem_matchesZ wns_matchesrrr_enum_allign_wordssr5cCst||\}}t||||dS)a Aligns/matches words in the hypothesis to reference by sequentially applying exact match, stemmed match and wordnet based synonym match. In case there are multiple matches the match which has the least number of crossing is chosen. :param hypothesis: hypothesis string :param reference: reference string :param stemmer: nltk.stem.api.StemmerI object (default PorterStemmer()) :type stemmer: nltk.stem.api.StemmerI or any class that implements a stem method :param wordnet: a wordnet corpus reader object (default nltk.corpus.wordnet) :type wordnet: WordNetCorpusReader :return: sorted list of matched tuples, unmatched hypothesis list, unmatched reference list :rtype: list of tuples, list of tuples, list of tuples )r!r)rr5)r r r!rrrrrr allign_wordssr6cCs|d}d}xn|t|dkrv||dd||ddkrd||dd||ddkrd|d7}q |d7}|d7}q W|S)at Counts the fewest possible number of chunks such that matched unigrams of each chunk are adjacent to each other. This is used to caluclate the fragmentation part of the metric. :param matches: list containing a mapping of matched words (output of allign_words) :return: Number of chunks a sentence is divided into post allignment :rtype: int rr)r)matchesrchunksrrr _count_chunks s    r9g?g?cCst|||d\}} t|} t| } t|| |d\} } } t| }yLt|| }t|| }||||d||}tt| }||}Wntk rdSX|||}d||S)aT Calculates METEOR score for single hypothesis and reference as per "Meteor: An Automatic Metric for MT Evaluation with HighLevels of Correlation with Human Judgments" by Alon Lavie and Abhaya Agarwal, in Proceedings of ACL. http://www.cs.cmu.edu/~alavie/METEOR/pdf/Lavie-Agarwal-2007-METEOR.pdf >>> hypothesis1 = 'It is a guide to action which ensures that the military always obeys the commands of the party' >>> reference1 = 'It is a guide to action that ensures that the military will forever heed Party commands' >>> round(single_meteor_score(reference1, hypothesis1),4) 0.7398 If there is no words match during the alignment the method returns the score as 0. We can safely return a zero instead of raising a division by zero error as no match usually implies a bad translation. >>> round(meteor_score('this is a cat', 'non matching hypothesis'),4) 0.0 :param references: reference sentences :type references: list(str) :param hypothesis: a hypothesis sentence :type hypothesis: str :param preprocess: preprocessing function (default str.lower) :type preprocess: method :param stemmer: nltk.stem.api.StemmerI object (default PorterStemmer()) :type stemmer: nltk.stem.api.StemmerI or any class that implements a stem method :param wordnet: a wordnet corpus reader object (default nltk.corpus.wordnet) :type wordnet: WordNetCorpusReader :param alpha: parameter for controlling relative weights of precision and recall. :type alpha: float :param beta: parameter for controlling shape of penalty as a function of as a function of fragmentation. :type beta: float :param gamma: relative weight assigned to fragmentation penality. :type gamma: float :return: The sentence-level METEOR score. :rtype: float )r )r!rg)rrr5floatr9ZeroDivisionError)r r r r!ralphabetagammaZenum_hypothesisZenum_referenceZtranslation_lengthZreference_lengthr7r,Z matches_countZ precisionZrecallZfmeanZ chunk_countZ frag_fracZpenaltyrrrsingle_meteor_score"s 5     r@cs tfdd|DS)a Calculates METEOR score for hypothesis with multiple references as described in "Meteor: An Automatic Metric for MT Evaluation with HighLevels of Correlation with Human Judgments" by Alon Lavie and Abhaya Agarwal, in Proceedings of ACL. http://www.cs.cmu.edu/~alavie/METEOR/pdf/Lavie-Agarwal-2007-METEOR.pdf In case of multiple references the best score is chosen. This method iterates over single_meteor_score and picks the best pair among all the references for a given hypothesis >>> hypothesis1 = 'It is a guide to action which ensures that the military always obeys the commands of the party' >>> hypothesis2 = 'It is to insure the troops forever hearing the activity guidebook that party direct' >>> reference1 = 'It is a guide to action that ensures that the military will forever heed Party commands' >>> reference2 = 'It is the guiding principle which guarantees the military forces always being under the command of the Party' >>> reference3 = 'It is the practical guide for the army always to heed the directions of the party' >>> round(meteor_score([reference1, reference2, reference3], hypothesis1),4) 0.7398 If there is no words match during the alignment the method returns the score as 0. We can safely return a zero instead of raising a division by zero error as no match usually implies a bad translation. >>> round(meteor_score(['this is a cat'], 'non matching hypothesis'),4) 0.0 :param references: reference sentences :type references: list(str) :param hypothesis: a hypothesis sentence :type hypothesis: str :param preprocess: preprocessing function (default str.lower) :type preprocess: method :param stemmer: nltk.stem.api.StemmerI object (default PorterStemmer()) :type stemmer: nltk.stem.api.StemmerI or any class that implements a stem method :param wordnet: a wordnet corpus reader object (default nltk.corpus.wordnet) :type wordnet: WordNetCorpusReader :param alpha: parameter for controlling relative weights of precision and recall. :type alpha: float :param beta: parameter for controlling shape of penalty as a function of as a function of fragmentation. :type beta: float :param gamma: relative weight assigned to fragmentation penality. :type gamma: float :return: The sentence-level METEOR score. :rtype: float c s"g|]}t|dqS))r!rr=r>r?)r@)rr )r=r>r?r r!rrrr"s z meteor_score..)max)Z referencesr r r!rr=r>r?r)r=r>r?r r!rr meteor_scorejs; rBN)Znltk.stem.porterrZ nltk.corpusr itertoolsrrstrlowerrrrr*r+r1r2r5r6r9r@rBrrrr s0  1 & ( C