3 df@sddlmZddZdS)) defaultdictc sdd|jD}dd|jD}d dddddddgt|jt|t|jt|ttx,D]$\}}dj|dj|qjWfdd }fd d }|||||tS)u" This module symmetrisatizes the source-to-target and target-to-source word alignment output and produces, aka. GDFA algorithm (Koehn, 2005). Step 1: Find the intersection of the bidirectional alignment. Step 2: Search for additional neighbor alignment points to be added, given these criteria: (i) neighbor alignments points are not in the intersection and (ii) neighbor alignments are in the union. Step 3: Add all other alignment points that are not in the intersection, not in the neighboring alignments that met the criteria but in the original forward/backward alignment outputs. >>> forw = ('0-0 2-1 9-2 21-3 10-4 7-5 11-6 9-7 12-8 1-9 3-10 ' ... '4-11 17-12 17-13 25-14 13-15 24-16 11-17 28-18') >>> back = ('0-0 1-9 2-9 3-10 4-11 5-12 6-6 7-5 8-6 9-7 10-4 ' ... '11-6 12-8 13-12 15-12 17-13 18-13 19-12 20-13 ' ... '21-3 22-12 23-14 24-17 25-15 26-17 27-18 28-18') >>> srctext = ("この よう な ハロー 白色 わい 星 の Ｌ 関数 " ... "は Ｌ と 共 に 不連続 に 増加 する こと が " ... "期待 さ れる こと を 示し た 。") >>> trgtext = ("Therefore , we expect that the luminosity function " ... "of such halo white dwarfs increases discontinuously " ... "with the luminosity .") >>> srclen = len(srctext.split()) >>> trglen = len(trgtext.split()) >>> >>> gdfa = grow_diag_final_and(srclen, trglen, forw, back) >>> gdfa == sorted(set([(28, 18), (6, 6), (24, 17), (2, 1), (15, 12), (13, 12), ... (2, 9), (3, 10), (26, 17), (25, 15), (8, 6), (9, 7), (20, ... 13), (18, 13), (0, 0), (10, 4), (13, 15), (23, 14), (7, 5), ... (25, 14), (1, 9), (17, 13), (4, 11), (11, 17), (9, 2), (22, ... 12), (27, 18), (24, 16), (21, 3), (19, 12), (17, 12), (5, ... 12), (11, 6), (12, 8)])) True References: Koehn, P., A. Axelrod, A. Birch, C. Callison, M. Osborne, and D. Talbot. 2005. Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation. In MT Eval Workshop. :type srclen: int :param srclen: the number of tokens in the source language :type trglen: int :param trglen: the number of tokens in the target language :type e2f: str :param e2f: the forward word alignment outputs from source-to-target language (in pharaoh output format) :type f2e: str :param f2e: the backward word alignment outputs from target-to-source language (in pharaoh output format) :rtype: set(tuple(int)) :return: the symmetrized alignment points from the GDFA algorithm cSs g|]}ttt|jdqS)-)tuplemapintsplit).0ar 3/tmp/pip-build-v9q4h5k9/nltk/nltk/translate/gdfa.py Esz'grow_diag_final_and..cSs g|]}ttt|jdqS)r)rrrr)rr r r r r Fsrefcstd}x|tkrd}xtD]}xtD]}||fkr6xzD]r}tddt||f|D}|\}}|krL|krL|krLj|dj|dj||d7}d}qLWq6Wq(W|rPqWdS) zz Search for the neighbor points and them to the intersected alignment points if criteria are met. r Tcss|]\}}||VqdS)Nr )rijr r r csz9grow_diag_final_and..grow_diag..rrFN)lenrangerzipadd)Zprev_lenZ no_new_pointsrrZneighbore_newf_new)aligned alignment neighborssrclentrglenunionr r grow_diagRs$    z&grow_diag_final_and..grow_diagcsnxhtD]\}xVtD]J}|kr|kr||fkrj||fdj|dj|qWq WdS)z Adds remaining points that are not in the intersection, not in the neighboring alignments but in the original *e2f* and *f2e* alignments rrN)rr)r rr)rrrrrr r final_andss z&grow_diag_final_and..final_and)r!rr!)rr!)r r)rr r!r!)r!r!r!)r!r r!)r r!)r r )rset intersectionrrrsorted)rrZe2fZf2errrr r )rrrrrrr grow_diag_final_and s:!r%N) collectionsrr%r r r r s