o rZh@sddlmZddZdS)) defaultdictcsdd|D}dd|D}gdt|t|t|t|ttD]\}}d|d|q.fdd}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 cS g|] }ttt|dqS-tuplemapintsplit.0arB/var/www/auris/lib/python3.10/site-packages/nltk/translate/gdfa.py E z'grow_diag_final_and..cSrrrr rrrrFr))r)rr)r)rr)rr)rr)rr)rrefcstd}|tkrjd}tD]K}tD]D}||fvr\D]9}tddt||f|D}|\}}|vr[|vr[|vr[|d|d||d7}d}q"qq|rbdS|tks dSdS) zz Search for the neighbor points and them to the intersected alignment points if criteria are met. rTcss|] \}}||VqdS)Nr)r ijrrr csz9grow_diag_final_and..grow_diag..rrFN)lenrangerzipadd)Zprev_lenZ no_new_pointsrrZneighbore_newf_newaligned alignmentZ neighborssrclentrglenunionrr grow_diagRs*      z&grow_diag_final_and..grow_diagcsftD],}tD]%}|vr/|vr/||fvr/||fd|d|q qdS)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)r r!r"r#r$rr final_andss   z&grow_diag_final_and..final_and)r set intersectionr$rrsorted)r"r#Ze2fZf2errr%r&rrrgrow_diag_final_and s: !r*N) collectionsrr*rrrrs