def train(self, prefix, e, f): """ Train the giza word alignments on the provided text files. :param prefix: Prefix for where the giza output files will be stored. :type prefix: path+prefix :param e: Path to the "e" file :type e: path :param f: Path to the "f" :type f: path """ GIZA_LOG.info("Starting mgiza training from scratch...") self.tf = GizaFiles(prefix, e, f) GIZA_LOG.info("Converting txt files to SNTS and VCB files...") self.tf.txt_to_snt(ev = Vocab(), fv = Vocab()) # Now, do the aligning... exe = c.getpath('mgiza') if exe is None: raise GizaAlignmentException('Path to mgiza binary not defined.') elif not os.path.exists(exe): raise GizaAlignmentException('Path to mgiza binary "%s" invalid.') elts = [exe, '-o', os.path.join(self.tf.prefix, self.tf.name), '-S', self.tf.e_vcb, '-T', self.tf.f_vcb, '-C', self.tf.ef_snt, '-CoocurrenceFile', self.tf.ef_cooc, '-hmmiterations', '5', '-model4iterations', '0', '-ncpus', '0'] cmd = ' '.join(elts) GIZA_LOG.debug('Command: "{}"'.format(cmd)) p = ProcessCommunicator(elts) status = p.wait() GIZA_LOG.debug("Exit code: {}".format(str(status))) if status != 0: raise GizaAlignmentException("mgiza exited abnormally with a return code of {}".format(str(status))) self.tf.merge_a3() # self.tf.clean() return self.tf.aligned_sents()
def enrich(**kwargs): global classifier if ARG_OUTFILE not in kwargs: ENRICH_LOG.critical("No output file specified.") sys.exit() # ============================================================================= # Set up the alternate classifier path... # ============================================================================= class_path = kwargs.get('class_path') #=========================================================================== # Set up the different arguments... #=========================================================================== inpath = kwargs.get(ARG_INFILE) parse_args = kwargs.get(PARSE_VAR, []) pos_args = kwargs.get(POS_VAR, []) aln_args = kwargs.get(ALN_VAR, []) max_parse_length = kwargs.get('max_parse_length', 10) if not (parse_args or pos_args or aln_args): ENRICH_LOG.warning("No enrichment specified. Basic processing only will be performed.") #=========================================================================== # Sanity check the arguments. #=========================================================================== # Check that alignment is asked for if projection is asked for. if (ARG_POS_PROJ in pos_args or ARG_PARSE_PROJ in parse_args) and (not aln_args): ENRICH_LOG.warn("You have asked for projection methods but have not requested " + \ "alignments to be generated. Projection may fail if alignment not already present in file.") ENRICH_LOG.log(1000, 'Loading input file...') with open(inpath, 'r', encoding='utf-8') as in_f: corp = xigtxml.load(in_f, mode=INCREMENTAL) # ------------------------------------------- # Initialize the English tagger if: # A) "proj" option is selected for pos. # B) "trans" option is given for pos. # C) "heurpos" option is given for alignment. # ------------------------------------------- s = None if ARG_POS_PROJ in pos_args or ARG_POS_TRANS in pos_args or ARG_ALN_HEURPOS in aln_args: ENRICH_LOG.log(1000, 'Initializing tagger...') tagger = c.getpath('stanford_tagger_trans') try: s = StanfordPOSTagger(tagger) except TaggerError as te: ENRICH_LOG.critical(te) sys.exit(2) # ------------------------------------------- # Initialize the parser if: # A) "trans" option is given for parse # B) "proj" option is given for parse. # ------------------------------------------- if ARG_PARSE_TRANS in parse_args or ARG_PARSE_PROJ in parse_args: ENRICH_LOG.log(1000, "Intializing English parser...") sp = stanford_parser.StanfordParser() # ------------------------------------------- # Initialize the classifier if: # A) "class" option is given for pos # B) "heurpos" option is given for alignment. # ------------------------------------------- m = None if ARG_POS_CLASS in pos_args or ARG_ALN_HEURPOS in aln_args: ENRICH_LOG.log(1000, "Initializing gloss-line classifier...") p = load_posdict() m = mallet_maxent.MalletMaxent(classifier) # -- 1b) Giza Gloss to Translation alignment -------------------------------------- if ARG_ALN_GIZA in aln_args or ARG_ALN_GIZAHEUR in aln_args: ENRICH_LOG.log(1000, 'Aligning gloss and translation lines using mgiza++...') try: if ARG_ALN_GIZAHEUR in aln_args: giza_align_t_g(corp, resume=True, use_heur=True, symmetric=kwargs.get(ALN_SYM_VAR, SYMMETRIC_INTERSECT)) if ARG_ALN_GIZA in aln_args: giza_align_t_g(corp, resume=True, use_heur=False, symmetric=kwargs.get(ALN_SYM_VAR, SYMMETRIC_INTERSECT)) except GizaAlignmentException as gae: gl = logging.getLogger('giza') gl.critical(str(gae)) raise gae # ------------------------------------------- # Begin iterating through the corpus # ------------------------------------------- for inst in corp: feedback_string = 'Instance {:15s}: {{:20s}}{{}}'.format(inst.id) reasons = [] inst_status = None def fail(reason): nonlocal inst_status, reasons if reason not in reasons: reasons.append(reason) inst_status = 'WARN' def success(): nonlocal inst_status inst_status = 'OK' # ------------------------------------------- # Define the reasons for failure # ------------------------------------------- F_GLOSS_LINE = "NOGLOSS" F_LANG_LINE = "NOLANG" F_TRANS_LINE = "NOTRANS" F_BAD_LINES = "BADLINES" F_L_G_ALN = "L_G_ALIGN" F_T_G_ALN = "G_T_ALIGN" F_NO_TRANS_POS="NO_POS_TRANS" F_PROJECTION = "PROJECTION" F_UNKNOWN = "UNKNOWN" F_PARSELEN = "OVER_MAX_LENGTH" try: # ------------------------------------------- # Get the different lines # ------------------------------------------- def tryline(func): nonlocal inst try: return func(inst) except NoNormLineException as nnle: return None gl = tryline(gloss_line) tls = tryline(trans_lines) lls = tryline(lang_lines) has_gl = gl is not None has_tl = tls is not None has_ll = lls is not None has_all = lambda: (has_gl and has_tl and has_ll) # ------------------------------------------- # Translation Line # ------------------------------------------- if has_tl: if ARG_POS_PROJ in pos_args or ARG_POS_TRANS in pos_args or ARG_ALN_HEURPOS in aln_args: try: tag_trans_pos(inst, s) except CriticalTaggerError as cte: ENRICH_LOG.critical(str(cte)) sys.exit(2) if ARG_PARSE_PROJ in parse_args or ARG_PARSE_TRANS in parse_args: if len(trans(inst)) <= max_parse_length: parse_translation_line(inst, sp, pt=True, dt=True) else: fail(F_PARSELEN) # 4) POS tag the gloss line -------------------------------------------- if has_gl: if ARG_POS_CLASS in pos_args or ARG_ALN_HEURPOS in aln_args: classify_gloss_pos(inst, m, posdict=p) # ------------------------------------------- # Try getting alignments. # ------------------------------------------- if has_gl and has_ll: try: add_gloss_lang_alignments(inst) except GlossLangAlignException as glae: fail(F_L_G_ALN) if has_gl and has_tl: if ARG_ALN_HEURPOS in aln_args: heur_align_inst(inst, use_pos=True) if ARG_ALN_HEUR in aln_args: heur_align_inst(inst, use_pos=False) # ------------------------------------------- # Now, do the necessary projection tasks. # ------------------------------------------- # Project the classifier tags... if has_ll and has_gl and ARG_POS_CLASS in pos_args: try: project_gloss_pos_to_lang(inst, tag_method=INTENT_POS_CLASS) except GlossLangAlignException: fail(F_L_G_ALN) # ------------------------------------------- # Do the trans-to-lang projection... # ------------------------------------------- if has_all(): proj_aln_method = ALN_ARG_MAP[kwargs.get('proj_aln', ARG_ALN_ANY)] aln = get_trans_gloss_alignment(inst, aln_method=proj_aln_method) if not aln or len(aln) == 0: fail(F_T_G_ALN) else: # ------------------------------------------- # POS Projection # ------------------------------------------- if ARG_POS_PROJ in pos_args: trans_tags = trans_tag_tier(inst) if not trans_tags: fail(F_NO_TRANS_POS) else: project_trans_pos_to_gloss(inst) try: project_gloss_pos_to_lang(inst, tag_method=INTENT_POS_PROJ) except GlossLangAlignException as glae: fail(F_L_G_ALN) # ------------------------------------------- # Parse projection # ------------------------------------------- if ARG_PARSE_PROJ in parse_args: try: project_pt_tier(inst, proj_aln_method=proj_aln_method) except PhraseStructureProjectionException as pspe: fail(F_PROJECTION) except NoAlignmentProvidedError as nape: fail(F_T_G_ALN) try: project_ds_tier(inst, proj_aln_method=proj_aln_method) except ProjectionException as pe: fail(F_PROJECTION) except NoAlignmentProvidedError as nape: fail(F_T_G_ALN) # Sort the tiers... ---------------------------------------------------- inst.sort_tiers() except Exception as e: # ENRICH_LOG.warn("Unknown Error occurred processing instance {}".format(inst.id)) ENRICH_LOG.debug(e) # raise(e) fail(F_UNKNOWN) if not reasons: success() ENRICH_LOG.info(feedback_string.format(inst_status, ','.join(reasons))) ENRICH_LOG.log(1000, 'Writing output file...') if hasattr(kwargs.get(ARG_OUTFILE), 'write'): xigtxml.dump(kwargs.get(ARG_OUTFILE), corp) else: xigtxml.dump(writefile(kwargs.get(ARG_OUTFILE)), corp) ENRICH_LOG.log(1000, 'Done.') ENRICH_LOG.log(1000, "{} instances written.".format(len(corp)))
def resume(self, prefix, new_e, new_f): """ "Force" align a new set of data using the old model, per the instructions at: http://www.kyloo.net/software/doku.php/mgiza:forcealignment """ # First, initialize a new GizaFile container for # the files we are going to create new_gf = GizaFiles(prefix, new_e, new_f) # Now, we're going to extend the old vocabulary files # with the new text to align. old_ev = Vocab.load(self.tf.e_vcb) old_fv = Vocab.load(self.tf.f_vcb) old_ev.add_from_txt(new_gf.e) old_fv.add_from_txt(new_gf.f) # Now that we've extended the vocabs, let's dump the # now-extended vocabs into the new filepaths. old_ev.dump(new_gf.e_vcb) old_fv.dump(new_gf.f_vcb) # Write out new_gf.txt_to_snt(ev = old_ev, fv = old_fv) exe = c.getpath('mgiza') if exe is None: raise GizaAlignmentException('Path to mgiza binary not defined.') elif not os.path.exists(exe): raise GizaAlignmentException('Path to mgiza binary "%s" invalid.' % exe) args = [exe, #self.tf.cfg, '-restart', '2', '-o', os.path.join(new_gf.prefix, new_gf.name), '-m2', '5', '-previoust', self.tf.t, '-previousa', self.tf.a, '-previousn', self.tf.n, '-previousd', self.tf.d3, '-c', new_gf.ef_snt, '-s', new_gf.e_vcb, '-t', new_gf.f_vcb, '-Coocurrencefile', new_gf.ef_cooc] cmd = ' '.join(args) GIZA_LOG.debug('Command: "{}"'.format(cmd)) p = ProcessCommunicator(args) status = p.wait() GIZA_LOG.debug("Exit status {}".format(str(status))) if status != 0: raise GizaAlignmentException("mgiza exited abnormally with a return code of {}".format(str(status))) new_gf.merge_a3() # new_gf.clean() return new_gf.aligned_sents()