def evaluate_instance(inst, classifier, tagger): # Get the supervised POS tags... """ :param inst: :type inst: RGIgt :param classifier: MalletMaxent :param tagger: StanfordPOSTagger """ sup_gloss_tier = pos_tag_tier(inst, GLOSS_WORD_ID) # We will incrementally build up the tag sequences... sup_lang_tier = pos_tag_tier(inst, LANG_WORD_ID) sup_tags = [] prj_tags = [] cls_tags = [] # If there are no supervised tags on the gloss line, but there are on the language line... if sup_gloss_tier is None and sup_lang_tier is not None: try: add_gloss_lang_alignments(inst) project_lang_to_gloss(inst) sup_gloss_tier = pos_tag_tier(inst, GLOSS_WORD_ID) except RGXigtException: pass if sup_gloss_tier: # Do the classification classify_gloss_pos(inst, classifier) cls_tier = pos_tag_tier(inst, GLOSS_WORD_ID, tag_method=INTENT_POS_CLASS) for sup_item in sup_gloss_tier: word = xigt_find(inst, id=sup_item.alignment) if not word: continue else: word = word.value() # prj_item = xigt_find(prj_tier, alignment=sup_item.alignment) # if prj_item is None: # prj_tag = 'UNK' # else: # prj_tag = prj_item.value() cls_item = xigt_find(cls_tier, alignment=sup_item.alignment) if cls_item is None: cls_tag = 'UNK' else: cls_tag = cls_item.value() sup_tags.append(POSToken(word, label=sup_item.value())) # prj_tags.append(POSToken(word, label=prj_tag)) cls_tags.append(POSToken(word, label=cls_tag)) return sup_tags, cls_tags
def gather_gloss_pos_stats(inst, subword_dict, feat_list): """ Given an instance, look for the gloss pos tags, and save the statistics about them, so that we can filter by the number of times each kind was seen later. :param inst: Instance to process. :type inst: RGIgt :param subword_dict: This dictionary will record the number of times each (word, TAG) pair has been seen. :type subword_dict: SubwordDict :param gram_tag_dict: This dictionary will record the number of times individual grams are seen. :type gram_tag_dict: TwoLevelCountDict """ # Grab the gloss POS tier... gpos_tier = gloss_tag_tier(inst) lpos_tier = lang_tag_tier(inst) gw_tier = gloss(inst) if CLASS_FEATS_ALN in feat_list: heur_align_inst(inst) get_trans_glosses_alignment(inst, aln_method=INTENT_ALN_HEUR) # If there are POS tags on the language line but not the gloss line... if gpos_tier is None and lpos_tier is not None: add_gloss_lang_alignments(inst) project_lang_to_gloss(inst) gpos_tier = gloss_tag_tier(inst) # If this tier exists, then let's process it. if gpos_tier is not None: # Iterate over each gloss POS tag... for i, gw in enumerate(gw_tier): tag = xigt_find(inst, alignment=gw.id) if tag is None: continue prev_word = gw_tier[i-1].value().lower() if i > 0 else None next_word = gw_tier[i+1].value().lower() if i < len(gw_tier)-1 else None if CLASS_FEATS_ALN in feat_list: subword_dict.add_word_tag(gw.value().lower(), tag.value(), prev_word, next_word)
def more_morph_align_test(self): inst = self.xc[1] # Align the gloss/lang words (Needed for aligning morphs) add_gloss_lang_alignments(inst) gloss_tokens = glosses(inst) morph_tokens = morphemes(inst) # Do the alignment morph_align(gloss_tokens, morph_tokens) # Assert that the glosses are aligned... self.assertIsNotNone(gloss_tokens[0].alignment) self.assertEquals(gloss_tokens[11].alignment, morph_tokens[6].id) self.assertEquals(gloss_tokens[12].alignment, morph_tokens[6].id) self.assertEquals(gloss_tokens[13].alignment, morph_tokens[7].id) self.assertEquals(gloss_tokens[14].alignment, morph_tokens[7].id)
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 test_word_alignment(self): inst = self.xc[1] add_gloss_lang_alignments(inst) rgp(inst)