def lemmatize(infname, lang, outf=sys.stdout, sent_tag="seg",
encoding="utf-8", replace_unknown_lemma=True):
"""
Lemmatize reference translations in mteval format (may work for other
formats too)
Parameters
----------
infname: str
name of inputfile in mteval xml format
lang: str
two-letter language identifier
outf: file or str, optional
file or filename for output
encoding: str, optional
char encoding for output (should be the same as that of input)
replace_unknown_lemma: bool, optional
replace unknown lemma by word
"""
annotator = get_annotator(lang, replace_unknown_lemma=replace_unknown_lemma)
log.info("using annotator " + annotator.__class__.__name__)
log.info("reading evaluation data from file " + infname)
etree = et.ElementTree(file=infname)
sentences = [ sent_elem.text for sent_elem in etree.iter(sent_tag) ]
log.debug(u"input:\n" + u"\n".join(sentences))
graph_list = annotator.annot_sentences(sentences)
for sent_elem, graph in zip(etree.iter(sent_tag), graph_list):
lemma_text = " ".join(graph.source_lemmas())
sent_elem.text = lemma_text
log.info("writing lemmatized evaluation data to {0}".format(
getattr(outf, "name", outf)))
etree.write(outf, encoding=encoding)
def preprocess(data_set, lang_pair):
source_lang, target_lang = lang_pair.split("-")
graphs_fname = config["eval"][data_set][lang_pair]["graphs_fname"]
out_dir = os.path.dirname(graphs_fname)
if not os.path.exists(out_dir):
os.mkdir(out_dir)
# annotate
annotator = get_annotator(source_lang)
graph_list = annotator.annot_xml_file(
config["eval"][data_set][lang_pair]["src_fname"])
# lookup translations
dict_fname = TransDict.load(config["dict"][lang_pair]["pkl_fname"])
lookup = Lookup(dict_fname)
lookup(graph_list)
# score most frequent translation
freq_score = FreqScorer(config["count"]["lemma"][target_lang]["pkl_fname"])
freq_score(graph_list)
# dict upper scores
lemma_ref_fname = \
config["eval"][data_set][lang_pair]["lemma_ref_fname"]
scorer = DictUpperScorer(lemma_ref_fname)
scorer(graph_list)
# model upper scores
ambig_fname = config["sample"][lang_pair]["ambig_fname"]
filter = filter_functions(source_lang)
scorer = ModelUpperScorer(lemma_ref_fname, ambig_fname, filter)
scorer(graph_list)
# save graphs
log.info("saving preprocessed graphs to " + graphs_fname)
cPickle.dump(graph_list, open(graphs_fname, "wb"))
def make_graphs():
"""
Create annotated translations graphs with scores for random translation,
most frequent translation and approximated maximum. Also create minimal
translation dictionaries for these graphs and drawings.
"""
for lang_pair, src_fname, lemma_ref_fname in [
("en-de",
"sample_newstest2011-src.en.sgm",
"lemma_sample_newstest2011-ref.de.sgm"),
("de-en",
"sample_out_de-en.src",
"lemma_sample_out_de-en.ref") ]:
source_lang, target_lang = lang_pair.split("-")
root_fname = splitext(src_fname)[0]
# annotate
annotator = get_annotator(source_lang)
graphs = annotator.annot_xml_file(src_fname)
# lookup
dict_fname = config["dict"][lang_pair]["pkl_fname"]
trans_dict = TransDict.load(dict_fname)
lookup = LookupKeepKeys(trans_dict)
lookup(graphs)
# write pickle of minimal translation dict
min_dict = lookup.get_minimal_trans_dict()
min_dict_fname = "dict_" + root_fname + ".pkl"
dump(min_dict, open(min_dict_fname, "wb"))
# score most frequent translation
counts_fname = config["count"]["lemma"][target_lang]["pkl_fname"]
freq_score = FreqScorer(counts_fname)
freq_score(graphs)
# score random translation
counts_fname = config["count"]["lemma"][target_lang]["pkl_fname"]
rand_score = RandScorer()
rand_score(graphs)
# dict upper score
maxscore = DictUpperScorer(lemma_ref_fname)
maxscore(graphs)
# model upper scores
ambig_fname = config["sample"][lang_pair]["ambig_fname"]
filter = filter_functions(source_lang)
scorer = ModelUpperScorer(lemma_ref_fname, ambig_fname, filter)
scorer(graphs)
# draw graphs
draw = Draw()
draw(graphs, out_format="pdf",
base_score_attrs=["dup_score", "mup_score", "freq_score",
"rand_score"],
out_dir="_draw_" + lang_pair)
# save graphs
graphs_fname = "graphs_" + root_fname + ".pkl"
dump(graphs, open(graphs_fname, "wb"))
