def align_file(fin, fout, em_model, hmm_model):
pairs = Aligner.readAMR(fin)
print("Aligning")
algs = Aligner.alignPairs(pairs, em_model, hmm_model)
print("Writing alignments to file")
Aligner.printAlignments(algs, pairs, fout)
print("done")
def train_models(fnames, emiter, hmmiter, model_name):
if not fnames:
sys.exit("No file provided")
print("Reading AMR files")
pairs = []
for fname in fnames:
f = open(fname, "r")
pairs += Aligner.readAMR(f)
f.close()
sentences = [Aligner.tokenize(pair[0]) for pair in pairs]
graphs = [AMRGraph(pair[1], False) for pair in pairs]
emprobs = EM.train(sentences, graphs, model_name + ".em", emiter)
#emprobs = EM.load_model(model_name + ".em")
print("Initializing rule-based alignments")
n = len(sentences)
initalgs = [{}] * n
for i in range(n):
initalgs[i] = Aligner.initalign(graphs[i].ref, sentences[i])
if (i+1) % 1000 == 0:
print(str(i+1) + "/" + str(n))
hmmprobs = HMM.train(sentences, graphs, emprobs, model_name + ".hmm", hmmiter, initalgs)
print("Done")
