def main(args):
feature_extractor = FeatureExtractor(get_resources(), args.model)
train_feats, train_labels, _, _ = feature_extractor.get_features(
args.train, args.train_topk)
test_feats, _, test_segs, test_gold_truths = feature_extractor.get_features(
args.test, args.test_topk)
epochs, lr1, lr2 = 100, 0.01, 0.05
# Initialize model
model = None
if args.model == "mse":
model = mse_ranker.MSERanker(epochs, lr1)
elif args.model == "mr":
model = mr_ranker.MRRanker(epochs, lr1)
elif args.model == "mse_multi":
model = mse_multi_ranker.MSEMultiRanker(epochs, lr1, lr2)
elif args.model == "mr_multi":
model = mr_multi_ranker.MRMultiRanker(epochs, lr1, lr2)
# Train model
model.train(train_feats, train_labels)
# Rerank top-k segmentations
top_segmentations = []
for segs_feats, segs, gds in zip(test_feats, test_segs, test_gold_truths):
if len(segs) == 1:
top_segmentations.extend(segs)
else:
reranked_segs = rerank(segs, segs_feats, model, args.model)
top_segmentations.append(reranked_segs)
if args.output is not None:
fp = open(args.output, 'w')
for segs in top_segmentations:
target = "".join(segs[0].split())
fp.write(target + "\t" + "\t".join([seg.strip()
for seg in segs]) + "\n")
fp.close()
# Evaluate metrics
print("MRR:", mean_reciprocal_rank(test_gold_truths, top_segmentations))
print("Accuracy@1:", accuracy(1, test_gold_truths, top_segmentations))
print("Accuracy@2:", accuracy(2, test_gold_truths, top_segmentations))
print("Fscore@1:", fscore(1, test_gold_truths, top_segmentations))
print("Fscore@2:", fscore(2, test_gold_truths, top_segmentations))
