In this paper, we propose a three-step multilingual dependency parser, which generalizes an efficient parsing algorithm at first phase, a root parser and postprocessor at the second and third stages. The main focus of our work is to provide an efficient parser that is practical to use with combining only lexical and part-ofspeech features toward language independent parsing. The experimental results show that our method outperforms Maltparser in 13 languages. We expect that such an efficient model is applicable for most languages. 1

Entropy Guided Transformation Learning (ETL) is a new machine learning strategy that combines the advantages of decision trees (DT) and Transformation Based Learning (TBL). In this work, we apply the ETL framework to four phrase chunking tasks: Portuguese noun phrase chunking, English base noun phrase chunking, English text chunking and Hindi text chunking. In all four tasks, ETL shows better results than Decision Trees and also than TBL with hand-crafted templates. ETL provides a new training strategy that accelerates transformation learning. For the English text chunking task this corresponds to a factor of five speedup. For Portuguese noun phrase chunking, ETL shows the best reported results for the task. For the other three linguistic tasks, ETL shows state-of-theart competitive results and maintains the advantages of using a rule based system. 1

Many sequence labeling tasks in NLP require solving a cascade of segmentation and tagging subtasks, such as Chinese POS tagging, named entity recognition, and so on. Traditional pipeline approaches usually suffer from error propagation. Joint training/decoding in the cross-product state space could cause too many parameters and high inference complexity. In this paper, we present a novel method which integrates graph structures of two subtasks into one using virtual nodes, and performs joint training and decoding in the factorized state space. Experimental evaluations on CoNLL 2000 shallow parsing data set and Fourth SIGHAN Bakeoff CTB POS tagging data set demonstrate the superiority of our method over cross-product, pipeline and candidate reranking approaches. 1

Most existing systems solved the phrase chunking task with the sequence labeling approaches, in which the chunk candidates cannot be treated as a whole during parsing process so that the chunk-level features cannot be exploited in a natural way. In this paper, we formulate phrase chunking as a joint segmentation and labeling task. We propose an efficient dynamic programming algorithm with pruning for decoding, which allows the direct use of the features describing the internal characteristics of chunk and the features capturing the correlations between adjacent chunks. A relaxed, online maximum margin training algorithm is used for learning. Within this framework, we explored a variety of effective feature representations for Chinese phrase chunking. The experimental results show that the use of chunk-level features can lead to significant performance improvement, and that our approach achieves state-of-the-art performance. In particular, our approach is much better at recognizing long and complicated phrases. 1