Conclusion & Future Work ● The overall ranking of the system is #7 in the closed challenge, and #2 in the open challenge ● The results clearly show that the integration of HPSG parsing results in the semantic role labeling task brings substantial performance improvement. The conclusion from Zhang et al. (2008) on English has been reconfirmed on multiple languages, even where grammar coverage is low ● The gain is more significant on out-of-domain tests, indicating that the hybrid system is more robust to cross-domain variation ● The closed SRL system needs to be improved in the future Results In this paper we present our syntactic and semantic dependency parsing system, which extends the system of Zhang, Wang, & Uszkoreit (2008) in the multilingual direction, and achieves 76.49 average macro F1 Score on the closed joint task. Substantial improvements to the open SRL task have been observed that are attributed to the HPSG parses with hand-crafted grammars.

We propose a reordering method to improve the fluency of the output of the phrase-based SMT (PBSMT) system. We parse the transla-tion results that follow the source language or-der into non-projective dependency trees, then reorder dependency trees to obtain fluent tar-get sentences. Our method ensures that the translation results are grammatically correct and achieves major improvements over PB-SMT using dependency-based metrics. 1

We present our system used in the CoNLL 2007 shared task on multilingual parsing. The system is composed of three components: a k-best maximum spanning tree (MST) parser, a tree labeler, and a reranker that orders the k-best labeled trees. We present two techniques for training the MST parser: tree

In this paper we present our experiments in parsing Hindi. We first explored Malt and MST parsers. Considering pros of both these parsers, we developed a hybrid approach combining the output of these two parsers in an intuitive manner. We report our results on both development and test data

In this paper, we compare a higher order graph-based parser and a transitionbased parser with beam search. These parsers provide a higher accuracy than a second order MST parser and a deterministic transition-based parser. We apply and compare the output on languages, which have not been

We investigate the performance of an easyfirst, non-directional dependency parser on the Hebrew Dependency treebank. We show that with a basic feature set the greedy parser’s accuracy is on a par with that of a first-order globally optimized MST parser. The addition of morphological

The recent success of statistical parsing methods has made treebanks become important resources for building good parsers. However, constructing highquality annotated treebanks is a challenging task. We utilized two publicly available parsers, Berkeley and MST parsers, for feedback on improving

This i)al)cr descrihcs a natural language i)ars - ing algorith,n for unrestricted text whicll uses a i)rol)ability-based scoring fimctiou to select the "}mst" I)arse of a sentence. The parser, earl, is a I. ime-a.synchronous bottom-ul) chart I)arscr with Earicy-type top-down prediction

We report our dependency parsing experiments on two Indian Languages, Telugu and Hindi. We first explore two most popular dependency parsers namely, Malt parser and MST parser. Considering pros of both these parsers, we develop a hybrid approach combining the output of these two parsers

We describe a newly available Hebrew Dependency Treebank, which is extracted from the Hebrew (constituency) Treebank. We establish some baseline unlabeled dependency parsing performance on Hebrew, based on two state-of-the-art parsers, MST-parser and MaltParser. The evaluation is performed both