Efficient Inner-to-outer Greedy Algorithm for Higher-order Labeled Dependency Parsing
نویسندگان
چکیده
Many NLP systems use dependency parsers as critical components. Jonit learning parsers usually achieve better parsing accuracies than two-stage methods. However, classical joint parsing algorithms significantly increase computational complexity, which makes joint learning impractical. In this paper, we proposed an efficient dependency parsing algorithm that is capable of capturing multiple edge-label features, while maintaining low computational complexity. We evaluate our parser on 14 different languages. Our parser consistently obtains more accurate results than three baseline systems and three popular, off-the-shelf parsers.
منابع مشابه
Effective Greedy Inference for Graph-based Non-Projective Dependency Parsing
Exact inference in high-order graph-based non-projective dependency parsing is intractable. Hence, sophisticated approximation techniques based on algorithms such as belief propagation and dual decomposition have been employed. In contrast, we propose a simple greedy search approximation for this problem which is very intuitive and easy to implement. We implement the algorithm within the second...
متن کاملTackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies o...
متن کاملGreed is Good if Randomized: New Inference for Dependency Parsing
Dependency parsing with high-order features results in a provably hard decoding problem. A lot of work has gone into developing powerful optimization methods for solving these combinatorial problems. In contrast, we explore, analyze, and demonstrate that a substantially simpler randomized greedy inference algorithm already suffices for near optimal parsing: a) we analytically quantify the numbe...
متن کاملUngreedy Methods for Chinese Deterministic Dependency Parsing
Deterministic dependency parsing has often been regarded as an efficient algorithm while its parsing accuracy is a little lower than the best results reported by more complex methods. In this paper, we compare deterministic dependency parsers with complex parsing methods such as generative and discriminative parsers on the standard data set of Penn Chinese Treebank. The results show that, for C...
متن کاملEasy-First Dependency Parsing of Modern Hebrew
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-agreement feature improves the parsing accuracy, making it on-par with a second-order globally optimized MST pars...
متن کامل