HIT Dependency Parsing : Bootstrap Aggregating Heterogeneous Parsers
نویسندگان
چکیده
The paper describes our system of Shared Task on Parsing the Web. We only participate in dependency parsing task. A number of methods have been developed for dependency parsing. Each of the methods adopts very different view of dependency parsing, and each view can have its strengths and limitations. Thus system combination can have great potential to further improve the performance of dependency parsing. In this work, Bootstrap Aggregating (Bagging) is chosen to combine these methods. This approach obtains significantly improvements for dependency parsing, and especially we achieves a UAS of 93.88%, LAS of 91.88% on WSJ domain, which is the top result of all participated systems. We tried to use unlabeled data offered by this task as well, and unfortunately we received little improvements through tri-training. Finally, our final bagging system ranked thirdly of the shared task.
منابع مشابه
An improved joint model: POS tagging and dependency parsing
Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...
متن کاملJointly or Separately: Which is Better for Parsing Heterogeneous Dependencies?
For languages such as English, several constituent-to-dependency conversion schemes are proposed to construct corpora for dependency parsing. It is hard to determine which scheme is better because they reflect different views of dependency analysis. We usually obtain dependency parsers of different schemes by training with the specific corpus separately. It neglects the correlations between the...
متن کاملJoint Inference for Heterogeneous Dependency Parsing
This paper is concerned with the problem of heterogeneous dependency parsing. In this paper, we present a novel joint inference scheme, which is able to leverage the consensus information between heterogeneous treebanks in the parsing phase. Different from stacked learning methods (Nivre and McDonald, 2008; Martins et al., 2008), which process the dependency parsing in a pipelined way (e.g., a ...
متن کاملProbabilistic Models for Action-Based Chinese Dependency Parsing
Action-based dependency parsing, also known as deterministic dependency parsing, has often been regarded as a time efficient parsing algorithm while its parsing accuracy is a little lower than the best results reported by more complex parsing models. In this paper, we compare actionbased dependency parsers with complex parsing methods such as all-pairs parsers on Penn Chinese Treebank. For Chin...
متن کاملCreating POS Tagging and Dependency Parsing Experts via Topic Modeling
Part of speech (POS) taggers and dependency parsers tend to work well on homogeneous datasets but their performance suffers on datasets containing data from different genres. In our current work, we investigate how to create POS tagging and dependency parsing experts for heterogeneous data by employing topic modeling. We create topic models (using Latent Dirichlet Allocation) to determine genre...
متن کامل