Hiroshi Noji

Learn More
We present a constituent shift-reduce parser with a structured perceptron that finds the optimal parse in a practical runtime. The key ideas are new feature templates that facilitate state merging of dynamic programming and A* search. Our system achieves 91.1 F1 on a standard English experiment, a level which cannot be reached by other beam-based systems(More)
Center-embedding is difficult to process and is known as a rare syntactic construction across languages. In this paper we describe a method to incorporate this assumption into the grammar induction tasks by restricting the search space of a model to trees with limited centerembedding. The key idea is the tabulation of left-corner parsing, which captures the(More)
We propose a transition system for dependency parsing with a left-corner parsing strategy. Unlike parsers with conventional transition systems, such as arc-standard or arc-eager, a parser with our system correctly predicts the processing difficulties people have, such as of center-embedding. We characterize our transition system by comparing its oracle(More)
We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique. Our approach is an extension to the recently proposed adversarial training technique for domain adaptation, which we apply on top of a graph-based neural dependency parsing model on(More)
Universal Dependencies (UD) is becoming a standard annotation scheme crosslinguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words. To improve the parsability of UD, we propose a backand-forth conversion algorithm, in which we preprocess the training treebank to(More)
We propose a new A* CCG parsing model in which the probability of a tree is decomposed into factors of CCG categories and its syntactic dependencies both defined on bi-directional LSTMs. Our factored model allows the precomputation of all probabilities and runs very efficiently, while modeling sentence structures explicitly via dependencies. Our model(More)