Hiroshi Noji

Optimal Shift-Reduce Constituent Parsing with Structured Perceptron

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 even with large beam sizes.1

Using Left-corner Parsing to Encode Universal Structural Constraints in Grammar Induction.

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 degree of center-embedding of a parse via its stack depth. We apply the technique to learning of famous generative model, the dependency model with valence (Klein and Manning, 2004). Cross-linguistic experiments on Universal Dependencies show that often our method boosts the performance from the baseline, and competes with the current state-ofthe-art model in a number of languages.

Jigg: A Framework for an Easy Natural Language Processing Pipeline

We present Jigg, a Scala (or JVMbased) NLP annotation pipeline framework, which is easy to use and is extensible. Jigg supports a very simple interface similar to Stanford CoreNLP, the most successful NLP pipeline toolkit, but has more flexibility to adapt to new types of annotation. On this framework, system developers can easily integrate their downstream system into a NLP pipeline from a raw text by just preparing a wrapper of it.

A* CCG Parsing with a Supertag and Dependency Factored Model.

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 achieves the state-of-the-art results on English and Japanese CCG parsing.

Adversarial Training for Cross-Domain Universal Dependency Parsing

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 bidirectional LSTMs. In our experiments, we find our baseline graph-based parser already outperforms the official baseline model (UDPipe) by a large margin. Further, by applying our technique to the treebanks of the same lan- guage with different domains, we observe an additional gain in the performance, in particular for the domains with less training data