Japanese Dependency Analysis using Cascaded Chunking
By Taku Kudo, Yuji Matsumoto. Conference on Computational Natural Language Learning, 2002
569 citations recorded by the source corpus.
In this paper, we propose a new statistical Japanese dependency parser using a cascaded chunking model. Conventional Japanese statistical dependency parsers are mainly based on a probabilistic model, which is not always efficient or scalable. We propose a new method that is simple and efficient, since it parses a sentence deterministically only deciding whether the current segment modifies the segment on its immediate right hand side. Experiments using the Kyoto University Corpus show that the method outperforms previous systems as well as improves the parsing and training efficiency.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/f6c043a4c9bb41fb155bc3485e80bb079ef61cb9
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Joakim Nivre
- Hiroshi Noji
- Masashi Yoshikawa
- Yuji Matsumoto
- Masso Utiyama
- Takayuki Sato
- Chenchen Ding
- Khin Mar Soe
Citations in the corpus
- Algorithms for Deterministic Incremental Dependency Parsing (2008, methodology): “The dominant learning method in this tradition is support vector machines (Kudo and Matsumoto 2002; Yamada and Matsumoto 2003; Nivre et al. 2006) but memory-based learning has also been used (Nivre, Hall, and Nilsson 2004; Nivre and Scholz 2004; Attardi 2006).”
- Introduction of the Asian Language Treebank (2016, background): “Besides KNP, CaboCha [5] and J.DepP [6] also conduct Japanese dependency analysis.”
- Controlling the Voice of a Sentence in Japanese-to-English Neural Machine Translation (2016, background): “0.68; Kudo and Matsumoto (2002)) to obtain the root phrase of the Japanese sentence in PREDICT.”
- Efficient probabilistic grammar induction for design (2018, unknown): “Additionally, advanced methods of chunking have been developed to improve the performance of such systems (Kudo & Matsumoto, 2002; Lee & Wu 2007).”
- A* CCG Parsing with a Supertag and Dependency Factored Model (2017, methodology): “# violations is the number of combinations violating the constraints on the outputs. dependencies , the syntactic representation ordinary used in Japanese NLP (Kudo and Matsumoto, 2002).”