Japanese dependency analysis using cascaded chunking

Kudo, Takeo; Matsumoto, Yūji

doi:10.3115/1118853.1118869

Cited by 317 publications

(212 citation statements)

References 9 publications

Supporting

Mentioning

209

Contrasting

Unclassified

Order By: Relevance

“…The Japanese text was segmented using a morphological analyzer, ChaSen † [22] and parsed by a dependency parser, CaboCha † † [23]. If a sentence is composed of two or more sub-sentences (two or more predicates), the argument reordering can only be done within the sub-sentence.…”

Section: Experiments Resultsmentioning

confidence: 99%

Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation

Goh

Watanabe

Sumita

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWhile phrase-based statistical machine translation systems prefer to translate with longer phrases, this may cause errors in a free word order language, such as Japanese, in which the order of the arguments of the predicates is not solely determined by the predicates and the arguments can be placed quite freely in the text. In this paper, we propose to reorder the arguments but not the predicates in Japanese using a dependency structure as a kind of reordering. Instead of a single deterministically given permutation, we generate multiple reordered phrases for each sentence and translate them independently. Then we apply a re-ranking method using a discriminative approach by Ranking Support Vector Machines (SVM) to re-score the multiple reordered phrase translations. In our experiment with the travel domain corpus BTEC, we gain a 1.22% BLEU score improvement when only 1-best is used for re-ranking and 4.12% BLEU score improvement when n-best is used for Japanese-English translation.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation

Goh

Watanabe

Sumita

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The corpus contains articles from 2003-2102, with a total of 117,492 sentence pairs. We used the Japanese data to extract the noun-verb collocation candidates using a dependency parser, Cabocha (Kudo and Matsumoto, 2002). For our work, we focus on the object-verb, subject-verb and dativeverb dependency relations.…”

Section: Data Setmentioning

confidence: 99%

Proceedings of the 10th Workshop on Multiword Expressions (MWE)

2014

View full text Add to dashboard Cite

“…When hierarchical structure has to be recognized, additional local decisions are required to determine the embedding of phrases, resulting in a more complex inference process which recursively builds the global solution. Such type of systems can be found for deeper levels of partial parsing (Tjong Kim Sang & Déjean, 2001;Carreras et al, 2002;Kudo & Matsumoto, 2002), or in full parsing (Magerman, 1996;Ratnaparkhi, 1999;Haruno et al, 1999). In general, a learning system for these tasks makes use of several learned functions which interact in some way to determine the final structure.…”

Section: Introductionmentioning

confidence: 99%

Filtering-Ranking Perceptron Learning for Partial Parsing

2005

View full text Add to dashboard Cite

Abstract. This work introduces a general phrase recognition system based on perceptrons, and a global online learning algorithm to train them together. The method applies to complex domains in which some structure has to be recognized. This global problem is broken down into two layers of local subproblems: a filtering layer, which reduces the search space by identifying plausible phrase candidates; and a ranking layer, which builds the optimal phrase structure by discriminating among competing phrases. A recognition-based feedback rule is presented which reflects to each local function its committed errors from a global point of view, and allows to train them together online as perceptrons. As a result, the learned functions automatically behave as filters and rankers, rather than binary classifiers, which we argue to be better for this type of problems. Extensive experimentation on partial parsing tasks gives state-of-the-art results and evinces the advantages of the global training method over optimizing each function locally and independently.

show abstract

Japanese dependency analysis using cascaded chunking

Cited by 317 publications

References 9 publications

Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation

Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation

Proceedings of the 10th Workshop on Multiword Expressions (MWE)

Filtering-Ranking Perceptron Learning for Partial Parsing

Contact Info

Product

Resources

About