Japanese dependency structure analysis based on maximum entropy models

Uchimoto, Kiyotaka; Sekine, Satoshi; Isahara, Hitoshi

doi:10.3115/977035.977062

Cited by 36 publications

(62 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And we also employ the flag of the beginning/ending bunsetsu of a sentence, the distance between the two bunsetsus, pause symbol and their combination features. They conform with features used in previous reports [18], [19]. <c> and <b> were handled as surface forms in SDA.…”

Section: Methodsmentioning

confidence: 78%

See 1 more Smart Citation

Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection

Oba

Hori

Nakamura

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Takanobu OBA†a) , Takaaki HORI †b) , and Atsushi NAKAMURA †c) , Members SUMMARY A dependency structure interprets modification relationships between words or phrases and is recognized as an important element in semantic information analysis. With the conventional approaches for extracting this dependency structure, it is assumed that the complete sentence is known before the analysis starts. For spontaneous speech data, however, this assumption is not necessarily correct since sentence boundaries are not marked in the data. Although sentence boundaries can be detected before dependency analysis, this cascaded implementation is not suitable for online processing since it delays the responses of the application. To solve these problems, we proposed a sequential dependency analysis (SDA) method for online spontaneous speech processing, which enabled us to analyze incomplete sentences sequentially and detect sentence boundaries simultaneously. In this paper, we propose an improved SDA integrating a labeling-based sentence boundary detection (SntBD) technique based on Conditional Random Fields (CRFs). In the new method, we use CRF for soft decision of sentence boundaries and combine it with SDA to retain its online framework. Since CRF-based SntBD yields better estimates of sentence boundaries, SDA can provide better results in which the dependency structure and sentence boundaries are consistent. Experimental results using spontaneous lecture speech from the Corpus of Spontaneous Japanese show that our improved SDA outperforms the original SDA with SntBD accuracy providing better dependency analysis results.

show abstract

Section: Methodsmentioning

confidence: 78%

“…Some dependency models for calculating dependency [18] and also have modeled a dependency link that takes context structures into consideration [20]. Kudo et al have proposed two types of modeling methods [19].…”

Section: Dependency Modelingmentioning

confidence: 99%

Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection

Oba

Hori

Nakamura

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…In the evaluation of dependency parsing, we obtained the dependency accuracy (the percentage of correctly analyzed dependencies out of all dependencies) and sentency accuracy (the percentage of the sentences in which all the dependencies are analyzed correctly), which were defined by Uchimoto et al (1999). We compared our method to Yoshida's method (Yoshida et al, 2014) and two conventional sequential methods.…”

Section: Outline Of Experimentsmentioning

confidence: 99%

Japanese Word Reordering Executed Concurrently with Dependency Parsing and Its Evaluation

Ohno

Yoshida²,

Kato

et al. 2015

Proceedings of the 15th European Workshop on Natural Language Generation (ENLG)

View full text Add to dashboard Cite

This paper proposes a method for reordering words in a Japanese sentence based on concurrent execution with dependency parsing so that the sentence becomes more readable. Our contributions are summarized as follows: (1) we extend a probablistic model used in the previous work which concurrently performs word reordering and dependency parsing; (2) we conducted an evaluation experiment using our semi-automatically constructed evaluation data so that sentences in the data are more likely to be spontaneously written by natives than the automatically constructed evaluation data in the previous work.

show abstract

“…This score has been used in many researches and can be computed in various ways, for example, by using machine learning methods such as Maximum Entropy Models [22], Support Vector Machines [23], and MIRA [24] or conditional probabilistic models [26], [33], to estimate the score from kinds of linguistic features related with the two words.…”

Section: The Scores Of the Edgesmentioning

confidence: 99%

“…Of course, a rich set of training data and accurate knowledge are crucial for this method. Various methods have been proposed for the learning part of this approach: learning actions of a deterministic parser [18], [19], learning similarity of tree structures [20], [21], and learning the scores of dependencies [22]- [24].…”

Section: Linesmentioning

confidence: 99%

Dependency Parsing with Lattice Structures for Resource-Poor Languages

Sudprasert

Kawtrakul

Boitet

et al. 2009

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we present a new dependency parsing method for languages which have very small annotated corpus and for which methods of segmentation and morphological analysis producing a unique (automatically disambiguated) result are very unreliable. Our method works on a morphosyntactic lattice factorizing all possible segmentation and part-of-speech tagging results. The quality of the input to syntactic analysis is hence much better than that of an unreliable unique sequence of lemmatized and tagged words. We propose an adaptation of Eisner's algorithm for finding the k-best dependency trees in a morphosyntactic lattice structure encoding multiple results of morphosyntactic analysis. Moreover, we present how to use Dependency Insertion Grammar in order to adjust the scores and filter out invalid trees, the use of language model to rescore the parse trees and the k-best extension of our parsing model. The highest parsing accuracy reported in this paper is 74.32% which represents a 6.31% improvement compared to the model taking the input from the unreliable morphosyntactic analysis tools.

show abstract

Japanese dependency structure analysis based on maximum entropy models

Cited by 36 publications

References 5 publications

Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection

Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection

Japanese Word Reordering Executed Concurrently with Dependency Parsing and Its Evaluation

Dependency Parsing with Lattice Structures for Resource-Poor Languages

Contact Info

Product

Resources

About