The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Struktur pergantungan mentafsirkan hubungan pengubahsuaian antara perkataan atau frasa dan diiktiraf sebagai elemen penting dalam analisis maklumat semantik. Dengan pendekatan konvensional untuk mengekstrak struktur kebergantungan ini, diandaikan bahawa ayat lengkap diketahui sebelum analisis bermula. Untuk data pertuturan spontan, walau bagaimanapun, andaian ini tidak semestinya betul kerana sempadan ayat tidak ditanda dalam data. Walaupun sempadan ayat boleh dikesan sebelum analisis kebergantungan, pelaksanaan bertingkat ini tidak sesuai untuk pemprosesan dalam talian kerana ia menangguhkan respons aplikasi. Untuk menyelesaikan masalah ini, kami mencadangkan kaedah analisis kebergantungan berurutan (SDA) untuk pemprosesan pertuturan spontan dalam talian, yang membolehkan kami menganalisis ayat yang tidak lengkap secara berurutan dan mengesan sempadan ayat secara serentak. Dalam makalah ini, kami mencadangkan SDA yang dipertingkatkan yang menyepadukan teknik pengesanan sempadan ayat (SntBD) berasaskan pelabelan berdasarkan Medan Rawak Bersyarat (CRF). Dalam kaedah baharu, kami menggunakan CRF untuk keputusan lembut sempadan ayat dan menggabungkannya dengan SDA untuk mengekalkan rangka kerja dalam taliannya. Memandangkan SntBD berasaskan CRF menghasilkan anggaran sempadan ayat yang lebih baik, SDA boleh memberikan hasil yang lebih baik di mana struktur kebergantungan dan sempadan ayat adalah konsisten. Keputusan eksperimen menggunakan ucapan syarahan spontan daripada Corpus of Spontaneous Japanese menunjukkan bahawa SDA kami yang dipertingkatkan mengatasi SDA asal dengan ketepatan SntBD memberikan hasil analisis kebergantungan yang lebih baik.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Takanobu OBA, Takaaki HORI, Atsushi NAKAMURA, "Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 5, pp. 1272-1281, May 2010, doi: 10.1587/transinf.E93.D.1272.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1272/_p
Salinan
@ARTICLE{e93-d_5_1272,
author={Takanobu OBA, Takaaki HORI, Atsushi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection},
year={2010},
volume={E93-D},
number={5},
pages={1272-1281},
abstract={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.},
keywords={},
doi={10.1587/transinf.E93.D.1272},
ISSN={1745-1361},
month={May},}
Salinan
TY - JOUR
TI - Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1272
EP - 1281
AU - Takanobu OBA
AU - Takaaki HORI
AU - Atsushi NAKAMURA
PY - 2010
DO - 10.1587/transinf.E93.D.1272
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2010
AB - 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.
ER -