[논문]Utterance Generation With Variational Auto-Encoder for Slot Filling in Spoken Language Understanding

Shin, Youhyun; Yoo, Kang Min; Lee, Sang-Goo

doi:10.1109/lsp.2019.2895284

Utterance Generation With Variational Auto-Encoder for Slot Filling in Spoken Language Understanding

IEEE signal processing letters, v.26 no.3, 2019년, pp.505 - 509

Shin, Youhyun (Department of Computer Science Engineering, Seoul National University, Seoul, South Korea) , Yoo, Kang Min (Department of Computer Science Engineering, Seoul National University, Seoul, South Korea) , Lee, Sang-Goo (Department of Computer Science Engineering, Seoul National University, Seoul, South Korea)

Abstract ▼ AI-Helper

Slot filling must be trained using human-labeled data that are expensive and only a limited amount of labeled utterances are readily available for learning. Data generation methods can help increase the size of the dataset and make variations to the training dataset by means of emerging new instances. We propose a novel labeled utterance generation algorithm to augment training data. Our hypothesis is that words in an utterance can be separated into the two parts, namely, slot values that are instances of slot types and the accompanying contexts. Our model aims to generate utterances that are diverse combinations of slot values and contexts that can appear together. To create various utterances containing a given condition, our deep generative model uses a conditional variational auto-encoder architecture. We conduct experiments on various slot filling datasets, specifically airline travel information systems (ATIS), Snips, and MIT Corpus. A quantitative analysis shows that the application of data augmentation using the proposed model improves the F1 score for slot filling. We also demonstrate that our labeled utterance generation model yields more desirable utterances.

참고문헌 (25)

10.18653/v1/K16-1002
Proc Adv Neural Inf Process Syst Semi-supervised learning with deep generative models kingma 0 3581
A neural algorithm of artistic style gatys 2015
Proc Adv Neural Inf Process Syst Learning structured output representation using deep conditional generative models sohn 0 3483
Proc 34th Int Conf Mach Learn Toward controlled generation of text hu 0 1587
Proc Thirty-Second Assoc Advanc Artifi Intell Conf Artif Intell Style transfer in text: Exploration and evaluation fu 0 663
Disentangled representation learning for text style transfer john 2018
Proc Adv Neural Inf Process Syst Style transfer from non-parallel text by cross-alignment shen 0 6830
Proc Neural Inf Process Syst Deep Learn Represent Learn Workshop Distilling the knowledge in a neural network hinton 0
Guu, Kelvin, Hashimoto, Tatsunori B., Oren, Yonatan, Liang, Percy. Generating Sentences by Editing Prototypes. Transactions of the association for computational linguistics, vol.6, 437-450.

상세보기
10.21437/Interspeech.2018-1808
10.18653/v1/D16-1223
Proc INTERSPEECH Labeled data generation with encoder-decoder ISTM for semantic slot filling kurata 0 725
Proc Annu Conf Int Speech Commun Assoc RNN-based labeled data generation for spoken language understanding tam 0 125
Proc 27th Int Conf Comput Linguistics Sequence-to-sequence data augmentation for dialogue language understanding hou 0 1234
10.1109/ICASSP.2017.7953243
Proc INTERSPEECH Attention-based recurrent neural network models for joint intent detection and slot filling liu 0 685
Auto-encoding variational Bayes kingma 2013
Proc AAAI Neural models for sequence chunking zhai 0 3365
Comput Linguistics Class-based n-gram models of natural language brown 1992 18 467
Proc INTERSPEECH Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding mesnil 0 3771
Proc Int Conf Learn Represent Adam: A method for stochastic optimization kingma 0
10.18653/v1/N18-2118
Mesnil, Gregoire, Dauphin, Yann, Kaisheng Yao, Bengio, Yoshua, Li Deng, Hakkani-Tur, Dilek, Xiaodong He, Heck, Larry, Tur, Gokhan, Dong Yu, Zweig, Geoffrey. Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding. IEEE/ACM transactions on audio, speech, and language processing, vol.23, no.3, 530-539.

상세보기
Knowledge as a teacher: Knowledge-guided structural attention networks chen 2016

LOADING...

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Utterance Generation With Variational Auto-Encoder for Slot Filling in Spoken Language Understanding

Abstract ▼ AI-Helper

참고문헌 (25)

이 논문을 인용한 문헌

연구과제 타임라인

관련 콘텐츠

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

Utterance Generation With Variational Auto-Encoder for Slot Filling in Spoken Language Understanding

Abstract ▼ AI-Helper

참고문헌 (25)

이 논문을 인용한 문헌

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

관련 콘텐츠

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트