@inproceedings{chien-2019-deep,
title = "Deep {B}ayesian Natural Language Processing",
author = "Chien, Jen-Tzung",
editor = "Nakov, Preslav and
Palmer, Alexis",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-4006",
doi = "10.18653/v1/P19-4006",
pages = "25--30",
abstract = "This introductory tutorial addresses the advances in deep Bayesian learning for natural language with ubiquitous applications ranging from speech recognition to document summarization, text classification, text segmentation, information extraction, image caption generation, sentence generation, dialogue control, sentiment classification, recommendation system, question answering and machine translation, to name a few. Traditionally, {``}deep learning{''} is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The {``}semantic structure{''} in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The {``}distribution function{''} in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process, Chinese restaurant process, hierarchical Pitman-Yor process, Indian buffet process, recurrent neural network, long short-term memory, sequence-to-sequence model, variational auto-encoder, generative adversarial network, attention mechanism, memory-augmented neural network, skip neural network, stochastic neural network, predictive state neural network and policy neural network. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference and sampling method are formulated to tackle the optimization for complicated models. The word and sentence embeddings, clustering and co-clustering are merged with linguistic and semantic constraints. A series of case studies and domain applications are presented to tackle different issues in deep Bayesian processing, learning and understanding. At last, we will point out a number of directions and outlooks for future studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chien-2019-deep">
<titleInfo>
<title>Deep Bayesian Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jen-Tzung</namePart>
<namePart type="family">Chien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This introductory tutorial addresses the advances in deep Bayesian learning for natural language with ubiquitous applications ranging from speech recognition to document summarization, text classification, text segmentation, information extraction, image caption generation, sentence generation, dialogue control, sentiment classification, recommendation system, question answering and machine translation, to name a few. Traditionally, “deep learning” is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The “semantic structure” in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The “distribution function” in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process, Chinese restaurant process, hierarchical Pitman-Yor process, Indian buffet process, recurrent neural network, long short-term memory, sequence-to-sequence model, variational auto-encoder, generative adversarial network, attention mechanism, memory-augmented neural network, skip neural network, stochastic neural network, predictive state neural network and policy neural network. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference and sampling method are formulated to tackle the optimization for complicated models. The word and sentence embeddings, clustering and co-clustering are merged with linguistic and semantic constraints. A series of case studies and domain applications are presented to tackle different issues in deep Bayesian processing, learning and understanding. At last, we will point out a number of directions and outlooks for future studies.</abstract>
<identifier type="citekey">chien-2019-deep</identifier>
<identifier type="doi">10.18653/v1/P19-4006</identifier>
<location>
<url>https://aclanthology.org/P19-4006</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>25</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Bayesian Natural Language Processing
%A Chien, Jen-Tzung
%Y Nakov, Preslav
%Y Palmer, Alexis
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F chien-2019-deep
%X This introductory tutorial addresses the advances in deep Bayesian learning for natural language with ubiquitous applications ranging from speech recognition to document summarization, text classification, text segmentation, information extraction, image caption generation, sentence generation, dialogue control, sentiment classification, recommendation system, question answering and machine translation, to name a few. Traditionally, “deep learning” is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The “semantic structure” in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The “distribution function” in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process, Chinese restaurant process, hierarchical Pitman-Yor process, Indian buffet process, recurrent neural network, long short-term memory, sequence-to-sequence model, variational auto-encoder, generative adversarial network, attention mechanism, memory-augmented neural network, skip neural network, stochastic neural network, predictive state neural network and policy neural network. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference and sampling method are formulated to tackle the optimization for complicated models. The word and sentence embeddings, clustering and co-clustering are merged with linguistic and semantic constraints. A series of case studies and domain applications are presented to tackle different issues in deep Bayesian processing, learning and understanding. At last, we will point out a number of directions and outlooks for future studies.
%R 10.18653/v1/P19-4006
%U https://aclanthology.org/P19-4006
%U https://doi.org/10.18653/v1/P19-4006
%P 25-30
Markdown (Informal)
[Deep Bayesian Natural Language Processing](https://aclanthology.org/P19-4006) (Chien, ACL 2019)
ACL
- Jen-Tzung Chien. 2019. Deep Bayesian Natural Language Processing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pages 25–30, Florence, Italy. Association for Computational Linguistics.