@inproceedings{lin-etal-2019-dive,
title = "Dive into Deep Learning for Natural Language Processing",
author = "Lin, Haibin and
Shi, Xingjian and
Lausen, Leonard and
Zhang, Aston and
He, He and
Zha, Sheng and
Smola, Alexander",
editor = "Baldwin, Timothy and
Carpuat, Marine",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-2001",
abstract = "Deep learning has become the dominant approach to NLP problems, especially when applied on large scale corpora. Recent progress on unsupervised pre-training techniques such as BERT, ELMo, GPT-2, and language modeling in general, when applied on large corpora, is shown to be effective in improving a wide variety of downstream tasks. These techniques push the limits of available hardware, requiring specialized frameworks optimized for GPU, ASIC, and distributed cloud-based training.A few complexities pose challenges to scale these models and algorithms effectively. Compared to other areas where deep learning is applied, these NLP models contain a variety of moving parts: text normalization and tokenization, word representation at subword-level and word-level, variable-length models such as RNN and attention, and sequential decoder based on beam search, among others.In this hands-on tutorial, we take a closer look at the challenges from these complexities and see how with proper tooling with Apache MXNet and GluonNLP, we can overcome these challenges and achieve state-of-the-art results for real-world problems. GluonNLP is a powerful new toolkit that combines MXNet{'}s speed, the flexibility of Gluon, and an extensive new library automating the most laborious aspects of deep learning for NLP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2019-dive">
<titleInfo>
<title>Dive into Deep Learning for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haibin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingjian</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonard</namePart>
<namePart type="family">Lausen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aston</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Zha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Smola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep learning has become the dominant approach to NLP problems, especially when applied on large scale corpora. Recent progress on unsupervised pre-training techniques such as BERT, ELMo, GPT-2, and language modeling in general, when applied on large corpora, is shown to be effective in improving a wide variety of downstream tasks. These techniques push the limits of available hardware, requiring specialized frameworks optimized for GPU, ASIC, and distributed cloud-based training.A few complexities pose challenges to scale these models and algorithms effectively. Compared to other areas where deep learning is applied, these NLP models contain a variety of moving parts: text normalization and tokenization, word representation at subword-level and word-level, variable-length models such as RNN and attention, and sequential decoder based on beam search, among others.In this hands-on tutorial, we take a closer look at the challenges from these complexities and see how with proper tooling with Apache MXNet and GluonNLP, we can overcome these challenges and achieve state-of-the-art results for real-world problems. GluonNLP is a powerful new toolkit that combines MXNet’s speed, the flexibility of Gluon, and an extensive new library automating the most laborious aspects of deep learning for NLP.</abstract>
<identifier type="citekey">lin-etal-2019-dive</identifier>
<location>
<url>https://aclanthology.org/D19-2001</url>
</location>
<part>
<date>2019-11</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dive into Deep Learning for Natural Language Processing
%A Lin, Haibin
%A Shi, Xingjian
%A Lausen, Leonard
%A Zhang, Aston
%A He, He
%A Zha, Sheng
%A Smola, Alexander
%Y Baldwin, Timothy
%Y Carpuat, Marine
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F lin-etal-2019-dive
%X Deep learning has become the dominant approach to NLP problems, especially when applied on large scale corpora. Recent progress on unsupervised pre-training techniques such as BERT, ELMo, GPT-2, and language modeling in general, when applied on large corpora, is shown to be effective in improving a wide variety of downstream tasks. These techniques push the limits of available hardware, requiring specialized frameworks optimized for GPU, ASIC, and distributed cloud-based training.A few complexities pose challenges to scale these models and algorithms effectively. Compared to other areas where deep learning is applied, these NLP models contain a variety of moving parts: text normalization and tokenization, word representation at subword-level and word-level, variable-length models such as RNN and attention, and sequential decoder based on beam search, among others.In this hands-on tutorial, we take a closer look at the challenges from these complexities and see how with proper tooling with Apache MXNet and GluonNLP, we can overcome these challenges and achieve state-of-the-art results for real-world problems. GluonNLP is a powerful new toolkit that combines MXNet’s speed, the flexibility of Gluon, and an extensive new library automating the most laborious aspects of deep learning for NLP.
%U https://aclanthology.org/D19-2001
Markdown (Informal)
[Dive into Deep Learning for Natural Language Processing](https://aclanthology.org/D19-2001) (Lin et al., EMNLP-IJCNLP 2019)
ACL
- Haibin Lin, Xingjian Shi, Leonard Lausen, Aston Zhang, He He, Sheng Zha, and Alexander Smola. 2019. Dive into Deep Learning for Natural Language Processing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts, Hong Kong, China. Association for Computational Linguistics.