《Python自然語言處理實戰》連結表

第1章

【Google Cloud API】 https://cloud.google.com/natural-language/

【Microsoft Azure的文字分析API】 https://azure.microsoft.com/is-is/services/concepting-services/text-analytics/

【Google Translate】 https://cloud.google.com/translate/

【AllenNLP的語義角色標記】 https://demo.allennlp.org/semantic-role-labeling

【Quepy】 http://quepy.machinalis.com/

【AllenNLP的機器閱讀理解】 http://demo.allennlp.org/machine-comprehension

【AllenNLP的文字蘊含】 http://demo.allennlp.org/textual-entailment

【AllenNLP的指代消解】 http://demo.allennlp.org/coreference-resolution

【Bing API】 https://azure.microsoft.com/zh-CN/services/cognitive-services/bing-web-search-api/

【聊天機器人的正規化】 https://aws.amazon.com/lex/details/

【Google文字轉語音】 https://cloud.google.com/text-to-speech/

【Google語音轉文字】 https://cloud.google.com/speech-to-text/

【AllenNLP的成分語法分析】 http://demo.allennlp.org/constituency-parsing

第3章

【CUDA下載頁面】 https://developer.nvidia.com/cuda-downloads

【cuDNN下載頁面】 https://developer.nvidia.com/cudnn

第5章

---

資料集名稱：源網址

IMDb movie Dataset：http://ai.stanford.edu/~amaas/data/sentiment/

Twiiter Sentiment Analysis Dataset：http://thinknook.com/twitter-sentiment-analysis-training-corpus-dataset-2012-09-22/

YouTube Spam Collection Dataset：https://archive.ics.uci.edu/ml/datasets/YouTube+Spam+Collection

News Aggregator Dataset：https://archive.ics.uci.edu/ml/datasets/News+Aggregator

Yelp reviews：https://www.yelp.com/dataset

Amazon reviews：http://jmcauley.ucsd.edu/data/amazon/

Reuters Corpora：http://trec.nist.gov/data/reuters/reuters.html

---

【第5章完整的公開資料集列表可從UCI庫（https://archive.ics.uci.edu/ml/datasets.html）和Kaggle（https://archive.ics.uci.edu/ml/datasets.html）獲取。】

【Latent Dirichlet Allocation】 https://dl.acm.org/citation.cfm?id=944937

【Large-scale Multi-label Text Classification – Revisiting Neural Networks】 https://arxiv.org/abs/1312.5419

【Bag of Tricks for Efficient Text Classification】 https://arxiv.org/abs/1607.01759

【Bag of Tricks for Efficient Text Classification】 https://arxiv.org/abs/1607.01759

【Deep Learning for Extreme Multi-label Text Classification】 https://dl.acm.org/citation.cfm?id=3080834

【Hierarchical Attention Networks for Document Classfication】 http://www.cs.cmu.edu/~./hovy/papers/16HLT-hierarchical-attention-networks.pdf

【GitHub專案richliao/textClassifier】 https://github.com/richliao/textClassifier

【GitHub專案ematvey/hierarchical-attention-networks】https://github.com/ematvey/hierarchical-attention-networks

第8章

【Linux核心檔案】 https://www.kernel.org/

【Abstractive Text Summarization Using Sequence-To-Sequence RNNs and Beyond】 https://arxiv.org/abs/1602.06023

【Get to the Point: Summarization with Pointer-Generator Networks】 https://arxiv.org/abs/1704.04368

【QA學術資料集】

---

資料集名稱：URL

bAbI text understanding tasks：https://research.fb.com/downloads/babi/

SQuAD: Stanford Question Answering Dataset：https://stanford-qa.com/

VQA: Visual Question Answering Dataset：http://www.visualqa.org/

AI2 Reasoning Challenge：http://data.allenai.org/arc/

---

【Memory Networks】 http://arxiv.org/abs/1410.3916

第9章

【End-to-End Memory Networks】 http://arxiv.org/abs/1503.08895

【Learning End-to-End Goal-Oriented Dialog】 http://arxiv.org/abs/1605.07683

【bAbI dialog資料集下載】 https://research.fb.com/downloads/babi/

---

論文標題：ArXiv URL

Dynamic Memory Networks (DMNs) and Dynamic Coattention Networks (DCNs)：https://arxiv.org/abs/1506.07285和https://arxiv.org/abs/1711.00106

Neural Turing Machines (NTMs) Differentiable Neural Computer (DNC)：https://arxiv.org/abs/1410.5401和https://www.nature.com/articles/nature20101

Seq2seq Memory Network：https://arxiv.org/pdf/1702.01932.pdf

Recurrent Entity Networks：https://arxiv.org/pdf/1612.03969.pdf

---

第10章

【Google Translate服務】 https://translate.google.com/

【TED演講的翻譯】 https://wit3.fbk.eu/mt.php?release=2015-0

第11章

【Jakobovski的免費數字音訊資料集】 https://github.com/Jakobovski/free-spoken-digit-dataset/tree/master/recording

【librosa】 https://github.com/librosa/librosa

【DeepSpeech模型原始論文】 https://arxiv.org/abs/1412.5567

【語言資料協會語音錄音下載】 https://www.kaggle.com/nltkdata/timitcorpus

【DeepSpeech在大型資料集上的實現】 https://github.com/mozilla/DeepSpeech

【Listen, Attend, and Spell: A Neural Network for Large Vocabulary Conversational Speech Recognition】 https://a.google/research/pubs/pub44926

【DeepSpeech模型的PyTorch實現】 https://github.com/XenderLiu/ListenAttend-and-Spell-Pytorc

第12章

【WaveNet: A Generative Model for Raw Audio】 https://arxiv.org/abs/1609.03499

【Tacotron】 https://arxiv.org/abs/1703.10135

【dropout】 http://jmlr.org/apers/v15/srivastava14a.html

【Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift】 https://arxiv.org/abs/1502.03167

【殘差連線】 https://arxiv.org/abs/1512.03385

【高速公路網路】 https://arxiv.org/abs/1505.00387

【Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation】 https://arxiv.org/abs/1609.08144

【Griffin-Lim】 https://ieeexplore.ieee.org/document/1164317/

【Adam優化器】 https://arxiv.org/abs/1412.6980

【LJ語音資料集】 https://keithito.com/LJ-SpeechDataset/

第13章

【TensorFlow Serving安裝指導】 https://www.tensorflow.org/serving/setup

【Google Cloud Platform】 https://cloud.google.com/

【CoreML2】 https://developer.apple.com/machine-learning/