# Road Map for Learning Speech and Language We put here the excellent materials that we believe can help students learn about speech and language processing techniques. Materials are tentatively categorized by subject. If you feel there is a better way to organize them, please suggest. This is a temporary repository. In the future, we will move the content to an easily accessible place (such as the Github webpage). It would be nice to find helpful material from the IEEE Signal Processing Society Resource Center. https://rc.signalprocessingsociety.org/education.html ## General - [Speech and Language Processing (Textbook by Dan Jurufsky)](https://web.stanford.edu/~jurafsky/slp3/) - added by Cheng-Han Chiang - https://gitplanet.com/label/speech-processing (speech-processing open source projects) - added by Kuan Po Huang - [MLSS 2021 TAIPEI (Machine Learning Summer School)](https://ai.ntu.edu.tw/?page_id=4835) - added by Kuan Po Huang - https://www.youtube.com/watch?v=rmVRLeJRkl4&list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ (Stanford CS224N NLP with Deep Learning by Christopher Manning) - added by Juncheng Xie - https://www.youtube.com/watch?v=rha64cQRLs8&list=PLoROMvodv4rPt5D0zs3YhbWSZA8Q_DyiJ (Stanford CS224U Natural Language Understanding by Christopher Potts) - added by Juncheng Xie - [Open Speech Corpora](https://github.com/coqui-ai/open-speech-corpora) - added by Po-chun Hsu - https://www.youtube.com/watch?v=oWsMIW-5xUc&list=PLLssT5z_DsK8HbD2sPcUIDfQ7zmBarMYv (Stanford Natural Language Porcessing by Dan Jurafsky) - added by Yu Kuan Fu - https://www.nltk.org/book/ (manual for nature language toolkits) - added by Yu Kuan Fu - https://cseweb.ucsd.edu/~nnakashole/teaching/eisenstein-nov18.pdf (textbook for NLP, eisentein) - added by Yu Kuan Fu - [**IEEE SPS Education Center**: Natural Speech Technology](https://rc.signalprocessingsociety.org/workshops/SPSVID0085.html) (ASRU 2015 Natural Speech Technology) - added by Hsuan-Jui Chen ### Acoustic Feature * https://towardsdatascience.com/whats-wrong-with-spectrograms-and-cnns-for-audio-processing-311377d7ccd (Insights into the decline of spectrogram-based models) * Insights into the decline of spectrogram-based models * added by Yuan Tseng * http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/ * Brief Tutorial of MFCC * added by Yuan Tseng - https://medium.com/analytics-vidhya/understanding-the-mel-spectrogram-fca2afa2ce53 (Brief tutorial to Mel Spectrogram) - added by Wei-Ping Huang - [Mel-Frequency Cepstral Coefficients Explained Easily](https://www.youtube.com/watch?v=4_SH2nfbQZ8&ab_channel=ValerioVelardo-TheSoundofAI) - added by You-Cheng Jiang ### Model - https://nlp.seas.harvard.edu/2018/04/03/attention.html (Introduction for transformer with code) - added by Chin-Lun Fu - https://www.youtube.com/watch?v=LE3NfEULV6k (Transfer learning and Transformer models) - added by Chin-Lun Fu ### Toolkit - https://www.eleanorchodroff.com/tutorial/montreal-forced-aligner-v2.html (Montreal Force Aligner tutorial) - added by Wei-Ping Huang Zih-Ching Chen: - https://www.youtube.com/watch?v=8rXD5-xhemo&list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z (Stanford Introduction to NLP by Christopher Manning, 2019) - The link may be wrong. - Updated Kai-Wei Chang: - https://jalammar.github.io/illustrated-gpt2 (The Illustrated GPT-2 (Visualizing Transformer Language Models)) Shu-wen Yang: - [Kaldi Tutorial by Dan Povey](https://www.danielpovey.com/kaldi-lectures.html): step-by-step hands on tutorial - [ESPNet Tutorial](https://github.com/espnet/interspeech2019-tutorial): Interspeech 2019 tutorial materials - [SpeechBrain Tutorial](https://speechbrain.github.io/tutorial_basics.html): Colab collection - [Next generation of Kaldi: K2, Lhotse, Icefall, Interspeech 2021 Tutorial](https://www.bilibili.com/video/BV1AU4y177we/): I am not sure whether Bilibili is the link we can use... - [Sequence-to-sequence PyTorch implementation tutorial](https://github.com/bentrevett/pytorch-seq2seq): from simple to complex Seq-to-seq models with jupyter notebook - [Annotated Transformer by harvardnlp](https://github.com/harvardnlp/annotated-transformer): I learned how to implement Transformer right following this material... ## Speech Processing ### ASR - https://link.springer.com/book/10.1007/978-3-319-64680-0 (Introductory Book about recent deep learning approaches to ASR) - added by Yuan Tseng - https://www.youtube.com/watch?v=q67z7PTGRi8 (An overview of ASR) - added by Yu Kuan Fu - https://www.youtube.com/watch?v=YYNNTrSROa4&list=PLp-0K3kfddPzQXwzXpqmJmwbqGsoHqgyx (An introduction to RNN, CTC, attention-based model) - added by Yu Kuan Fu IEEE SPS education seasonal school: summer school 2021: - [Feature for Automatic Speech Recognition](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSEDU21VID021.html) - added by Wei-Tsung Kao - [Building Automatic Speech Recognition ASR System using Kaldi Toolkit, Librispeech](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSEDU21VID014.html) - added by Wei-Tsung Kao - [Builing Speech Recognition System for Indian Languages](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSEDU21VID017.html) - added by Wei-Tsung Kao - [Intuit Speech Recognition Systems - End to End ASR and Self Supervised Learning](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSEDU21VID033.html) - added by Wei-Tsung Kao - [**IEEE SPS Education Center**: ASR using GMM-HMM and Language model](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSEDU21VID011.html) - added by You-Cheng Jiang - [Sequence Modeling With CTC (distill)](https://distill.pub/2017/ctc/) - added by Heng-Jui Chang - [Kaldi Tutorial](https://www.eleanorchodroff.com/tutorial/kaldi/introduction.html) - added by Heng-Jui Chang - [Building an End-to-End Speech Recognition Model in PyTorch](https://www.assemblyai.com/blog/end-to-end-speech-recognition-pytorch/) - added by Chih-Chiang Chang - [**IEEE SPS Education Center**: End-to-End Speech Recognition Systems Explored](https://rc.signalprocessingsociety.org/workshops/mlsp/SPSVID00356.html) - added by Hsuan-Jui Chen ### TTS & Voice Conversion - Tutorial of Xu Tan and Tao Qin https://github.com/tts-tutorial/ijcai2021 - recommended by Abeer Alwan, added by Hung-yi Lee - [A Survey on Neural Speech Synthesis by Microsoft Research Asia](https://github.com/tts-tutorial/survey) - added by Po-chun Hsu - [ASRU 2015 Acoustic Modeling for Speech Synthesis by Heiga Zen](https://rc.signalprocessingsociety.org/workshops/SPSVID0075.html) - added by Po-chun Hsu - [Speech Synthesis on speech.zone](https://speech.zone/courses/speech-synthesis/) - added by Po-chun Hsu - [Theory and Practice of Voice Conversion by Sisman et al.](https://www.youtube.com/watch?v=R6vdUrqsuAs) - added by Po-chun Hsu - https://github.com/wenet-e2e/speech-synthesis-paper (TTS paper list) - added by Wei-Ping Huang ### Speech Enhancement / Speech Separation Kuan Po Huang: - https://github.com/Wenzhe-Liu/awesome-speech-enhancement (A Github repository that summarizes papers, codes, and tools for single-/multi-channel speech enhancement/speech separation.) - https://sigsep.github.io/ (Open Resources for Music Source Separation) - https://sigsep.github.io/tutorials/ (Tutorials and Overview Talks) - Current Trends in Audio Source Separation - Deep learning for music separation - Music Source Separation with DNNs, Making it work - [**IEEE SPS Education Center**: What is Spoken Language Technology -- Supervised Speech Separation](https://rc.signalprocessingsociety.org/other-topics/general-sps/SPSVID0096.html) Yuan Tseng: - https://github.com/JusperLee/Speech-Separation-Paper-Tutorial (Up-to-date speech separation paper list) - https://github.com/gemengtju/Tutorial_Separation (list of useful resources for speech separation) - https://dl.acm.org/doi/10.1109/TASLP.2018.2842159 (Old (2017) intro to speech separation) - https://source-separation.github.io/tutorial/landing.html (Intro & Tools for Source Separation) - https://hal.inria.fr/hal-01945345/document (Intro paper to Music Source Separation) Yuan Kuei Wu: - [**IEEE SPS Education Center**: Audio-Visual Speech Enhancement and Separation Based on Deep Learning: Part 3 Section 3: Conclusions and Future Works](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID1820.html) - [**IEEE SPS Education Center**: Tutorial 1 - Blind Audio Source Separation on Tensor Representation](https://rc.signalprocessingsociety.org/conferences/icassp/SPSVID00247.html) ### Speaker Identification / Verification / Diarization Chi-Luen Feng - https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speaker-recognition-overview(An overview of the speaker recognition by microsoft, also include the quick start session to help user to know how to use speaker recognition tech in Azure) - https://wiki.aalto.fi/display/ITSP/Speaker+Recognition+and+Verification (a page talk about speaker recognition and verification, besides it also talk about how to consturct i-vector, GMM method, and how to evaluate the performance) - https://arxiv.org/pdf/2012.00931.pdf (an overview of the speaker recognition paper) - https://keras.io/examples/audio/speaker_recognition_using_cnn/ (speaker recognition tutorial on Keras) - https://pytorch.org/tutorials/intermediate/speech_recognition_pipeline_tutorial.html (speaker recognition tutorial on Pytorch) Haibin-Wu - https://cis.cihe.edu.hk/video/20210320.mak.mp4#t=58 ("Deep Learning for Speaker Recognition", a tutorial for speaker recognition given by Professor Man Wai MAK in The Hong Kong Polytechnic University, in IEEE Workshop on Deep Learning, Hong Kong, March. 2021) - https://polyuit-my.sharepoint.com/personal/enmwmak_polyu_edu_hk/_layouts/15/onedrive.aspx?id=%2Fpersonal%2Fenmwmak%5Fpolyu%5Fedu%5Fhk%2FDocuments%2FDocuments%2FTeaching%2FEIE558%2F2021%2FEIE558%5FSpeakerRecognition1%2Emp4&parent=%2Fpersonal%2Fenmwmak%5Fpolyu%5Fedu%5Fhk%2FDocuments%2FDocuments%2FTeaching%2FEIE558%2F2021&ga=1 (very comprehensive and detailed speaker recognition tutorial from Professor Man Wai MAK in The Hong Kong Polytechnic University - part 1) - https://polyuit-my.sharepoint.com/personal/enmwmak_polyu_edu_hk/_layouts/15/onedrive.aspx?id=%2Fpersonal%2Fenmwmak%5Fpolyu%5Fedu%5Fhk%2FDocuments%2FDocuments%2FTeaching%2FEIE558%2F2021%2FEIE558%5FSpeakerRecognition2%2Emp4&parent=%2Fpersonal%2Fenmwmak%5Fpolyu%5Fedu%5Fhk%2FDocuments%2FDocuments%2FTeaching%2FEIE558%2F2021&ga=1 (very comprehensive and detailed speaker recognition tutorial from Professor Man Wai MAK in The Hong Kong Polytechnic University - part 2) ### Speech Translation (Spoken language processing?) Hsiang-Sheng Tsai: * https://github.com/dqqcasia/awesome-speech-translation (speech translation paper) * [Literature Survey : Spoken Language Translation](https://www.cfilt.iitb.ac.in/resources/surveys/Sanket_SurveyPaper_SPKMT.pdf) Chih-Chiang Chang: * EACL 2021 tutorial: [Speech Translation](https://st-tutorial.github.io/overview/) * Blog: [Getting Started with End-to-End Speech Translation](https://towardsdatascience.com/getting-started-with-end-to-end-speech-translation-3634c35a6561) * INTERSPEECH 2019 survey talk: [Spoken Language Translation](https://www.youtube.com/watch?v=beB5L6rsb0I) * Toolkits, Datasets for ST, ASR, MT (https://st-benchmark.github.io/resources/#toolkits) ### Spoken Document Retrieval Chyi-Jiunn Lin: - [Spoken Content Retrieval – Beyond Cascading Speech Recognition with Text Retrieval](https://speech.ee.ntu.edu.tw/~tlkagk/paper/Overview.pdf) ### Spoken Language Understanding Chyi-Jiunn Lin: - [Spoken Language Understanding: Interpreting the signs given by a speech signal](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=4490201) - [Spoken Language Understanding: An introduction to the statistical framework](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1511821) ### Prosody Nigel Ward: - [Prosody Research and Applications, short tutorial at Interspeech 2019] (https://www.youtube.com/watch?v=uyW0pOAKRME) ### more ... ## Natural Langauge Processing ### Question Answering Andy T. Liu: - https://towardsdatascience.com/question-answering-with-a-fine-tuned-bert-bc4dafd45626 (QA tutorial and code implementation with the BERT model) Darong Liu： https://github.com/seriousran/awesome-qa (an github repo tracking all research topic related to QA) Chyi-Jiunn Lin: - [xanhho/Reading-Comprehension-Question-Answering-Papers](https://github.com/xanhho/Reading-Comprehension-Question-Answering-Papers) ### Open-Domain Question Answering Chyi-Jiunn Lin: - [T8: Open-Domain Question Answering](https://github.com/danqi/acl2020-openqa-tutorial) (ACL 2020 tutorial by Danqi Chen) - [How to Build an Open-Domain Question Answering System?](https://lilianweng.github.io/posts/2020-10-29-odqa/) - [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://arxiv.org/abs/2101.00774) ### Conversational AI #### Task-oriented Dialogue Hsuan Su: - https://youtu.be/eAncgjQjqlE (Interactive Learning of Task-Oriented Dialog Systems) - https://docs.google.com/document/d/1ZiZErpg1DQ_m7PsgOr4hvTVaT3qi7ZKykRwvDPYT7NU/edit?usp=sharing (data sets for dialogue state tracking) - #### Open-domain Dialogue ### Syntactic Parsing Yuan Tseng: - https://github.com/tukw/unsupervised-parsing-tutorial (Intro to recent developments in unsupervised constituency/dependency parsing) ### Machine Translation Juncheng Xie: - https://www.youtube.com/watch?v=DuYkqCQEbpo&list=PLQrCiUDqDLG0lQX54o9jB4phJ-SLI6ZBQ (Machine Translation by Philipp Koehn) - https://github.com/THUNLP-MT/MT-Reading-List (A paper list for NMT) - https://www.virtual2021.eacl.org/tutorial_T1.html (Advances and Challenges in Unsupervised Neural Machine Translation by Wang and Zhao) Shen-Sian Syu: - [Sequence to Sequence Translation](https://drive.google.com/file/d/18J0RTgezne5rfu5f9ryaA4Yu1V567q28/view) - UW, Noah Smith , 2021 Chih-Chiang Chang: - EMNLP 2020 Tutorial T6: Simultaneous Translation. [video](https://virtual.2020.emnlp.org/tutorial_T6.html) [slides](http://mingboma.com/pdf/emnlp_tutorial_2020.pdf) - [Neural Machine Translation and Sequence-to-sequence Models: A Tutorial](https://arxiv.org/abs/1703.01619) ### Low-Resource Languages Wei-Ping Huang - https://github.com/RichardLitt/low-resource-languages (Tools for Low-Resource Language processing) ### Natural Language Understanding Chyi-Jiunn Lin: - [Natural Language Understanding: Foundations and State-of-the-Art](https://www.youtube.com/watch?v=mhHfnhh-pB4) (ICML 2015 tutorial by Percy Liang) ### Natural Langauge Processing Shen-Sian Syu - [Natural Language Processing, course in CMU, Spring 2021, 11-411 / 11-611](http://demo.clab.cs.cmu.edu/NLP/#schedule) - [Multilingual Natural Language Process, course in CMU, Fall 2020, 11-737](http://demo.clab.cs.cmu.edu/11737fa20/) - [Natural Language Processing, course in UW, Noah A. Smith, Spring 2017, CSEP 517](https://courses.cs.washington.edu/courses/csep517/17sp/) ## Technology ### Interpretability of Speech and Language Models Cheng-Han Chiang - https://github.com/Eric-Wallace/interpretability-tutorial-emnlp2020 (Interpreting Predictions of NLP Models, EMNLP 2020 Tutorial) ### Self-supervised Learning for speech and language Andy T. Liu: - https://neptune.ai/blog/self-supervised-learning (a general tutorial, but it covers most of the important aspects) - [**IEEE SPS Education Center**: Self-Supervised Learning: the Future of Signal Understanding](https://rc.signalprocessingsociety.org/conferences/icip/SPSVID00415.html) (I'm guessing this is a more general kind of tutorial / talk) - [**IEEE SPS Education Center**: Similarity Analysis Of Self-Supervised Speech Representations](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID0371.html) (The authors include Yu-An Chung and James Glass, many of us are familiar with their work) Kuan Po Huang: [**IEEE SPS Education Center**: Self-Supervised Adversarial Training](https://rc.signalprocessingsociety.org/conferences/icassp-2020/SPSICASSP20VID0549.html) Guan-Ting Lin: - [**IEEE SPS Education Center**: Semi-Supervised Spoken Language Understanding Via Self-Supervised Speech And Language Model Pretraining](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID0431.html) Darong Liu： https://github.com/jason718/awesome-self-supervised-learning (includes all ssl research in cv, nlp and speech) Yuan-Kuei Wu - [Awesome-Speech-Pretraining](https://github.com/ddlBoJack/Awesome-Speech-Pretraining) ### Meta Learning for speech and language Guan-Ting Lin: * [**IEEE SPS Education Center**: Meta Learning For End-To-End Low-Resource Speech Recognition](https://rc.signalprocessingsociety.org/conferences/icassp-2020/SPSICASSP20VID0544.html) Sung-Feng Huang * [Meta-Learning: Learning to Learn Fast](https://lilianweng.github.io/posts/2018-11-30-meta-learning/) (Meta-learning general tutorial) * [Learning to learn](https://bair.berkeley.edu/blog/2017/07/18/learning-to-learn/) (Chelsea Finn blog for general meta-learning introduction) * [Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning](https://sites.google.com/view/icml19metalearning) (ICML 2019 Meta-Learning Tutorial) * [AAAI 2021 Meta Learning Tutorial](https://sites.google.com/mit.edu/aaai2021metalearningtutorial/home) * [Meta-Learning in Neural Networks: A Survey](https://ieeexplore.ieee.org/document/9428530) (Overall meta-learning definition/application) * [Meta Learning for Natural Language Processing: A Survey](https://openreview.net/pdf?id=5FENjGCL0Eu) * [**IEEE SPS Education Center**: Plenary V: Advancing Technological Equity In Speech And Language Processing](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID1810.html) Kuan Po Huang: - [**IEEE SPS Education Center**: T-5: Meta Learning and its applications to Human Language Processing: Part 5](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID1817.html) (Tutorial of meta NLP by Hung-yi Lee) - [ACL 2021 Meta-learning for NLP](https://meta-nlp-2021.github.io/#home) (ACL 2021 workshop) Shih-Cheng Huang: - [Stanford CS330: Multi-Task and Meta-Learning, 2019](https://www.youtube.com/playlist?list=PLoROMvodv4rMC6zfYmnD7UG3LVvwaITY5) (Meta-Learning general tutorial by Chelsea Finn) - [Interspeech 2020 special session](https://sunprinces.github.io/interspeech2020-meta-learning/) (Special session of Meta-Learning for Human Language Technology) ### Generative Adversarial Network for speech and language Darong Liu： - [**IEEE SPS Education Center**: Tutorial 7 - Generative Adversarial Network and its Applications on Speech Signal and Natural Language Processing](https://rc.signalprocessingsociety.org/conferences/icassp/SPSVID00252.html) (gan tutorial in 2018 icassp by Pf. Hung-Yi Lee) Shih-Cheng Huang: - [Generative Adversarial Networks for Text Generation — Part 1](https://becominghuman.ai/generative-adversarial-networks-for-text-generation-part-1-2b886c8cab10) (Introduction of GAN on text generation and its issues) - [Generative Adversarial Networks for Text Generation — Part 2](https://becominghuman.ai/generative-adversarial-networks-for-text-generation-part-2-rl-1bc18a2b8c60) (RL ways to overcome the issues) - [Generative Adversarial Networks for Text Generation — Part 3](https://becominghuman.ai/generative-adversarial-networks-for-text-generation-part-3-non-rl-methods-70d1be02350b) (Non-RL ways to overcome the issues) ### Adversarial Attack for speech and language Yen Meng: - [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://proceedings.mlr.press/v97/qin19a/qin19a.pdf) - [**IEEE SPS Education Center**: Adversarial Attacks On Audio Source Separation](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID0932.html) - [**IEEE SPS Education Center**: Class-Conditional Defense Gan Against End-To-End Speech Attacks](https://rc.signalprocessingsociety.org/conferences/icassp-2021/SPSICASSP21VID0845.html) Cheng-Han Chiang - [Robustness and Adversarial Examples in Natural Language Processing (EMNLP 2021 Tutorial)](https://robustnlp-tutorial.github.io/) - [**IEEE SPS Education Center**: Privacy Assessment Of Federated Learning Using Private Personalized Layers](https://rc.signalprocessingsociety.org/workshops/mlsp-2021/MLSP21VID0036.html) ### Life-long learning for speech and language ### Energy-Based Models for Speech and Language * Energy-Based Models with Applications to Speech and Language Processing ICASSP2022 Tutorial, Singapore, 22 May, 2022 slides & videos: http://oa.ee.tsinghua.edu.cn/~ouzhijian/ICASSP2022/index.html - added by Zhijian Ou ### Tiny ML for speech and language Tzu Hsun Joseph Feng: - [Awesome-Pruning](https://github.com/he-y/Awesome-Pruning ) (Pruning related paper collection) - [An Overview of Model Cpmpression Techniques for Deep Learning in Space](https://medium.com/gsi-technology/an-overview-of-model-compression-techniques-for-deep-learning-in-space-3fd8d4ce84e5) (General tutorial about model compression) - [Neural Magic’s five-part blog series on pruning in machine learning](https://neuralmagic.com/blog/pruning-overview/) - Seasonal Schools - [**IEEE SPS Education Center**: Sparse Representations in signal Processing](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSVID00275.html) - [**IEEE SPS Education Center**: Low Dimensional Models and Dimensionality Reduction](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSVID00277.html) - [**IEEE SPS Education Center**: Introduction to Compression](https://rc.signalprocessingsociety.org/education/seasonal-schools/SPSVID00279.html) (not sure) ### Fairness for speech and language Hsuan Su - http://web.cs.ucla.edu/~kwchang/talks/emnlp19-fairnlp/ (Introduction of Bias & Fairness in NLP) - https://github.com/uclanlp/awesome-fairness-papers Zih-Ching Chen - https://facctconference.org/static/tutorials/chang_wordembed.pdf Chin-Lun Fu - https://guide.allennlp.org/fairness (Intro for Fairness and Bias Mitigation) Shih-Cheng Huang - [Reducing Toxicity in Language Models](https://lilianweng.github.io/posts/2021-03-21-lm-toxicity/) (Introduction of Detoxification) ### Multimodality Language Processing Cheng-Han Chiang - [MultiModal Machine Learning, course in CMU, Fall 2020](https://cmu-multicomp-lab.github.io/mmml-course/fall2020/) ### Reinforcement Learning for Language Processing Hsuan Su - https://sites.cs.ucsb.edu/~william/papers/ACL2018DRL4NLP.pdf (RL4NLP) ### Machine Reasoning Chyi-Jiunn Lin: - [Neural Machine Reasoning](https://neuralreasoning.github.io/) (IJCAI 2021 tutorial) ### Knowledge Distillation Shen-Sian Syu - [Understanding Knowledge Distillation in Neural Sequence Generation](https://www.microsoft.com/en-us/research/video/understanding-knowledge-distillation-in-neural-sequence-generation/) - Microsoft, Jiatao Gu, First propose NAT Model. ## Parameter Efficient NLP Zih-Ching Chen - https://www.youtube.com/watch?v=Hp5wBKeEDyY (Adapters in NLP by Jonas Pfeiffer, the author of AdapterFusion, AdapterDrop, and AdapterHub) - https://adapterhub.ml/ - [Colab Tutorial for adapters](https://github.com/Adapter-Hub/adapter-transformers/tree/master/notebooks) Chin-Lun Fu - https://chowdera.com/2022/01/202201101722246262.html (prompt learning tutorial) - https://github.com/thunlp/PromptPapers (prompt paper) You-Cheng Jiang - [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://arxiv.org/abs/2107.13586)