{"id":16516829,"url":"https://github.com/adamspannbauer/cs224n","last_synced_at":"2026-06-13T09:02:40.248Z","repository":{"id":83432071,"uuid":"357573125","full_name":"AdamSpannbauer/cs224n","owner":"AdamSpannbauer","description":null,"archived":false,"fork":false,"pushed_at":"2021-04-21T10:32:50.000Z","size":43183,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-11-29T23:10:20.377Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AdamSpannbauer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-04-13T13:59:23.000Z","updated_at":"2022-01-18T08:03:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"a0211758-5b8e-4764-9185-8e39865c68dd","html_url":"https://github.com/AdamSpannbauer/cs224n","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AdamSpannbauer/cs224n","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamSpannbauer%2Fcs224n","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamSpannbauer%2Fcs224n/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamSpannbauer%2Fcs224n/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamSpannbauer%2Fcs224n/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdamSpannbauer","download_url":"https://codeload.github.com/AdamSpannbauer/cs224n/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamSpannbauer%2Fcs224n/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34278154,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-13T02:00:06.617Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-11T16:27:05.532Z","updated_at":"2026-06-13T09:02:39.241Z","avatar_url":"https://github.com/AdamSpannbauer.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Stanford CS224n: NLP with Deep Learning\r\n\r\n\r\n## Lectures\r\n\r\n[YouTube Playlist](https://www.youtube.com/playlist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z)\r\n\r\n## Schedule\r\n\r\nSee schedule below for ordering, assignemnts, and additional links.  For context on pacing, the class met every Tuesday and Thursday.\r\n\r\nBelow table copied from [here](http://web.stanford.edu/class/cs224n/index.html#schedule).\r\n\r\n\r\n\u003ctable class=\"table\"\u003e\r\n  \u003ccolgroup\u003e\r\n    \u003ccol style=\"width:20%\"\u003e\r\n    \u003ccol style=\"width:40%\"\u003e\r\n    \u003ccol style=\"width:10%\"\u003e\r\n    \u003ccol style=\"width:10%\"\u003e\r\n  \u003c/colgroup\u003e\r\n  \u003cthead\u003e\r\n  \u003ctr class=\"active\"\u003e\r\n    \u003cth\u003eDescription\u003c/th\u003e\r\n    \u003cth\u003eCourse Materials\u003c/th\u003e\r\n    \u003cth\u003eEvents\u003c/th\u003e\r\n    \u003cth\u003eDeadlines\u003c/th\u003e\r\n  \u003c/tr\u003e\r\n  \u003c/thead\u003e\r\n  \u003ctbody\u003e\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eWord Vectors\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture01-wordvecs1.pdf\"\u003eslides\u003c/a\u003e]\r\n      \u003c!--[\u003ca href=\"https://stanford-pilot.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=b2acdfb7-8038-49fb-941e-ab25012bd9ec\"\u003evideo\u003c/a\u003e]--\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes01-wordvecs1.pdf\"\u003enotes\u003c/a\u003e]\r\n      \u003cbr\u003e\u003cbr\u003e\r\n      Gensim word vectors example:\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/materials/Gensim.zip\"\u003ecode\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/materials/Gensim%20word%20vector%20visualization.html\"\u003epreview\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"http://arxiv.org/pdf/1301.3781.pdf\"\u003eEfficient Estimation of Word Representations in Vector Space\u003c/a\u003e (original word2vec paper)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf\"\u003eDistributed Representations of Words and Phrases and their Compositionality\u003c/a\u003e (negative sampling paper)\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Assignment 1 \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a1.zip\"\u003ecode\u003c/a\u003e]\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a1_preview/exploring_word_vectors.html\"\u003epreview\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eWord Vectors 2 and Word Window Classification\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture02-wordvecs2.pdf\"\u003eslides\u003c/a\u003e]\r\n      \u003c!--[\u003ca href=\"\"\u003evideo\u003c/a\u003e]--\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes02-wordvecs2.pdf\"\u003enotes\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"http://nlp.stanford.edu/pubs/glove.pdf\"\u003eGloVe: Global Vectors for Word Representation\u003c/a\u003e (original GloVe paper)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.aclweb.org/anthology/Q15-1016\"\u003eImproving Distributional Similarity with Lessons Learned from Word Embeddings\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.aclweb.org/anthology/D15-1036\"\u003eEvaluation methods for unsupervised word embeddings\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n      Additional Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"http://aclweb.org/anthology/Q16-1028\"\u003eA Latent Variable Model Approach to PMI-based Word Embeddings\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://transacl.org/ojs/index.php/tacl/article/viewFile/1346/320\"\u003eLinear Algebraic Structure of Word Senses, with Applications to Polysemy\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://papers.nips.cc/paper/7368-on-the-dimensionality-of-word-embedding.pdf\"\u003eOn the Dimensionality of Word Embedding\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr class=\"warning\"\u003e\r\n    \u003ctd\u003ePython Review Session\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-python-review-code-updated.zip\"\u003ecode\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-python-review-code-updated.pdf\"\u003epreview\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      \u003ci class=\"fa fa-clock-o\"\u003e\u003c/i\u003e 10:00am - 11:20am\u003c!--\u003cbr\u003e160-124 [\u003ca href=\"https://campus-map.stanford.edu/\"\u003emap\u003c/a\u003e]--\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eBackprop and Neural Networks\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture03-neuralnets.pdf\"\u003eslides\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes03-neuralnets.pdf\"\u003enotes\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/gradient-notes.pdf\"\u003ematrix calculus notes\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/review-differential-calculus.pdf\"\u003eReview of differential calculus\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://cs231n.github.io/neural-networks-1/\"\u003eCS231n notes on network architectures\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://cs231n.github.io/optimization-2/\"\u003eCS231n notes on backprop\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://cs231n.stanford.edu/handouts/derivatives.pdf\"\u003eDerivatives, Backpropagation, and Vectorization\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.iro.umontreal.ca/~vincentp/ift3395/lectures/backprop_old.pdf\"\u003eLearning Representations by Backpropagating Errors\u003c/a\u003e (seminal Rumelhart et al. backpropagation paper)\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n      Additional Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"https://medium.com/@karpathy/yes-you-should-understand-backprop-e2f06eab496b\"\u003eYes you should understand backprop\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.jmlr.org/papers/volume12/collobert11a/collobert11a.pdf\"\u003eNatural Language Processing (Almost) from Scratch\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Assignment 2 \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a2.zip\"\u003ecode\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a2.pdf\"\u003ehandout\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 1 \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eDependency Parsing\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture04-dep-parsing.pdf\"\u003eslides\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes04-dependencyparsing.pdf\"\u003enotes\u003c/a\u003e]\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"slides/cs224n-2021-lecture04-dep-parsing-annotated.pdf\"\u003eslides (annotated)\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"https://www.aclweb.org/anthology/W/W04/W04-0308.pdf\"\u003eIncrementality in Deterministic Dependency Parsing\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://www.emnlp2014.org/papers/pdf/EMNLP2014082.pdf\"\u003eA Fast and Accurate Dependency Parser using Neural Networks\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.morganclaypool.com/doi/abs/10.2200/S00169ED1V01Y200901HLT002\"\u003eDependency Parsing\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1603.06042.pdf\"\u003eGlobally Normalized Transition-Based Neural Networks\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://nlp.stanford.edu/~manning/papers/USD_LREC14_UD_revision.pdf\"\u003eUniversal Stanford Dependencies: A cross-linguistic typology\u003c/a\u003e\u003c/li\u003e\u003ca href=\"http://nlp.stanford.edu/~manning/papers/USD_LREC14_UD_revision.pdf\"\u003e\r\n        \u003c/a\u003e\u003cli\u003e\u003ca href=\"http://nlp.stanford.edu/~manning/papers/USD_LREC14_UD_revision.pdf\"\u003e\u003c/a\u003e\u003ca href=\"http://universaldependencies.org/\"\u003eUniversal Dependencies website\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr class=\"warning\"\u003e\r\n    \u003ctd\u003ePyTorch Tutorial Session\r\n    \u003cbr\u003e\r\n      [\u003ca href=\"https://colab.research.google.com/drive/1Z6K6nwbb69XfuInMx7igAp-NNVj_2xc3?usp=sharing\"\u003ecolab notebook\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/materials/CS224N_PyTorch_Tutorial.html\"\u003epreview\u003c/a\u003e]\r\n    \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/materials/CS224N PyTorch Tutorial.ipynb\"\u003ejupyter notebook\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      \u003ci class=\"fa fa-clock-o\"\u003e\u003c/i\u003e 10:00am - 11:20am\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eRecurrent Neural Networks and Language Models\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture05-rnnlm.pdf\"\u003eslides\u003c/a\u003e]\r\n       [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes05-LM_RNN.pdf\"\u003enotes (lectures 5 and 6)\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"https://web.stanford.edu/~jurafsky/slp3/3.pdf\"\u003eN-gram Language Models\u003c/a\u003e (textbook chapter)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://karpathy.github.io/2015/05/21/rnn-effectiveness/\"\u003eThe Unreasonable Effectiveness of Recurrent Neural Networks\u003c/a\u003e (blog post overview)\u003c/li\u003e\r\n        \u003c!-- \u003cli\u003e\u003ca href=\"http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/\"\u003eRecurrent Neural Networks Tutorial\u003c/a\u003e (practical guide)\u003c/li\u003e --\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.deeplearningbook.org/contents/rnn.html\"\u003eSequence Modeling: Recurrent and Recursive Neural Nets\u003c/a\u003e (Sections 10.1 and 10.2)\u003c/li\u003e\r\n       \u003cli\u003e\u003ca href=\"http://norvig.com/chomsky.html\"\u003eOn Chomsky and the Two Cultures of Statistical Learning\u003c/a\u003e\r\n      \u003c/li\u003e\u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 3 \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n        \u003cbr\u003e\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a3.zip\"\u003ecode\u003c/a\u003e]\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a3.pdf\"\u003ehandout\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 2 \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eVanishing Gradients, Fancy RNNs, Seq2Seq\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture06-fancy-rnn.pdf\"\u003eslides\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes05-LM_RNN.pdf\"\u003enotes (lectures 5 and 6)\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"http://www.deeplearningbook.org/contents/rnn.html\"\u003eSequence Modeling: Recurrent and Recursive Neural Nets\u003c/a\u003e (Sections 10.3, 10.5, 10.7-10.12)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://ai.dinfo.unifi.it/paolo//ps/tnn-94-gradient.pdf\"\u003eLearning long-term dependencies with gradient descent is difficult\u003c/a\u003e (one of the original vanishing gradient papers)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1211.5063.pdf\"\u003eOn the difficulty of training Recurrent Neural Networks\u003c/a\u003e (proof of vanishing gradient problem)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174/lectures/vanishing_grad_example.html\"\u003eVanishing Gradients Jupyter Notebook\u003c/a\u003e (demo for feedforward networks)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://colah.github.io/posts/2015-08-Understanding-LSTMs/\"\u003eUnderstanding LSTM Networks\u003c/a\u003e (blog post overview)\u003c/li\u003e\r\n        \u003c!-- \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1504.00941.pdf\"\u003eA simple way to initialize recurrent networks of rectified linear units\u003c/a\u003e\u003c/li\u003e --\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eMachine Translation, Attention, Subword Models\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture07-nmt.pdf\"\u003eslides\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes06-NMT_seq2seq_attention.pdf\"\u003enotes\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1162/syllabus.shtml\"\u003eStatistical Machine Translation slides, CS224n 2015\u003c/a\u003e (lectures 2/3/4)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://www.cambridge.org/core/books/statistical-machine-translation/94EADF9F680558E13BE759997553CDE5\"\u003eStatistical Machine Translation\u003c/a\u003e (book by Philipp Koehn)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://www.aclweb.org/anthology/P02-1040.pdf\"\u003eBLEU\u003c/a\u003e (original paper)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1409.3215.pdf\"\u003eSequence to Sequence Learning with Neural Networks\u003c/a\u003e (original seq2seq NMT paper)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1211.3711.pdf\"\u003eSequence Transduction with Recurrent Neural Networks\u003c/a\u003e (early seq2seq speech recognition paper)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1409.0473.pdf\"\u003eNeural Machine Translation by Jointly Learning to Align and Translate\u003c/a\u003e (original seq2seq+attention paper)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://distill.pub/2016/augmented-rnns/\"\u003eAttention and Augmented Recurrent Neural Networks\u003c/a\u003e (blog post overview)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1703.03906.pdf\"\u003eMassive Exploration of Neural Machine Translation Architectures\u003c/a\u003e (practical advice for hyperparameter choices)\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/abs/1604.00788.pdf\"\u003eAchieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1808.09943.pdf\"\u003eRevisiting Character-Based Neural Machine Translation with Capacity and Compression\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 4 \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n        \u003cbr\u003e\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a4.zip\"\u003ecode\u003c/a\u003e]\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a4.pdf\"\u003ehandout\u003c/a\u003e]\r\n        [\u003ca href=\"https://docs.google.com/document/d/1BQOAjhBxWbywkB4rMFH9iinb6YHSjaWw1TOVlGfyYho/edit#heading=h.4tqnggp12z76\"\u003eAzure Guide\u003c/a\u003e]\r\n        [\u003ca href=\"https://docs.google.com/document/d/1jtANWXbIYXMZO_2X7jupauPxcEbz-TVJkdatg4gzOdk/edit\"\u003ePractical Guide to VMs\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 3 \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eFinal Projects: Custom and Default; Practical Tips\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture08-final-project.pdf\"\u003eslides\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/final-project-practical-tips.pdf\"\u003enotes\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"https://www.deeplearningbook.org/contents/guidelines.html\"\u003ePractical Methodology\u003c/a\u003e (\u003ci\u003eDeep Learning\u003c/i\u003e book chapter)\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eProject Proposal \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n        \u003cbr\u003e\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/project/project-proposal-instructions-2021.pdf\"\u003einstructions\u003c/a\u003e]\r\n        \u003cbr\u003e\u003cbr\u003e\r\n        Default Final Project \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n        \u003cbr\u003e\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/project/default-final-project-handout-squad-track.pdf\"\u003ehandout (IID SQuAD track)\u003c/a\u003e]\r\n        \u003cbr\u003e\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/project/default-final-project-handout-robustqa-track.pdf\"\u003ehandout (Robust QA track)\u003c/a\u003e]\r\n        \u003c!--[\u003ca href=\"https://github.com/minggg/squad\"\u003ecode\u003c/a\u003e]--\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eTransformers \u003ci\u003e(lecture by \u003ca href=\"https://nlp.stanford.edu/~johnhew/\"\u003eJohn Hewitt\u003c/a\u003e)\u003c/i\u003e\r\n    \u003cbr\u003e\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture09-transformers.pdf\"\u003eslides\u003c/a\u003e]\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes07-QA.pdf\"\u003enotes\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\u003ca href=\"http://web.stanford.edu/class/cs224n/project/default-final-project-handout-squad-track.pdf\"\u003eProject Handout (IID SQuAD track)\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://web.stanford.edu/class/cs224n/project/default-final-project-handout-robustqa-track.pdf\"\u003eProject Handout (Robust QA track)\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/abs/1706.03762.pdf\"\u003eAttention Is All You Need\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://jalammar.github.io/illustrated-transformer/\"\u003eThe Illustrated Transformer\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://ai.googleblog.com/2017/08/transformer-novel-neural-network.html\"\u003eTransformer (Google AI blog post)\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1607.06450.pdf\"\u003eLayer Normalization\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1802.05751.pdf\"\u003eImage Transformer\u003c/a\u003e\u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"https://arxiv.org/pdf/1809.04281.pdf\"\u003eMusic Transformer: Generating music with long-term structure\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eMore about Transformers and Pretraining \u003ci\u003e(lecture by \u003ca href=\"https://nlp.stanford.edu/~johnhew/\"\u003eJohn Hewitt\u003c/a\u003e)\u003c/i\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture10-pretraining.pdf\"\u003eslides\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/readings/cs224n-2019-notes07-QA.pdf\"\u003enotes\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n    Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/1810.04805.pdf\"\u003eBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n           \u003ca href=\"https://arxiv.org/abs/1902.06006.pdf\"\u003eContextual Word Representations: A Contextual Introduction\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\u003ca href=\"http://jalammar.github.io/illustrated-bert/\"\u003eThe Illustrated BERT, ELMo, and co.\u003c/a\u003e\u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 5 \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a5.zip\"\u003ecode\u003c/a\u003e]\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/assignments/a5.pdf\"\u003ehandout\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 4 \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eQuestion Answering \u003ci\u003e(guest lecture by \u003ca href=\"https://www.cs.princeton.edu/~danqic/\"\u003eDanqi Chen\u003c/a\u003e)\u003c/i\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture11-qa-v2.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n    Suggested Readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/1606.05250.pdf\"\u003eSQuAD: 100,000+ Questions for Machine Comprehension of Text\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/1611.01603.pdf\"\u003eBidirectional Attention Flow for Machine Comprehension\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/1704.00051.pdf\"\u003eReading Wikipedia to Answer Open-Domain Questions\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/1906.00300.pdf\"\u003eLatent Retrieval for Weakly Supervised Open Domain Question Answering\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/2004.04906.pdf\"\u003eDense Passage Retrieval for Open-Domain Question Answering\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/2012.12624.pdf\"\u003eLearning Dense Representations of Phrases at Scale\u003c/a\u003e\r\n        \u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003eProject Proposal \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eNatural Language Generation \u003ci\u003e(lecture by \u003ca href=\"https://atcbosselut.github.io/\"\u003eAntoine Bosselut\u003c/a\u003e)\u003c/i\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture12-generation.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n    Suggested readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/abs/1904.09751.pdf\"\u003eThe Curious Case of Neural Text Degeneration\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/abs/1704.04368.pdf\"\u003eGet To The Point: Summarization with Pointer-Generator Networks\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/abs/1805.04833.pdf\"\u003eHierarchical Neural Story Generation\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/abs/1603.08023.pdf\"\u003eHow NOT To Evaluate Your Dialogue System\u003c/a\u003e\r\n        \u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003e\u003ci\u003e\u003c/i\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003eProject Milestone \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/project/project-milestone-instructions-2021.pdf\"\u003einstructions\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003eAssignment 5 \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n      \u003ctd\u003eReference in Language and Coreference Resolution\r\n        \u003cbr\u003e\r\n        [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture13-coref.pdf\"\u003eslides\u003c/a\u003e]\r\n      \u003c/td\u003e\r\n    \u003ctd\u003e\r\n    Suggested readings:\r\n      \u003col\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://web.stanford.edu/~jurafsky/slp3/22.pdf\"\u003eCoreference Resolution chapter of Jurafsky and Martin\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n          \u003ca href=\"https://arxiv.org/pdf/1707.07045.pdf\"\u003eEnd-to-end Neural Coreference Resolution\u003c/a\u003e.\r\n        \u003c/li\u003e\r\n      \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eT5 and large language models: The good, the bad, and the ugly \u003ci\u003e(guest lecture by \u003ca href=\"https://colinraffel.com/\"\u003eColin Raffel\u003c/a\u003e)\u003c/i\u003e\r\n    \u003cbr\u003e\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture14-t5.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n    Suggested readings:\r\n    \u003col\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://colinraffel.com/publications/jmlr2020exploring.pdf\"\u003eExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer\u003c/a\u003e\r\n        \u003c/li\u003e\r\n    \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eIntegrating knowledge in language models \u003ci\u003e(lecture by \u003ca href=\"http://www.mleszczy.com\"\u003eMegan Leszczynski\u003c/a\u003e)\u003c/i\u003e\r\n    \u003cbr\u003e\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture15-lm.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\r\n    Suggested readings:\r\n    \u003col\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/pdf/1905.07129.pdf\"\u003eERNIE: Enhanced Language Representation with Informative Entities\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/pdf/1906.07241.pdf\"\u003eBarack’s Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://arxiv.org/pdf/1912.09637.pdf\"\u003ePretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model\u003c/a\u003e\r\n        \u003c/li\u003e\r\n        \u003cli\u003e\r\n        \u003ca href=\"https://www.aclweb.org/anthology/D19-1250.pdf\"\u003eLanguage Models as Knowledge Bases?\u003c/a\u003e\r\n        \u003c/li\u003e\r\n    \u003c/ol\u003e\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003eProject Milestone \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eSocial \u0026amp; Ethical Considerations in NLP Systems \u003ci\u003e(guest lecture by \u003ca href=\"http://www.cs.cmu.edu/~ytsvetko/\"\u003eYulia Tsvetkov\u003c/a\u003e)\u003c/i\u003e\r\n    \u003cbr\u003e\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture16-ethics.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eModel Analysis and Explanation \u003ci\u003e(lecture by \u003ca href=\"https://nlp.stanford.edu/~johnhew/\"\u003eJohn Hewitt\u003c/a\u003e)\u003c/i\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture17-analysis.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eFuture of NLP + Deep Learning \u003ci\u003e(lecture by \u003ca href=\"https://murtyshikhar.github.io/\"\u003eShikhar Murty\u003c/a\u003e)\u003c/i\u003e\r\n      \u003cbr\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/slides/cs224n-2021-lecture18-future.pdf\"\u003eslides\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003eProject Summary Image and Paragraph \u003cb\u003e\u003cfont color=\"green\"\u003eout\u003c/font\u003e\u003c/b\u003e\r\n    [\u003ca href=\"http://web.stanford.edu/class/cs224n/project/project-summary-instructions-2021.pdf\"\u003einstructions\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eAsk Me Anything / Final Project Assistance\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\r\n      Project \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\r\n      [\u003ca href=\"http://web.stanford.edu/class/cs224n/project/project-report-instructions-2021.pdf\"\u003einstructions\u003c/a\u003e]\r\n    \u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003eFinal Project Emergency Assistance\r\n    \u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003ctr\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003e\u003c/td\u003e\r\n    \u003ctd\u003eProject Summary Image and Paragraph \u003cb\u003e\u003cfont color=\"red\"\u003edue\u003c/font\u003e\u003c/b\u003e\r\n    \u003c/td\u003e\r\n  \u003c/tr\u003e\r\n\r\n  \u003c/tbody\u003e\r\n\u003c/table\u003e\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadamspannbauer%2Fcs224n","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadamspannbauer%2Fcs224n","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadamspannbauer%2Fcs224n/lists"}