# This is a combination of 7 commits.

# This is the 1st commit message:

Add paper, citations, and figures

# This is the commit message #2:

Fix citation DOIs

# This is the commit message #3:

Add missing DOIs

# This is the commit message #4:

Add citations without doi to ignorelist

# This is the commit message #5:

Add citation without doi to ignorelist

# This is the commit message #6:

Make revisions based on review, focus paper on toolkit's contents

# This is the commit message #7:

Add missing footnote url

papers/jyotika_singh/main.log

@@ -0,0 +1,6 @@
+This is pdfTeX, Version 3.141592653-2.6-1.40.22 (TeX Live 2021) (preloaded format=pdflatex 2021.12.27)  30 MAY 2024 18:00
+entering extended mode
+ restricted \write18 enabled.
+ %&-line parsing enabled.
+**main.tex
+(./main.tex

papers/jyotika_singh/mybib.bib

@@ -0,0 +1,259 @@
+@inbook{Jones1994,
+	title = {Natural Language Processing: A Historical Review},
+	ISBN = {9780585359588},
+	url = {http://dx.doi.org/10.1007/978-0-585-35958-8_1},
+	DOI = {10.1007/978-0-585-35958-8_1},
+	booktitle = {Current Issues in Computational Linguistics: In Honour of Don Walker},
+	publisher = {Springer Netherlands},
+	author = {Jones,  Karen Sparck},
+	year = {1994},
+	pages = {3–16}
+}
+
+@article{nepai,
+	url = {https://neptune.ai/blog/sentiment-analysis-python-textblob-vs-vader-vs-flair},
+	title={Sentiment Analysis in Python: TextBlob vs Vader Sentiment vs Flair vs Building It From Scratch},
+	publisher={Neptune.ai},
+	author={Shahul ES},
+	year = {2023},
+	month = aug,
+	day={30}
+
+}
+
+@article{textblob,
+	title={textblob Documentation},
+	author={Loria, Steven},
+	journal={Release 0.15},
+	volume={2},
+	year={2018}
+}
+
+@article{articleuse,
+	author = {Cer, Daniel and Yang, Yinfei and Kong, Sheng-yi and Hua, Nan and Limtiaco, Nicole and John, Rhomni and Constant, Noah and Guajardo-Cespedes, Mario and Yuan, Steve and Tar, Chris and Sung, Yun-Hsuan and Strope, Brian and Kurzweil, Ray},
+	year = {2018},
+	month = {03},
+	pages = {},
+	title = {Universal Sentence Encoder}
+}
+
+@article{vader, 
+	title={VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text}, 
+	volume={8}, url={https://ojs.aaai.org/index.php/ICWSM/article/view/14550}, 
+	DOI={10.1609/icwsm.v8i1.14550}, 
+	number={1}, 
+	journal={Proceedings of the International AAAI Conference on Web and Social Media}, 
+	author={Hutto, C. and Gilbert, Eric},
+	year={2014}, 
+	month={May}, 
+	pages={216-225}
+}
+
+@book{Singh2023,
+	title = {Natural Language Processing in the Real World: Text Processing,  Analytics,  and Classification},
+	ISBN = {9781003264774},
+	url = {http://dx.doi.org/10.1201/9781003264774},
+	DOI = {10.1201/9781003264774},
+	publisher = {Chapman and Hall/CRC},
+	author = {Singh,  Jyotika},
+	year = {2023},
+	month = may 
+}
+
+@article{tdsnlp,
+	title = {Natural Language Processing Tasks},
+	publisher = {Towards Data Science},
+	author = {Meyer,  Patrick},
+	year = {2021},
+	month = oct,
+	url={https://towardsdatascience.com/natural-language-processing-tasks-3278907702f3},
+	urldate={2024-05-31}
+}
+
+@article{audioIntro,
+	title={An introduction to audio processing and machine learning using Python},
+	url={https://opensource.com/article/19/9/audio-processing-machine-learning-python},
+	publisher={Opensource.com},
+	author={Singh,  Jyotika},
+	year = {2019},
+	month=Sep ,
+	urldate={2024-05-31}
+}
+
+@article{mklearn,
+	title={11 NLP Applications & Examples in Business},
+	publisher={Monkey Learn},
+	author={Wolff,  Rachel},
+	year={2020},
+	month=may,
+	day={20},
+	url={https://monkeylearn.com/blog/natural-language-processing-applications/},
+	urldate={2024-05-31}
+}
+
+@InProceedings{audio2022,
+	author={Singh, J},
+	title={py{A}udio{P}rocessing: {A}udio {P}rocessing, {F}eature {E}xtraction, and {M}achine {L}earning {M}odeling},
+	booktitle={{P}roceedings of the 21st {P}ython in {S}cience {C}onference},
+	pages={152-158},
+	year={2022},
+	doi={10.25080/majora-212e5952-017}
+}
+
+
+@article{nersd,
+	title={Named Entity Recognition},
+	publisher={Science Direct},
+	author={Science Direct},
+	url={https://www.sciencedirect.com/topics/computer-science/named-entity-recognition#featured-authors},
+	urldate={2024-05-31}
+}
+
+@InProceedings{ social2021,
+	author={ Singh, J},
+	title={{S}ocial {M}edia {A}nalysis using {N}atural {L}anguage {P}rocessing {T}echniques},
+	booktitle={{P}roceedings of the 20th {P}ython in {S}cience {C}onference},
+	pages={74-80},
+	year={2021},
+	doi={10.25080/majora-1b6fd038-009}
+}
+
+@article{kdnner,
+	author={Banerjee, Suvro},
+	title={Introduction to Named Entity Recognition},
+	url= {https://www.kdnuggets.com/2018/12/introduction-named-entity-recognition.html},
+	year= { 2018},
+	month=dec,
+	urldate={2024-05-31}
+}
+
+@article{attn,
+	doi = {10.48550/ARXIV.1706.03762},
+	url = {https://arxiv.org/abs/1706.03762},
+	author = {Vaswani,  Ashish and Shazeer,  Noam and Parmar,  Niki and Uszkoreit,  Jakob and Jones,  Llion and Gomez,  Aidan N. and Kaiser,  Lukasz and Polosukhin,  Illia},
+	keywords = {Computation and Language (cs.CL),  Machine Learning (cs.LG),  FOS: Computer and information sciences,  FOS: Computer and information sciences},
+	title = {Attention Is All You Need},
+	publisher = {arXiv},
+	year = {2017},
+	copyright = {arXiv.org perpetual,  non-exclusive license}
+}
+
+@inproceedings{jupyter,
+	author = {Kluyver, Thomas and Ragan-Kelley, Benjamin and Pérez, Fernando and Granger, Brian and Bussonnier, Matthias and Frederic, Jonathan and Kelley, Kyle and Hamrick, Jessica and Grout, Jason and Corlay, Sylvain and Ivanov, Paul and Avila, Damián and Abdalla, Safia and Willing, Carol and {Jupyter development team}},
+  	editor = {Loizides, Fernando and Scmidt, Birgit},
+  	location = {Netherlands},
+  	publisher = {IOS Press},
+  	url = {https://eprints.soton.ac.uk/403913/},
+  	booktitle = {Positioning and Power in Academic Publishing: Players, Agents and Agendas},
+  	year = {2016},
+  	pages = {87--90},
+  	title = {Jupyter Notebooks - a publishing format for reproducible computational workflows},
+}
+
+@inproceedings{stannlp,
+	url = {http://nlp.stanford.edu/~manning/papers/gibbscrf3.pdf},
+	author = {Jenny Rose Finkel, Trond Grenager, and Christopher Manninga},
+	title = {Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling},
+	publisher = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL 2005)},
+	year = {2005},
+	pages = {363--370},
+	doi = {http://dx.doi.org/10.3115/1219840.1219885}
+}
+
+@article{spacy,
+	author = {Honnibal, Matthew and Montani, Ines and Van Landeghem, Sofie and Boyd, Adriane},
+	title  = {spaCy: Industrial-strength Natural Language Processing in Python},
+	year   = {2020},
+	doi = {10.5281/zenodo.1212303}
+}
+
+@article{nltk,
+	doi = {10.48550/ARXIV.CS/0205028},
+	url = {https://arxiv.org/abs/cs/0205028},
+	author = {Loper,  Edward and Bird,  Steven},
+	keywords = {Computation and Language (cs.CL),  FOS: Computer and information sciences,  FOS: Computer and information sciences,  D.2.6; I.2.7; J.5; K.3.2},
+	title = {NLTK: The Natural Language Toolkit},
+	publisher = {arXiv},
+	year = {2002},
+	copyright = {Assumed arXiv.org perpetual,  non-exclusive license to distribute this article for submissions made before January 2004}
+}
+
+@article{matplotlib,
+	author = {Hunter, J. D.},
+	publisher = {IEEE COMPUTER SOC},
+	year = {2007},
+	doi = {https://doi.org/10.1109/MCSE.2007.55},
+	journal = {Computing in Science \& Engineering},
+  	number = {3},
+  	pages = {90--95},
+  	title = {Matplotlib: A 2D graphics environment},
+  	volume = {9},
+}
+
+@article{wordcloud,
+	title={WordCloud: a Cytoscape plugin to create a visual semantic summary of networks},
+	author = {Oesper, Layla and Merico, Daniele and Isserlin, Ruth and Bader, Gary D},
+	journal = {Source code for biology and medicine},
+	volume = {6},
+	number = {1},
+	pages = {7},
+	year = {2011},
+	doi = {http://dx.doi.org/10.1186/1751-0473-6-7},
+	publisher = {Springer}
+}
+
+@article{zsc,
+	url = {https://huggingface.co/tasks/zero-shot-classification},
+	title = {Zero-Shot Classification},
+	publisher = {Hugging Face},
+	author = {Hugging Face},
+	urldate = {2024-05-31}
+}
+
+@article{zscbench,
+	title = {Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach},
+	author = {Wenpeng Yin and Jamaal Hay and Dan Roth},
+	journal = {ArXiv},
+	year = {2019},
+	volume = {abs/1909.00161},
+	url = {https://api.semanticscholar.org/CorpusID:202540839},
+	doi = {http://dx.doi.org/10.18653/v1/D19-1404}
+}
+
+@inbook{2011,
+	ISBN = {9780387301648},
+	url = {http://dx.doi.org/10.1007/978-0-387-30164-8_832},
+	DOI = {10.1007/978-0-387-30164-8_832},
+	booktitle = {Encyclopedia of Machine Learning},
+	publisher = {Springer US},
+	year = {2011},
+	pages = {986–987}
+}
+
+
+@misc{cnn,
+	doi = {10.48550/ARXIV.1511.08458},
+	url = {https://arxiv.org/abs/1511.08458},
+	author = {O'Shea,  Keiron and Nash,  Ryan},
+	keywords = {Neural and Evolutionary Computing (cs.NE),  Computer Vision and Pattern Recognition (cs.CV),  Machine Learning (cs.LG),  FOS: Computer and information sciences,  FOS: Computer and information sciences},
+	title = {An Introduction to Convolutional Neural Networks},
+	publisher = {arXiv},
+	year = {2015},
+	copyright = {arXiv.org perpetual,  non-exclusive license}
+}
+
+@article{lda,
+	author = {Blei, David M. and Ng, Andrew Y. and Jordan, Michael I.},
+	title = {Latent dirichlet allocation},
+	year = {2003},
+	issue_date = {3/1/2003},
+	publisher = {JMLR.org},
+	volume = {3},
+	number = {null},
+	issn = {1532-4435},
+	journal = {J. Mach. Learn. Res.},
+	month = {mar},
+	pages = {993–1022},
+	numpages = {30},
+	doi={http://dx.doi.org/10.7551/mitpress/1120.003.0082}
+}

papers/jyotika_singh/myst.yml

@@ -0,0 +1,45 @@
+version: 1
+project:
+  # Update this to match `scipy-2024-<folder>` the folder should be `<firstname_surname>`
+  id: scipy-2024-jyotika_singh
+  title: Navigating Model Selection for NLP tasks
+  subtitle: Considerations for decision making and nlprw_toolkit
+  # Authors should have affiliations, emails and ORCIDs if available
+  authors:
+    - name: Jyotika Singh
+      email: [email protected]
+      orcid: 0000-0002-5442-3004
+      affiliations:
+        - Independent
+  keywords:
+    - NLP
+    - Natural Language Processing
+    - Language data
+  # Add the abbreviations that you use in your paper here
+  abbreviations:
+    NLP: Natural Language Processing
+  # It is possible to explicitly ignore the `doi-exists` check for certain citation keys
+  error_rules:
+    - rule: doi-exists
+      severity: ignore
+      keys:
+        - jupyter
+        - audioIntro
+        - tdsnlp
+        - mklearn
+        - kdnner
+        - zsc
+        - nersd
+        - nepai
+        - textblob
+        - articleuse
+  # A banner will be generated for you on publication, this is a placeholder
+  banner: banner.png
+  # The rest of the information shouldn't be modified
+  subject: Research Article
+  open_access: true
+  license: CC-BY-4.0
+  venue: Scipy 2024
+  date: 2024-07-10
+site:
+  template: article-theme