References_CSP2021_ChristineChai.bib

% Data Preprocessing 

@article{chai2020importance,
  title={The Importance of Data Cleaning: Three Visualization Examples},
  author={Chai, Christine P},
  journal={CHANCE},
  volume={33},
  number={1},
  pages={4--9},
  year={2020},
  publisher={Taylor \& Francis}
}

@article{lohr2014bigdata,
  title = {For Big-Data Scientists, `Janitor Work' Is Key Hurdle to Insights},
  author = {Steve Lohr},
  journal = {The New York Times},
  year={2014},
  note={Available from: \url{https://www.nytimes.com/2014/08/18/technology/for-big-data-scientists-hurdle-to-insights-is-janitor-work.html}}
}

@inproceedings{gharehchopogh2011analysis,
  title={Analysis and evaluation of unstructured data: Text mining versus natural language processing},
  author={Gharehchopogh, Farhad Soleimanian and Khalifelu, Zeinab Abbasi},
  booktitle={2011 5th International Conference on Application of Information and Communication Technologies (AICT)},
  pages={1--4},
  year={2011},
  organization={IEEE}
}

@inproceedings{kalra2018importance,
  title={Importance of Text Data Preprocessing \& Implementation in {R}apid{M}iner},
  author={Kalra, Vaishali and Aggarwal, Rashmi},
  booktitle={Proceedings of the First International Conference on Information
Technology and Knowledge Management (ICITKM)},
  volume={14},
  pages={71--75},
  year={2018}
}

% ----------------------------------------------------------------------

% Text preprocessing and reproducibility
@article{roy2018clean,
  title={To Clean or Not to Clean: Document Preprocessing and Reproducibility},
  author={Roy, Dwaipayan and Mitra, Mandar and Ganguly, Debasis},
  journal={Journal of Data and Information Quality (JDIQ)},
  volume={10},
  number={4},
  pages={1--25},
  year={2018},
  publisher={ACM New York, NY, USA}
}

% Text Data Cleaning Literature
% Top Practical Books on Natural Language Processing
% https://machinelearningmastery.com/books-on-natural-language-processing/
% http://www.nltk.org/book/
% Book: Need to include a text data cleaning section
% 3. Processing Raw Text
@book{bird2009natural,
  title={Natural language processing with Python: Analyzing text with the natural language toolkit},
  author={Bird, Steven and Klein, Ewan and Loper, Edward},
  year={2009},
  publisher={O'Reilly Media Inc.}
}

% ELMo = Embeddings from Language Models
@article{peters2018deep,
  title={Deep contextualized word representations},
  author={Peters, Matthew E and Neumann, Mark and Iyyer, Mohit and Gardner, Matt and Clark, Christopher and Lee, Kenton and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:1802.05365},
  year={2018}
}

% BERT = Bidirectional Encoder Representations from Transformers (original paper)
% BERT supports ~100 different languages.
% https://github.com/google-research/bert/blob/master/multilingual.md
@article{devlin2018bert,
  title={{BERT}: Pre-training of deep bidirectional transformers for language understanding},
  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1810.04805},
  year={2018}
}

% GloVe = Global Vectors for Word Representation
% https://nlp.stanford.edu/projects/glove/
@inproceedings{pennington2014glove,
  title={{GloVe}: Global vectors for word representation},
  author={Pennington, Jeffrey and Socher, Richard and Manning, Christopher D},
  booktitle={Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)},
  pages={1532--1543},
  year={2014}
}

% word2vec
@article{mikolov2013efficient,
  title={Efficient estimation of word representations in vector space},
  author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
  journal={arXiv preprint arXiv:1301.3781},
  year={2013}
}

@inproceedings{wilson2020urban,
  title={Urban dictionary embeddings for slang {NLP} applications},
  author={Wilson, Steven and Magdy, Walid and McGillivray, Barbara and Garimella, Kiran and Tyson, Gareth},
  booktitle={Proceedings of The 12th Language Resources and Evaluation Conference},
  pages={4764--4773},
  year={2020}
}

% ----------------------------------------------------------------------

% Tokenization
@article{clough2001perl,
  title={A {Perl} program for sentence splitting using rules},
  author={Clough, Paul},
  journal={University of Sheffield},
  year={2001}
}

% ``Lexical richness is about the quality of vocabulary in a language sample.''
@article{malvern2012measures,
  title={Measures of lexical richness},
  author={Malvern, David and Richards, Brian},
  journal={The encyclopedia of applied linguistics},
  year={2012},
  publisher={Wiley Online Library}
}

@inproceedings{diaz2015analysis,
  title={An analysis of biomedical tokenization: Problems and strategies},
  author={D{\'\i}az, Noa P Cruz and L{\'o}pez, Manuel J Ma{\~n}a},
  booktitle={Proceedings of the Sixth International Workshop on Health Text Mining and Information Analysis},
  pages={40--49},
  year={2015}
}

@article{head2015extent,
  title={The extent and consequences of p-hacking in science},
  author={Head, Megan L and Holman, Luke and Lanfear, Rob and Kahn, Andrew T and Jennions, Michael D},
  journal={PLOS Biology},
  volume={13},
  number={3},
  pages={e1002106},
  year={2015},
  publisher={Public Library of Science}
}

% ``Arabic: A single word can comprise up to four independent tokens, morphological knowledge needs to be incorporated into the tokenizer.''
@inproceedings{attia2007arabic,
  title={Arabic tokenization system},
  author={Attia, Mohammed},
  booktitle={Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources},
  pages={65--72},
  year={2007}
}

% ``For unsegmented languages such as Japanese and Chinese, tokenization of a sentence has a significant impact on the performance of text classification.''
@inproceedings{hiraoka2019stochastic,
  title={Stochastic tokenization with a language model for neural text classification},
  author={Hiraoka, Tatsuya and Shindo, Hiroyuki and Matsumoto, Yuji},
  booktitle={Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  pages={1620--1629},
  year={2019}
}

% Korean is different than Chinese or Japanese in terms of tokenization.
% ``Korean is an outlier in the CJK family, which linguistically has a shared vocabulary in terms of roots, but uses an entirely different character representation. A straightforward approach would be to share the character level vocabulary between CJK languages, as it was possible between Chinese and Japanese. However, this, unfortunately, is not a straightforward operation, as Hangul (the Korean writing system) is phonetic, unlike the other two examples.''
 
@inproceedings{moon2020jamo,
  title={Jamo Pair Encoding: Subcharacter Representation-based Extreme {Korean} Vocabulary Compression for Efficient Subword Tokenization},
  author={Moon, Sangwhan and Okazaki, Naoaki},
  booktitle={Proceedings of The 12th Language Resources and Evaluation Conference},
  pages={3490--3497},
  year={2020}
}

% Compound Words -- Leverage Word Embeddings
@article{shwartz2019still,
  title={Still a pain in the neck: Evaluating text representations on lexical composition},
  author={Shwartz, Vered and Dagan, Ido},
  journal={Transactions of the Association for Computational Linguistics},
  volume={7},
  pages={403--419},
  year={2019},
  publisher={MIT Press}
}

% Turbo Topics
@article{blei2009visualizing,
  title={Visualizing topics with multi-word expressions},
  author={Blei, David M and Lafferty, John D},
  journal={arXiv preprint arXiv:0907.1013},
  year={2009}
}

% ----------------------------------------------------------------------

% Handling Punctuation

% Text Classification - Consider Documents Only
@article{korde2012text,
  title={Text classification and classifiers: A survey},
  author={Korde, Vandana and Mahender, C Namrata},
  journal={International Journal of Artificial Intelligence \& Applications},
  volume={3},
  number={2},
  pages={85},
  year={2012},
  publisher={Academy \& Industry Research Collaboration Center (AIRCC)}
}

% Text Summarization - Sentence Extraction
@article{patil2015automatic,
  title={Automatic text summarization},
  author={Patil, Aarti and Pharande, Komal and Nale, Dipali and Agrawal, Roshani},
  journal={International Journal of Computer Applications},
  volume={109},
  number={17},
  year={2015},
  publisher={Foundation of Computer Science}
}

% Machine Translation - Sentence Segmentation
@book{kim2019researching,
  title={Researching Translation in the Age of Technology and Global Conflict: Selected Works of {Mona Baker}},
  author={Kim, Kyung Hye and Zhu, Yifan},
  year={2019},
  publisher={Routledge}
}

% ``Syntactic information potentially plays a much more important role in question answering than it does in information retrieval''
@techreport{li2001incorporating,
  title={Incorporating Syntactic Information in Question Answering},
  author={Li, Xiaoyan and Croft, W Bruce},
  year={2001},
  institution={Center for Intelligent Information Retrieval at University of Massachusetts -- Amherst}
}

% Punctuation -- Discourse Parsing (Text Level)
% ``Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features.''
@inproceedings{ji2014representation,
  title={Representation learning for text-level discourse parsing},
  author={Ji, Yangfeng and Eisenstein, Jacob},
  booktitle={Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics},
  volume={1},
  pages={13--24},
  year={2014}
}

% Eats, Shoots and Leaves
@book{truss2004eats,
  title={Eats, Shoots \& Leaves: The zero tolerance approach to punctuation},
  author={Truss, Lynne},
  year={2004},
  publisher={Penguin}
}

% Python library: pycontractions
% https://pypi.org/project/pycontractions/
@misc{pycontractions,
  title={pycontractions 2.0.1},
  author={Beaver, Ian},
  year={2019},
  note={Python library. Available from: \url{https://pypi.org/project/pycontractions/}}
}

@article{rahman2017detecting,
  title={Detecting emotion from text and emoticon},
  author={Rahman, Romana and others},
  journal={London Journal of Research in Computer Science and Technology},
  year={2017}
}

% ----------------------------------------------------------------------

% Removing Stopwords

% Stopword definition (better)
% ``Stopwords are terms in a language that appear so often and pervasively in the documents as to make them irrelevant to distinguish documents with respect to their content.'' 
@article{ferilli2014automatic,
  title={Automatic learning of linguistic resources for stopword removal and stemming from text},
  author={Ferilli, Stefano and Esposito, Floriana and Grieco, Domenico},
  journal={Procedia Computer Science},
  volume={38},
  pages={116--123},
  year={2014},
  publisher={Elsevier}
}

% Domain-Specific Stopwords -- Examples
% `In the NIPS dataset, the words ``problem,'' ``algorithms,'' ``method,'' ``data,'' and ``learning'' are domain-specific stopwords.'
% Additional discussion: https://rxnlp.com/constructing-a-domain-specific-stop-word-list
@article{fan2017promoting,
  title={Promoting domain-specific terms in topic models with informative priors},
  author={Fan, Angela and Doshi-Velez, Finale and Miratrix, Luke},
  journal={arXiv preprint arXiv:1701.03227},
  year={2017}
}

% Real -- Zipf's law
@article{zipf1949human,
  title={Human behavior and the principle of least effort},
  author={Zipf, George Kingsley},
  year={1949},
  publisher={Addison-Wesley Press}
}

% Domain-Specific Stopwords -- Entropy (Information Theory)
@article{gerlach2019universal,
  title={A universal information theoretic approach to the identification of stopwords},
  author={Gerlach, Martin and Shi, Hanyu and Amaral, Lu{\'\i}s A Nunes},
  journal={Nature Machine Intelligence},
  volume={1},
  number={12},
  pages={606--612},
  year={2019},
  publisher={Nature Publishing Group}
}

% Domain-Specific Stopwords
@article{sarica2020stopwords,
  title={Stopwords in Technical Language Processing},
  author={Sarica, Serhad and Luo, Jianxi},
  journal={arXiv preprint arXiv:2006.02633},
  year={2020}
}

% Predefined stopword list: Appropriate or not?
@inproceedings{schofield2017pulling,
  title={Pulling out the stops: Rethinking stopword removal for topic models},
  author={Schofield, Alexandra and Magnusson, M{\aa}ns and Mimno, David},
  booktitle={Proceedings of the Fifteenth Conference of the European Chapter of the Association for Computational Linguistics},
  volume={2},
  pages={432--436},
  year={2017}
}

% Project Gutenberg -- Discussion 2015
% GlutenTag: NLP x Punctuation x Contractions
% ``We are careful to preserve within-word hyphenation, contractions, and the direction of quotation marks.''
@inproceedings{brooke2015gutentag,
  title={{GutenTag}: An {NLP}-driven tool for digital humanities research in the {Project Gutenberg} corpus},
  author={Brooke, Julian and Hammond, Adam and Hirst, Graeme},
  booktitle={Proceedings of the Fourth Workshop on Computational Linguistics for Literature},
  pages={42--47},
  year={2015}
}

% Stopwords in dependency parsing
@inproceedings{elming2013down,
  title={Down-stream effects of tree-to-dependency conversions},
  author={Elming, Jakob and Johannsen, Anders and Klerke, Sigrid and Lapponi, Emanuele and Alonso, Hector Martinez and S{\o}gaard, Anders},
  booktitle={Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={617--626},
  year={2013}
}

% Stopwords in dependency parsing
@inproceedings{poria2014dependency,
  title={Dependency-based semantic parsing for concept-level text analysis},
  author={Poria, Soujanya and Agarwal, Basant and Gelbukh, Alexander and Hussain, Amir and Howard, Newton},
  booktitle={International Conference on Intelligent Text Processing and Computational Linguistics},
  pages={113--127},
  year={2014},
  organization={Springer}
}

% Stopwords -> authorship attribution
@inproceedings{arun2009stopword,
  title={Stopword graphs and authorship attribution in text corpora},
  author={Arun, Rajkumar and Suresh, Venkatasubramaniyan and Madhavan, CE Veni},
  booktitle={2009 IEEE International Conference on Semantic Computing},
  pages={192--196},
  year={2009},
  organization={IEEE}
}

% Stopwords usage -> detect plagiarism
@article{stamatatos2011plagiarism,
  title={Plagiarism detection using stopword n-grams},
  author={Stamatatos, Efstathios},
  journal={Journal of the American Society for Information Science and Technology},
  volume={62},
  number={12},
  pages={2512--2527},
  year={2011},
  publisher={Wiley Online Library}
}

% Stopwords usage -> detect plagiarism
@article{sanchez2019paraphrase,
  title={Paraphrase plagiarism identification with character-level features},
  author={S{\'a}nchez-Vega, Fernando and Villatoro-Tello, Esa{\'u} and Montes-y-G{\'o}mez, Manuel and Rosso, Paolo and Stamatatos, Efstathios and Villase{\~n}or-Pineda, Luis},
  journal={Pattern Analysis and Applications},
  volume={22},
  number={2},
  pages={669--681},
  year={2019},
  publisher={Springer}
}

% ----------------------------------------------------------------------

% Stemming and Lemmatization

% Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press. 2008.
% Stemming and Lemmatization
% https://nlp.stanford.edu/IR-book/html/htmledition/stemming-and-lemmatization-1.html
% Book link: https://nlp.stanford.edu/IR-book/
@book{manning2008introduction,
  title={Introduction to Information Retrieval},
  author={Manning, Christopher and Raghavan, Prabhakar and Sch{\"u}tze, Hinrich},
  year={2008},
  publisher={Cambridge University Press}
}

% Advantages of Stemming
@incollection{biba2014boosting,
  title={Boosting text classification through stemming of composite words},
  author={Biba, Marenglen and Gjati, Eva},
  booktitle={Recent Advances in Intelligent Informatics},
  pages={185--194},
  year={2014},
  publisher={Springer}
}

% Word Stemming for Information Retrieval
@article{rajput2015survey,
  title={A survey of stemming algorithms for information retrieval},
  author={Rajput, Brajendra Singh and Khare, Nilay},
  journal={International Organization of Scientific Research -- Journal of Computer Engineering},
  volume={17},
  number={3},
  pages={76--80},
  year={2015}
}

% Stemming and Lemmatization destroy sentiment information
@inproceedings{bao2014role,
  title={The role of pre-processing in {Twitter} sentiment analysis},
  author={Bao, Yanwei and Quan, Changqin and Wang, Lijuan and Ren, Fuji},
  booktitle={International Conference on Intelligent Computing},
  pages={615--624},
  year={2014},
  organization={Springer}
}

@article{cambria2017sentiment,
  title={Sentiment analysis is a big suitcase},
  author={Cambria, Erik and Poria, Soujanya and Gelbukh, Alexander and Thelwall, Mike},
  journal={IEEE Intelligent Systems},
  volume={32},
  number={6},
  pages={74--80},
  year={2017},
  publisher={IEEE}
}


% Lemmatization hurts sentiment analysis
@article{bao2009novel,
  title={A Novel {PTSVM} Algorithm for {Twitter} Sentiment Analysis},
  author={Bao, Yanwei and Quan, Changqin},
  journal={International Journal of Advanced Intelligence},
  year={2009}
}

% Stemming hurts sentiment analysis
@techreport{ghazvinian2011star,
  title={Star Quality: Sentiment Categorization of Restaurant Reviews},
  author={Ghazvinian, Amir},
  institution={Stanford University},
  year={2011}
}

@article{porter1980algorithm,
  title={An algorithm for suffix stripping},
  author={Porter, Martin F},
  journal={Program},
  volume={14},
  number={3},
  pages={130--137},
  year={1980}
}

% Definition of stemming:
% ``A stemming algorithm is a computational procedure which reduces all words with the same root (or, if prefixes are left untouched, the same stem) to a common form, usually by stripping each word of its derivational and inflectional suffixes.''
@article{lovins1968development,
  title={Development of a stemming algorithm},
  author={Lovins, Julie Beth},
  journal={Mechanical Translation and Computational Linguistics},
  volume={11},
  number={1-2},
  pages={22--31},
  year={1968}
}

% Stemming: Lancaster Stemmer
@misc{paice2005lancaster,
  title={Lancaster Stemmer},
  author={Paice, C and Hooper, R},
  year={2005}
}

% Lemmatization -- Context
@inproceedings{bergmanis2018context,
  title={Context sensitive neural lemmatization with {Lematus}},
  author={Bergmanis, Toms and Goldwater, Sharon},
  booktitle={Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={1391--1400},
  volume={1},
  year={2018}
}

@inproceedings{tsarfaty2010statistical,
  title={Statistical parsing of morphologically rich languages ({SPMRL}): What, how and whither},
  author={Tsarfaty, Reut and Seddah, Djam{\'e} and Goldberg, Yoav and K{\"u}bler, Sandra and Candito, Marie and Foster, Jennifer and Versley, Yannick and Rehbein, Ines and Tounsi, Lamia},
  booktitle={Proceedings of the NAACL-HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages},
  pages={1--12},
  year={2010},
  organization={Association for Computational Linguistics},
  note={{NAACL-HLT} stands for the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.}
}

% ----------------------------------------------------------------------

% N-Gramming and Multi-Word Expressions

% N-gramming (word-based): word n-grams vs character n-grams
@article{gries2010lexical,
  title={Lexical gravity across varieties of {E}nglish: An {ICE}-based study of n-grams in {Asian} {Englishes}},
  author={Gries, Stefan Th. and Mukherjee, Joybrato},
  journal={International Journal of Corpus Linguistics},
  volume={15},
  number={4},
  pages={520--548},
  year={2010},
  publisher={John Benjamins}
}

% English has very few inflections.
@incollection{haspelmath1996word,
  title={Word-class-changing inflection and morphological theory},
  author={Haspelmath, Martin},
  booktitle={Yearbook of Morphology 1995},
  pages={43--66},
  year={1996},
  publisher={Springer}
}

% Inflectional languages: word order is still helpful
@article{beier2011exploiting,
  title={Exploiting word order to express an inflectional category: Reality status in Iquito},
  author={Beier, Christine and Hansen, Cynthia and Lai, I-wen and Michael, Lev},
  journal={Linguistic Typology},
  volume={15},
  number={1},
  pages={65--99},
  year={2011},
  publisher={De Gruyter Mouton}
}

% N-Gramming: Minimum Frequency 100 and 1000
% Default = n-grams have to occur at least five times.
% A low threshold of minimum frequency => steep increase in computation time
% Datasets: NYT and CW
% The paper used minimum frequency = 100 for NYT and 1000 for CW to reflect their different scales.
% [6] The ClueWeb09 dataset~\cite{callan2009clueweb09}
% [7] The New York Times Annotated Corpus~\cite{sandhaus2008nyt}
@inproceedings{berberich2013computing,
  title={Computing n-gram statistics in {MapReduce}},
  author={Berberich, Klaus and Bedathur, Srikanta},
  booktitle={Proceedings of the 16th International Conference on Extending Database Technology},
  pages={101--112},
  year={2013}
}

% ``The identification of Multi-Word Expressions (MWEs) is central to resolving ambiguity of phrases. Recent works show that deep learning methods outperform statistical and lexical based approaches.''
@inproceedings{ashok2019comparing,
  title={Comparing Different Word Embeddings for Multiword Expression Identification},
  author={Ashok, Aishwarya and Elmasri, Ramez and Natarajan, Ganapathy},
  booktitle={International Conference on Applications of Natural Language to Information Systems},
  pages={295--302},
  year={2019},
  organization={Springer}
}

% `` The tokenization of MWEs makes the occurrences of single words in a training corpus more sparse, but we show that it does not pose negative impacts on single-word translations.''
@inproceedings{otani2020pre,
  title={Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings},
  author={Otani, Naoki and Ozaki, Satoru and Zhao, Xingyuan and Li, Yucen and St Johns, Micaelah and Levin, Lori},
  booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  pages={4451--4464},
  year={2020}
}

% Conditional random fields
% This is an undirected probabilistic graphical model.
% Applications in pattern recognition and machine learning => structured prediction
% https://en.wikipedia.org/wiki/Conditional_random_field
@inproceedings{lafferty2001conditional,
  title={Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data},
  author={Lafferty, John D and McCallum, Andrew and Pereira, Fernando CN},
  booktitle={Proceedings of the Eighteenth International Conference on Machine Learning},
  pages={282--289},
  year={2001}
}

% Conditional random fields
@inproceedings{maldonado2017detection,
  title={Detection of Verbal Multi-Word Expressions via Conditional Random Fields with Syntactic Dependency Features and Semantic Re-Ranking},
  author={Maldonado, Alfredo and Han, Lifeng and Moreau, Erwan and Alsulaimani, Ashjan and Chowdhury, Koel Dutta and Vogel, Carl and Liu, Qun},
  booktitle={Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)},
  pages={114--120},
  year={2017}
}

% Multi-Word Expressions -- Word Sense Disambiguation
@inproceedings{finlayson2011detecting,
  title={Detecting multi-word expressions improves word sense disambiguation},
  author={Finlayson, Mark and Kulkarni, Nidhi},
  booktitle={Proceedings of the Workshop on Multiword Expressions: From Parsing and Generation to the Real World},
  pages={20--24},
  year={2011}
}

% Multi-Word Expressions -- Machine Translation
@inproceedings{tan2014manawi,
  title={Manawi: Using multi-word expressions and named entities to improve machine translation},
  author={Tan, Liling and Pal, Santanu},
  booktitle={Proceedings of the Ninth Workshop on Statistical Machine Translation},
  pages={201--206},
  year={2014}
}

% Multi-Word Expressions -- Machine Translation
@article{han2020multimwe,
  title={{MultiMWE}: Building a Multi-lingual Multi-Word Expression ({MWE}) Parallel Corpora},
  author={Han, Lifeng and Jones, Gareth JF and Smeaton, Alan F},
  journal={arXiv preprint arXiv:2005.10583},
  year={2020}
}

% Multi-Word Expressions x Psycholinguistics
@misc{muller2011multi,
  title={Multi-Word Expressions. Ingeborg Ohnheiser: Word Formation, An International Handbook of the Languages of Europe [HSK series]},
  author={M{\"u}ller, Peter O},
  year={2011},
  publisher={De Gruyter: Berlin}
}

% ----------------------------------------------------------------------

% From Reviewer 3 (Natural Language Engineering)
% Possibly the most important paper on tokenization in the past few years
@inproceedings{trieschnigg2007influence,
  title={The influence of basic tokenization on biomedical document retrieval},
  author={Trieschnigg, Dolf and Kraaij, Wessel and de Jong, Franciska},
  booktitle={Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages={803--804},
  year={2007}
}

% Implications of ``text cleaning'' issues for use of natural language processing in diagnosis
@article{cohen2019p-hacking,
  title={P-Hacking Lexical Richness Through Definitions of ``Type'' and ``Token''},
  author={Cohen, K Bretonnel and Hunter, Lawrence E and Pressman, Peter S},
  journal={Studies in Health Technology and Informatics},
  volume={264},
  pages={1433--1434},
  year={2019},
  organization={International Medical Informatics Association (IMIA)}
}

% A paper that talks a lot about normalization, taking a linguistic approach to the topic, and that led to the development of a new task type in biomedial natural language processing.
@inproceedings{cohen2002contrast,
  title={Contrast and variability in gene names},
  author={Cohen, K Bretonnel and Acquaah-Mensah, George K and Dolbey, Andrew E and Hunter, Lawrence},
  booktitle={Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain},
  volume={3},
  pages={14--20},
  year={2002},
  organization={Association for Computational Linguistics (ACL)}
}

% Paper with a good table to include in this paper
@article{gron2018clinical,
  title={Clinical sublanguages: Vocabulary structure and its impact on term weighting},
  author={Gr{\"o}n, Leonie and Bertels, Ann},
  journal={Terminology: International Journal of Theoretical and Applied Issues in Specialized Communication},
  volume={24},
  number={1},
  pages={41--65},
  year={2018},
  publisher={John Benjamins Publishing Company}
}

% Also added by Reviewer 3
@article{barrett2011building,
  title={Building a biomedical tokenizer using the token lattice design pattern and the adapted {Viterbi} algorithm},
  author={Barrett, Neil and Weber-Jahnke, Jens},
  journal={BMC Bioinformatics},
  volume={12},
  number={3},
  pages={S1},
  year={2011},
  publisher={BioMed Central}
}

% Important syntactic use of forward slash (/) characteristic of a clinical sublanguage in Bulgarian
@inproceedings{temnikova2013closure,
  title={Closure properties of {Bulgarian} clinical text},
  author={Temnikova, Irina and Nikolova, Ivelina and Baumgartner Jr, William A and Angelova, Galia and Cohen, K Bretonnel},
  booktitle={Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP)},
  pages={667--675},
  year={2013}
}

@article{jiang2007empirical,
  title={An empirical study of tokenization strategies for biomedical information retrieval},
  author={Jiang, Jing and Zhai, Chengxiang},
  journal={Information Retrieval},
  volume={10},
  number={4-5},
  pages={341--363},
  year={2007},
  publisher={Springer}
}

% ----------------------------------------------------------------------

% Example 1: JSM Abstract Dataset

% JSM Abstract Dataset (Session Scheduling)
% Yongjian Bi's Master's thesis
@mastersthesis{yongjianbi2016masters,
	author={Yongjian Bi},
	title={Scheduling Optimization with {LDA} and Greedy Algorithm},
	school={Duke University},
	year	={2016},
       note = {LDA stands for latent Dirichlet allocation}
}

% LDA and Conference Session Scheduling 
@mastersthesis{sweeney2020unsupervised,
  title={Unsupervised machine learning for conference scheduling: A natural language processing approach based on latent {Dirichlet} allocation},
  author={Sweeney, Kristian},
  school={NHH Norwegian School of Economics},
  year={2020}
}

% Virtual Conference Scheduling
@article{patro2020fair,
  title={On Fair Virtual Conference Scheduling: Achieving Equitable Participant and Speaker Satisfaction},
  author={Patro, Gourab K and Chakraborty, Abhijnan and Ganguly, Niloy and Gummadi, Krishna P},
  journal={arXiv preprint arXiv:2010.14624},
  year={2020}
}

% ----------------------------------------------------------------------

% Example 2: Social Media Data

% Twitter Abbreviations - 1
@inproceedings{pennell2011toward,
  title={Toward text message normalization: Modeling abbreviation generation},
  author={Pennell, Deana and Liu, Yang},
  booktitle={2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={5364--5367},
  year={2011},
  organization={IEEE}
}

@inproceedings{blodgett2018twitter,
  title={Twitter universal dependency parsing for {African-American} and mainstream {American English}},
  author={Blodgett, Su Lin and Wei, Johnny and O'Connor, Brendan},
  booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={1415--1425},
  year={2018}
}

% Social media data application -- COVID-19 x information spreading
@article{cinelli2020covid,
  title={The {COVID-19} social media infodemic},
  author={Cinelli, Matteo and Quattrociocchi, Walter and Galeazzi, Alessandro and Valensise, Carlo Michele and Brugnoli, Emanuele and Schmidt, Ana Lucia and Zola, Paola and Zollo, Fabiana and Scala, Antonio},
  journal={Scientific Reports},
  volume={10},
  number={1},
  pages={1--10},
  year={2020},
  publisher={Nature Publishing Group}
}

% COVID-19 Twitter Data Daily Updates
% https://github.com/thepanacealab/covid19_twitter
@article{banda2020large,
  title={A large-scale {COVID-19} {Twitter} chatter dataset for open scientific research -- {An} international collaboration},
  author={Banda, Juan M and Tekumalla, Ramya and Wang, Guanyu and Yu, Jingyuan and Liu, Tuo and Ding, Yuning and Chowell, Gerardo},
  journal={arXiv preprint arXiv:2004.03688},
  year={2020}
}

@article{muller2020covid,
  title={{COVID-Twitter-BERT}: A natural language processing model to analyse {COVID-19} content on {Twitter}},
  author={M{\"u}ller, Martin and Salath{\'e}, Marcel and Kummervold, Per E},
  journal={arXiv preprint arXiv:2005.07503},
  year={2020}
}

@article{giorgi2020twitter,
  title={Twitter corpus of the {\#BlackLivesMatter} movement and counter protests: 2013 to 2020},
  author={Giorgi, Salvatore and Guntuku, Sharath Chandra and Rahman, Muhammad and Himelein-Wachowiak, McKenzie and Kwarteng, Amy and Curtis, Brenda},
  journal={arXiv preprint arXiv:2009.00596},
  year={2020}
}

@article{chen2020election2020,
  title={{\#Election2020}: The first public {Twitter} dataset on the 2020 {US} presidential election},
  author={Chen, Emily and Deb, Ashok and Ferrara, Emilio},
  journal={arXiv preprint arXiv:2010.00600},
  year={2020}
}

@article{karami2020twitter,
  title={Twitter speaks: A case of national disaster situational awareness},
  author={Karami, Amir and Shah, Vishal and Vaezi, Reza and Bansal, Amit},
  journal={Journal of Information Science},
  volume={46},
  number={3},
  pages={313--324},
  year={2020},
  publisher={SAGE Publications Sage UK: London, England}
}

% Learning the Language of BlackTwitter (SDSS 2019)
% Brandeis Hill Marshall, Spelman College 
% https://ww2.amstat.org/meetings/sdss/2019/onlineprogram/AbstractDetails.cfm?AbstractID=305061
@inproceedings{marshall2018impact,
  title={The Impact of Live {Tweeting} on Social Movements},
  author={Marshall, Brandeis and Blunt, Takeria and Thompson, Tayloir},
  booktitle={2018 IEEE International Conference on Information Reuse and Integration (IRI)},
  pages={209--216},
  year={2018},
  organization={IEEE}
}

% ----------------------------------------------------------------------

% Example 3: Text with Numerical Ratings 

% Christine Chai's PhD dissertation
@phdthesis{chai2017phdthesis,
	author={Chai, Christine P},
	title={Statistical Issues in Quantifying Text Mining Performance},
	school={Duke University},
	year	={2017},
	type = {{PhD} dissertation}
}

% My Survey Text Mining Paper
@article{Chai2019Text,
   journal={Survey Practice},
   title={Text Mining in Survey Data},
   doi={10.29115/SP-2018-0035},
   volume={12},
   number={1},
   author={Chai, Christine P},
   year={2019},
   pages={1--13}
}

% sLDA original paper
% The paper was presented at NeurIPS 2007 and published in 2008.
@inproceedings{mcauliffe2007supervised,
  title={Supervised Topic Models},
  author={Mc{A}uliffe, Jon D and Blei, David M},
  booktitle={Advances in Neural Information Processing Systems},
  pages={121--128},
  year={2008}
}

% Survey Text with Numerical Ratings

% Nick Fisher Dataset (Employee Satisfaction Dataset)
% Full name: Nicholas Irving Fisher
@book{fisher2013analytics,
  title={Analytics for leaders: A performance measurement system for business success},
  author={Fisher, NI},
  year={2013},
  publisher={Cambridge University Press}
}

% Nick Fisher's paper on performance measurement (April 2019)
% https://rss.onlinelibrary.wiley.com/doi/10.1111/rssa.12424
@article{fisher2019comprehensive,
  title={A comprehensive approach to problems of performance measurement},
  author={Fisher, NI},
  journal={Journal of the Royal Statistical Society: Series A (Statistics in Society)},
  doi={10.1111/rssa.12424},
  volume={182},
  number={3},
  pages={755--803},
  year={2019}
}

% Nick Fisher's paper on survey rating correction \& EM algorithm
% Reverse rating (1-10) problems
@article{fisher2011getting,
  title={Getting the `correct' answer from survey responses: A simple application of the {EM} algorithm},
  author={Fisher, NI and Lee, AJ},
  journal={Australian \& New Zealand Journal of Statistics},
  volume={53},
  number={3},
  pages={353--364},
  year={2011},
  publisher={Wiley Online Library}
}

% ----------------------------------------------------------------------

% Example 4: Biomedical Data

% Biomedical word embeddings with GloVe
% ``distinct vector to represent each word and ignores the internal structure of words''
@article{zhang2019biowordvec,
  title={{BioWordVec}, improving biomedical word embeddings with subword information and {MeSH}},
  author={Zhang, Yijia and Chen, Qingyu and Yang, Zhihao and Lin, Hongfei and Lu, Zhiyong},
  journal={Scientific data},
  volume={6},
  number={1},
  pages={1--9},
  year={2019},
  publisher={Nature Publishing Group}
}

% ``We trained word embeddings using unstructured electronic health record (EHR) data available at Mayo Clinic and articles (MedLit) from PubMed Central, respectively.''
@article{wang2018comparison,
  title={A comparison of word embeddings for the biomedical natural language processing},
  author={Wang, Yanshan and Liu, Sijia and Afzal, Naveed and Rastegar-Mojarad, Majid and Wang, Liwei and Shen, Feichen and Kingsbury, Paul and Liu, Hongfang},
  journal={Journal of Biomedical Informatics},
  volume={87},
  pages={12--20},
  year={2018},
  publisher={Elsevier}
}

@article{lee2020biobert,
  title={{BioBERT}: A pre-trained biomedical language representation model for biomedical text mining},
  author={Lee, Jinhyuk and Yoon, Wonjin and Kim, Sungdong and Kim, Donghyeon and Kim, Sunkyu and So, Chan Ho and Kang, Jaewoo},
  journal={Bioinformatics},
  volume={36},
  number={4},
  pages={1234--1240},
  year={2020},
  publisher={Oxford University Press}
}

% ----------------------------------------------------------------------

% Discussion and Conclusion

% Title: Instead of Just Teaching Data Science, Let's Understand How and Why People Do It
% Conference: 2020 SDSS (Symposium on Data Science and Statistics)
% Author: Rebecca Nugent, Carnegie Mellon University 
% ``In data science, human subjective decisions play an important role as machine learning algorithms.''
% https://ww2.amstat.org/meetings/sdss/2020/onlineprogram/AbstractDetails.cfm?AbstractID=308230

% Title: Automating Data Science: Think About the Human-Machine Interface
% Conference: (Undated) NASEM Opportunities for Accelerating Scientific Discovery
% Author: Rebecca Nugent, Carnegie Mellon University 
% ``While much of data science relies on extracting signal/structure using machine learning algorithms, much is based on human subjective decisions.''

@misc{nugent2020instead,
   title={Instead of Just Teaching Data Science, Let's Understand How and Why People Do It},
   author={Rebecca Nugent},
   year={2020},
   howpublished={Symposium on Data Science and Statistics},
   note={Abstract available from: \url{https://ww2.amstat.org/meetings/sdss/2020/onlineprogram/AbstractDetails.cfm?AbstractID=308230}}
}

% Detecting multi-word expressions is a challenging problem, even with the help of word embeddings.
@inproceedings{hazem2018word,
  title={Word embedding approach for synonym extraction of multi-word terms},
  author={Hazem, Amir and Daille, B{\'e}atrice},
  booktitle={Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year={2018}
}

% Detecting multi-word expressions is a challenging problem, even with the help of word embeddings.
@inproceedings{park2019learning,
  title={Learning to generate word-and phrase-embeddings for efficient phrase-based neural machine translation},
  author={Park, Chan Young and Tsvetkov, Yulia},
  booktitle={Proceedings of the 3rd Workshop on Neural Generation and Translation},
  pages={241--248},
  year={2019}
}