====== Unsupervised Methods ======

===== General Methods =====
  * [[ml:EM algorithm]]
  * Density estimation, direct maximization of p(x)
  * [[https://www.aclweb.org/anthology/P05-1044.pdf|Smith & Eisner 2006 - Contrastive Estimation: Training Log-Linear Models on Unlabeled Data]]

===== Syntactic Parsing =====
See also [[nlp:constituency_parsing#unsupervised constituency parsing]] and [[dependency_parsing#unsupervised dependency parsing]].

==== Overviews ====
  * **Good historical overview**: [[https://www.aclweb.org/anthology/2020.tacl-1.15.pdf|Nishida 2020]] (Gives a good history of unsupervised parsing in the related work)
  * [[http://www.cs.columbia.edu/~rasooli/papers/candidacy2016.pdf|Slides from a candidacy exam]]
  * [[https://www.aclweb.org/anthology/2020.acl-main.300.pdf|Li et al 2020 - An Empirical Comparison of Unsupervised Constituency Parsing Methods]]
  * [[https://arxiv.org/pdf/2010.01535.pdf|Han et al 2020 - A Survey of Unsupervised Dependency Parsing]]

==== Papers ====
  * [[https://www.aclweb.org/anthology/P04-1061.pdf|Klein & Manning 2001 - Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency]] Dependency Model with Valence (DMV). What made Dan Klein famous
  * [[https://jscholarship.library.jhu.edu/bitstream/handle/1774.2/938/smith.2sp.thesis06.pdf?sequence=1&isAllowed=y|Noah Smith 2006 - Novel Estimation Methods for Unsupervised Discovery of Latent Structure in Natural Language Text]] What made Noah Smith famous
  * [[https://www.aclweb.org/anthology/N09-1009.pdf|Cohen & Smith 2009 - Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction]] What made Shay Cohen famous
  * [[https://arxiv.org/pdf/1904.02142.pdf|Drozdov et al 2019 - Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders]]
  * [[https://arxiv.org/pdf/2010.12784.pdf|Gupta et al 2020 - Clustering Contextualized Representations of Text for Unsupervised Syntax Induction]]


==== Grammar Learning ====
  * [[https://arxiv.org/pdf/2010.01160.pdf|Chaudhary et al 2020 - Automatic Extraction of Rules Governing Morphological Agreement]]

==== Image or Video-Aided ====
    * [[https://arxiv.org/pdf/2104.04369.pdf|Zhang et al 2021 - Video-aided Unsupervised Grammar Induction]] (Best paper at NAACL 2021)

===== Morphological Analysis =====
See also [[nlp:morphological_analysis#Unsupervised Analysers|unsupervised morphological analysers]].

===== POS Induction =====
  * [[https://aclanthology.org/D07-1031.pdf|Johnson 2007 - Why doesn’t EM find good HMM POS-taggers?]]
  * [[https://aclanthology.org/P09-1057.pdf|Ravi & Knight 2009 - Minimized Models for Unsupervised Part-of-Speech Tagging]]
  * [[https://aclanthology.org/D10-1056.pdf|Christodoulopoulos et al 2010 - Two Decades of Unsupervised POS induction: How far have we come?]]
  * [[https://arxiv.org/pdf/2010.12784.pdf|Gupta et al 2020 - Clustering Contextualized Representations of Text for Unsupervised Syntax Induction]]

===== Semantic Parsing =====
  * [[https://aclanthology.org/D09-1001.pdf|Poon & Domingos 2009 - Unsupervised Semantic Parsing]]

===== Information Extraction =====
  * Event Extraction
    * [[https://aclanthology.org/P11-1098.pdf|Chambers & Jurafsky 2011 - Template-Based Information Extraction without the Templates]]

===== Discourse Parsing =====
See also [[nlp:discourse_analysis#unsupervised discourse parsing]].

===== Other Unsupervised Tasks =====
  * [[question_answering#Unsupervised QA|Unsupervised Question Answering]]
  * [[nlp:machine_translation#unsupervised|Unsupervised Machine Translation]]

=== Miscellaneous Papers ===
  * [[https://www.aclweb.org/anthology/P08-1090.pdf|Chambers & Jurafsky 2008 - Unsupervised Learning of Narrative Event Chains]]

===== Related Pages =====
  * [[ml:EM Algorithm]]
  * [[nlp:constituency_parsing#Unsupervised Constituency Parsing]]
  * [[dependency_parsing#Unsupervised Dependency Parsing]]
  * [[nlp:discourse_analysis#Unsupervised Discourse Parsing]]