Mova0.5 pre-release⌕
☰
home / docs / papers / topics / Part-of-speech tagging

Part-of-speech tagging

80 paper cards from Mova's library · 2 of them with an idea Mova measured or kept

What it is

Part-of-speech tagging gives every word of a sentence its word class: noun, verb, adjective, preposition and so on, often with finer tags for number, tense or person. The difficulty is ambiguity: «book» is a noun in «a good book» and a verb in «book a table», and the tagger must decide from the context.

Taggers learned from annotated text have been accurate since the 1990s — hidden Markov models such as TnT, then perceptrons and neural networks — reaching about 97% of words right on news text in English. Unknown words and other kinds of text, from tweets to old books, are where they still go wrong.

How Mova does it

Mova's English tagger is an averaged perceptron over the word, its neighbours, suffixes, prefixes, word shape and a dictionary compiled into the code, with a beam of 8; unknown words get a prior from a TnT-style trigram model. It tags 94.35% of the words of the English Web Treebank right.

The papers (80)

Cards with a measured or kept idea first, then by citations.

  1. Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms measured — Michael Collins, 2002 · 1863 citations
  2. TnT – A Statistical Part-of-Speech Tagger measured — Thorsten Brants, 2000 · 1329 citations
  3. Building a Large Annotated Corpus of English: The Penn Treebank — Mitchell P. Marcus, Beatrice Santorini, Mary Ann Marcinkiewicz, 1993 · 7324 citations
  4. Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe — Milan Straka, Jana Straková, 2017 · 567 citations
  5. Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop — Nizar Habash, Owen Rambow, 2005 · 448 citations
  6. Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics? — Christopher D. Manning, 2011 · 409 citations
  7. Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task — Timothy Dozat, Peng Qi, Christopher D. Manning, 2017 · 220 citations
  8. Arabic Morphological Tagging, Diacritization, and Lemmatization Using Lexeme Models and Feature Ranking — Ryan Roth, Owen Rambow, Nizar Habash, Mona Diab et al., 2008 · 155 citations
  9. Arabic Diacritization through Full Morphological Tagging — Nizar Habash, Owen Rambow, 2007 · 143 citations
  10. Maximum Entropy Based Restoration of Arabic Diacritics — Imed Zitouni, Jeffrey S. Sorensen, Ruhi Sarikaya, 2006 · 143 citations
  11. An Empirical Analysis of Formality in Online Communication — Ellie Pavlick, Joel Tetreault, 2016 · 136 citations
  12. Dependency Parsing of Modern Standard Arabic with Lexical and Inflectional Features — Yuval Marton, Nizar Habash, Owen Rambow, 2013 · 82 citations
  13. Don't Throw Those Morphological Analyzers Away Just Yet: Neural Morphological Disambiguation for Arabic — Nasser Zalmout, Nizar Habash, 2017 · 58 citations
  14. Improving Arabic Dependency Parsing with Lexical and Inflectional Morphological Features — Yuval Marton, Nizar Habash, Owen Rambow, 2010 · 43 citations
  15. A global model for joint lemmatization and part-of-speech prediction — Kristina Toutanova, Colin Cherry, 2009 · 41 citations
  16. Integrated Morphological and Syntactic Disambiguation for Modern Hebrew — Reut Tsarfaty, 2006 · 38 citations
  17. Learning a POS tagger for AAVE-like language — Anna Jørgensen, Dirk Hovy, Anders Søgaard, 2016 · 34 citations
  18. Lemmatisation as a Tagging Task — Andrea Gesmundo, Tanja Samardžić, 2012 · 34 citations
  19. A Gold Standard Corpus of Early Modern German — Silke Scheible, Richard J. Whitt, Martin Durrell, Paul Bennett, 2011 · 33 citations
  20. Part-of-Speech Tagging for Historical English — Yi Yang, Jacob Eisenstein, 2016 · 30 citations
  21. Memory-Based Morphological Analysis Generation and Part-of-Speech Tagging of Arabic — Erwin Marsi, Antal van den Bosch, Abdelhadi Soudi, 2005 · 28 citations
  22. A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling — Diego Marcheggiani, Anton Frolov, Ivan Titov, 2017 · 27 citations
  23. Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System — Yoav Goldberg, Michael Elhadad, 2013 · 26 citations
  24. 'IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks' — Anders Björkelund, Agnieszka Falenska, Xiang Yu, Jonas Kuhn, 2017 · 25 citations
  25. POS Tagging for Historical Texts with Sparse Training Data — Marcel Bollmann, 2013 · 24 citations
  26. Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging — Nasser Zalmout, Nizar Habash, 2020 · 22 citations
  27. Joint Prediction of Morphosyntactic Categories for Fine-Grained Arabic Part-of-Speech Tagging Exploiting Tag Dictionary Information — Go Inoue, Hiroyuki Shindo, Yuji Matsumoto, 2017 · 21 citations
  28. Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts — Taesun Moon, Jason Baldridge, 2007 · 21 citations
  29. Formemes in English-Czech Deep Syntactic MT — Ondřej Dušek, Zdeněk Žabokrtský, Martin Popel, Martin Majliš et al., 2012 · 15 citations
  30. Nakdan: Professional Hebrew Diacritizer — Avi Shmidman, Shaltiel Shmidman, Moshe Koppel, Yoav Goldberg, 2020 · 13 citations
  31. Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging — Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Ahmed Abdelali et al., 2017 · 13 citations
  32. Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer — Seth Kulick, 2010 · 13 citations
  33. A Dependency Treebank of Spoken Second Language English — Kristopher Kyle, Masaki Eguchi, Aaron Miller, Theodore Sither, 2022 · 11 citations
  34. Tagging a Hebrew Corpus: the Case of Participles — Meni Adler, Yael Netzer, Yoav Goldberg, David Gabay et al., 2008 · 11 citations
  35. Improving Arabic Diacritization with Regularized Decoding and Adversarial Training — Han Qin, Guimin Chen, Yuanhe Tian, Yan Song, 2021 · 10 citations
  36. A POS Tagging Model Designed for Learner English — Ryo Nagata, Tomoya Mizumoto, Yuta Kikuchi, Yoshifumi Kawasaki et al., 2018 · 9 citations
  37. Investigating NP-Chunking with Universal Dependencies for English — Ophélie Lacroix, 2018 · 9 citations
  38. AMALGUM – A Free, Balanced, Multilayer English Web Corpus — Luke Gessler, Siyao Peng, Yang Liu, Yilun Zhu et al., 2020 · 7 citations
  39. Different Flavors of GUM: Evaluating Genre and Sentence Type Effects on Multilayer Corpus Annotation Quality — Amir Zeldes, Dan Simonson, 2016 · 7 citations
  40. Lemmatization and POS-tagging process by using joint learning approach. Experimental results on Classical Armenian, Old Georgian, and Syriac — Chahan Vidal-Gorène, Bastien Kindt, 2020 · 6 citations
  41. Towards JointUD: Part-of-speech Tagging and Lemmatization using Recurrent Neural Networks — Gor Arakelyan, Karen Hambardzumyan, Hrant Khachatrian, 2018 · 6 citations
  42. A Freely Available Syntactic Lexicon for English — Dania Egedi, Patrick Martin, 1994 · 6 citations
  43. A Cross-Task Flexible Transition Model for Arabic Tokenization, Affix Detection, Affix Labeling, POS Tagging, and Dependency Parsing — Stephen Tratz, 2013 · 4 citations
  44. A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration — Avi Shmidman, Joshua Guedalia, Shaltiel Shmidman, Moshe Koppel et al., 2020 · 3 citations
  45. Using Lexical Dependency and Ontological Knowledge to Improve a Detailed Syntactic and Semantic Tagger of English — Andrew Finch, Ezra Black, Young-Sook Hwang, Eiichiro Sumita, 2006 · 3 citations
  46. Estimating POS Annotation Consistency of Different Treebanks in a Language — Akshay Aggarwal, Daniel Zeman, 2020 · 2 citations
  47. Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches — Tianze Shi, Lillian Lee, 2020 · 2 citations
  48. A Survey of Corpora for Germanic Low-Resource Languages and Dialects — Verena Blaschke, Hinrich Schuetze, Barbara Plank, 2023 · 1 citations
  49. Detecting Syntactic Change Using a Neural Part-of-Speech Tagger — William Merrill, Gigi Stark, Robert Frank, 2019 · 1 citations
  50. Ranking Translations using Error Analysis and Quality Estimation — Mark Fishel, 2013 · 1 citations
  51. CAIT: A Syntactic Parsing Toolkit for Child–Adult InTeractions — Francesca Padovani, Xiulin Yang, Bastian Bunzeck, Jaap Jumelet et al., 2026
  52. Cross-Lingual and Cross-Domain Transfer Learning for POS Tagging in Historical Germanic Low-Resource Languages — Irene Miani, Sara Stymne, Gregory R. Darwin, 2026
  53. English Grammar (Wikibooks) — Wikibooks contributors, 2026
  54. Cross-Genre Learning for Old English Poetry POS Tagging — Irene Miani, Sara Stymne, Gregory R. Darwin, 2025
  55. Lemmatization as a Classification Task: Results from Arabic across Multiple Genres — Mostafa Saeed, Nizar Habash, 2025
  56. Pre-annotation Matters: A Comparative Study on POS and Dependency Annotation for an Alsatian Dialect — Delphine Bernhard, Nathanaël Beiner, Barbara Hoff, 2025
  57. Allen Institute for AI @ SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages — Lester James V. Miranda, 2024
  58. At the Crossroad of Cuneiform and NLP: Challenges for Fine-grained Part-of-speech Tagging — Gustav Ryberg Smidt, Els Lefever, Katrien de Graef, 2024
  59. Evaluating large language models for the tasks of PoS tagging within the Universal Dependency framework — Mateus Machado, Evandro Ruiz, 2024
  60. Whit's the Richt Pairt o Speech: PoS tagging for Scots — Harm Lameris, Sara Stymne, 2021
  61. Controlled Semi-automatic Annotation of Classical Ethiopic — Cristina Vertan, 2019
  62. Automatic Thesaurus Construction for Modern Hebrew — Chaya Liebeskind, Ido Dagan, Jonathan Schler, 2018
  63. Constructing an Annotated Resource for Part-Of-Speech Tagging of Mishnaic Hebrew — Emiliano Giovannetti, Davide Albanesi, Andrea Bellandi, Simone Marchi et al., 2018
  64. A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax — Christo Kirov, John Sylak-Glassman, Rebecca Knowles, Ryan Cotterell et al., 2017
  65. Analyzing the Impact of Spelling Errors on POS-Tagging and Chunking in Learner English — Tomoya Mizumoto, Ryo Nagata, 2017
  66. A Lexical Resource of Hebrew Verb-Noun Multi-Word Expressions — Chaya Liebeskind, Yaakov HaCohen-Kerner, 2016
  67. A Neural Model for Part-of-Speech Tagging in Historical Texts — Christian Hardmeier, 2016
  68. UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing — Milan Straka, Jan Hajič, Jana Straková, 2016
  69. Universal Dependencies v1: A Multilingual Treebank Collection — Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg et al., 2016
  70. An Empirical Comparison of Parsing Methods for Stanford Dependencies — Lingpeng Kong, Noah A. Smith, 2014
  71. A Good Part-of-Speech Tagger in about 200 Lines of Python — Matthew Honnibal, 2013
  72. Construction of English MWE Dictionary and its Application to POS Tagging — Yutaro Shigeto, Ai Azuma, Sorami Hisamoto, Shuhei Kondo et al., 2013
  73. Joint English Spelling Error Correction and POS Tagging for Language Learners Writing — Keisuke Sakaguchi, Tomoya Mizumoto, Mamoru Komachi, Yuji Matsumoto, 2012
  74. Exploring Difficulties in Parsing Imperatives and Questions — Tadayoshi Hara, Takuya Matsuzaki, Yusuke Miyao, Jun'ichi Tsujii, 2011
  75. Fine-Grain Morphological Analyzer and Part-of-Speech Tagger for Arabic Text — Majdi Sawalha, Eric Atwell, 2010
  76. Morphological Analysis Can Improve a CCG Parser for English — Matthew Honnibal, Jonathan K. Kummerfeld, James R. Curran, 2010
  77. Smoothing a Lexicon-based POS Tagger for Arabic and Hebrew — Saib Manour, Khalil Sima'an, Yoad Winter, 2007
  78. Towards broad coverage surface realization with CCG — Michael White, Rajakrishnan Rajkumar, Scott Martin, 2007
  79. Choosing an Optimal Architecture for Segmentation and POS-Tagging of Modern Hebrew — Roy Bar-Haim, Khalil Sima'an, Yoad Winter, 2005
  80. Part-of-Speech Tagging Guidelines for the Penn Treebank Project (3rd Revision) — Beatrice Santorini, 1990

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/