Mova0.5 pre-release⌕
☰
home / docs / papers / topics / Semantic role labeling

Semantic role labeling

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

What it is

Semantic role labeling, SRL for short, answers «who did what to whom» for every verb of a sentence. In «Mary sold the book to John for ten dollars», Mary is the seller, the book the thing sold, John the buyer and ten dollars the price — and the roles stay the same in «John bought the book from Mary».

Resources such as PropBank, VerbNet and FrameNet list the roles each verb takes. A labeler finds the verb, its arguments in the sentence and the role of each, usually on top of a parse tree. Roles are the bridge from grammar to meaning: subject and object change with the voice of the verb, roles do not.

How Mova does it

Mova's frames do this job: each clause becomes a frame with its event, who acts, who or what is acted on, and its place, time, cause and what came next, read from the dependency tree with a verb lexicon converted from VerbNet. Every role says which rule gave it.

The papers (46)

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

  1. Universal Decompositional Semantics on Universal Dependencies 1 idea kept — Aaron Steven White, Drew Reisinger, Keisuke Sakaguchi, Tim Vieira et al., 2016 · 125 citations
  2. What is it? Disambiguating the different readings of the pronoun 'it' 1 idea kept — Sharid Loáiciga, Liane Guillou, Christian Hardmeier, 2017 · 16 citations
  3. The Berkeley FrameNet Project — Collin F. Baker, Charles J. Fillmore, John B. Lowe, 1998 · 2624 citations
  4. The Proposition Bank: An Annotated Corpus of Semantic Roles — Martha Palmer, Daniel Gildea, Paul Kingsbury, 2005 · 2276 citations
  5. Automatic Labeling of Semantic Roles — Daniel Gildea, Daniel Jurafsky, 2002 · 1641 citations
  6. Abstract Meaning Representation for Sembanking — Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu et al., 2013 · 1117 citations
  7. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling — Xavier Carreras, Lluís Màrquez, 2005 · 643 citations
  8. Deep Semantic Role Labeling: What Works and What's Next — Luheng He, Kenton Lee, Mike Lewis, Luke Zettlemoyer, 2017 · 432 citations
  9. Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language — Luheng He, Mike Lewis, Luke Zettlemoyer, 2015 · 197 citations
  10. Large-Scale QA-SRL Parsing — Nicholas FitzGerald, Julian Michael, Luheng He, Luke Zettlemoyer, 2018 · 84 citations
  11. Crowdsourcing Question-Answer Meaning Representations — Julian Michael, Gabriel Stanovsky, Luheng He, Ido Dagan et al., 2018 · 69 citations
  12. PropBank: Semantics of New Predicate Types — Claire Bonial, Julia Bonn, Kathryn Conger, Jena D. Hwang et al., 2014 · 49 citations
  13. FrameNet: A Knowledge Base for Natural Language Processing — Collin F. Baker, 2014 · 44 citations
  14. Controlled Crowdsourcing for High-Quality QA-SRL Annotation — Paul Roit, Ayal Klein, Daniela Stepanov, Jonathan Mamou et al., 2020 · 41 citations
  15. VerbAtlas: a Novel Large-Scale Verbal Semantic Resource and Its Application to Semantic Role Labeling — Andrea Di Fabio, Simone Conia, Roberto Navigli, 2019 · 41 citations
  16. A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling — Diego Marcheggiani, Anton Frolov, Ivan Titov, 2017 · 27 citations
  17. PropBank Comes of Age—Larger, Smarter, and more Diverse — Sameer Pradhan, Julia Bonn, Skatje Myers, Kathryn Conger et al., 2022 · 21 citations
  18. QANom: Question-Answer driven SRL for Nominalizations — Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov et al., 2020 · 18 citations
  19. Semantic Role Labeling as Syntactic Dependency Parsing — Tianze Shi, Igor Malioutov, Ozan Irsoy, 2020 · 17 citations
  20. VerbNet Representations: Subevent Semantics for Transfer Verbs — Susan Windisch Brown, Julia Bonn, James Gung, Annie Zaenen et al., 2019 · 16 citations
  21. SemLink+: FrameNet, VerbNet and Event Ontologies — Martha Palmer, Claire Bonial, Diana McCarthy, 2014 · 12 citations
  22. Comprehensive and Consistent PropBank Light Verb Annotation — Claire Bonial, Martha Palmer, 2016 · 6 citations
  23. Parsing Gapping Constructions Based on Grammatical and Semantic Roles — Yoshihide Kato, Shigeki Matsubara, 2020 · 4 citations
  24. English Resource Semantics — Dan Flickinger, Emily M. Bender, Woodley Packard, 2016 · 4 citations
  25. Prepositional Phrase Attachment Problem Revisited: How VERBNET Can Help — Daniel Bailey, Yuliya Lierler, Benjamin Susman, 2015 · 4 citations
  26. Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities — Riccardo Orlando, Simone Conia, Roberto Navigli, 2023 · 3 citations
  27. Evaluating Universal Dependency Parser Recovery of Predicate Argument Structure via CompChain Analysis — Sagar Indurkhya, Beracah Yankama, Robert C. Berwick, 2021 · 2 citations
  28. Open-source Frame Semantic Parsing — David Chanin, 2023 · 1 citations
  29. Thematic role assignment in non-default verb classes: A cross-linguistic comparison of English and German — Louise Kyriaki, Matthias Schlesewsky, Ina Bornkessel-Schlesewsky, 2021 · 1 citations
  30. Comparing Sense Categorization Between English PropBank and English WordNet — Özge Bakay, Begüm Avar, Olcay Taner Yıldız, 2019 · 1 citations
  31. The Role of PropBank Sense IDs in AMR-to-text Generation and Text-to-AMR Parsing — Thu Hoang, Mina Yang, Shira Wein, 2025
  32. Can predicate-argument relationships be extracted from UD trees? — Adam Ek, Jean-Philippe Bernardy, Stergios Chatzikyriakidis, 2021
  33. How useful are Enhanced Universal Dependencies for semantic interpretation? — Jamie Y. Findlay, Dag T. T. Haug, 2021
  34. SemLink 2.0: Chasing Lexical Resources — Kevin Stowe, Jenette Preciado, Kathryn Conger, Susan Windisch Brown et al., 2021
  35. Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles — Ben Eyal, Michael Elhadad, 2020
  36. Out-of-domain FrameNet Semantic Role Labeling — Silvana Hartmann, Ilia Kuznetsov, Teresa Martin, Iryna Gurevych, 2017
  37. The Hebrew FrameNet Project — Avi Hayoun, Michael Elhadad, 2016
  38. MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility based on semantic roles — Chi-kiu Lo, Dekai Wu, 2011
  39. Abstraction and Generalisation in Semantic Role Labels: PropBank, VerbNet or both? — Paola Merlo, Lonneke van der Plas, 2009
  40. Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection — Hai Zhao, Wenliang Chen, Chunyu Kit, 2009
  41. The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages — Jan Hajič, Massimiliano Ciaramita, Richard Johansson, Daisuke Kawahara et al., 2009
  42. Dependency-based Semantic Role Labeling of PropBank — Richard Johansson, Pierre Nugues, 2008
  43. The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies — Mihai Surdeanu, Richard Johansson, Adam Meyers, Lluís Màrquez et al., 2008
  44. Merging PropBank, NomBank, TimeBank, Penn Discourse Treebank and Coreference — James Pustejovsky, Adam Meyers, Martha Palmer, Massimo Poesio, 2005
  45. From TreeBank to PropBank — Paul Kingsbury, Martha Palmer, 2002
  46. The Penn Treebank: Annotating Predicate Argument Structure — Mitchell Marcus, Grace Kim, Mary Ann Marcinkiewicz, Robert MacIntyre et al., 1994

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/topics/semantic-role-labeling/