rhetorical structure and argumentation structure in
play

Rhetorical structure and argumentation structure in monologue text - PowerPoint PPT Presentation

Rhetorical structure and argumentation structure in monologue text Andreas Peldszus Manfred Stede Applied Computational Linguistics, University of Potsdam 3rd Workshop on Argument Mining @ACL 2016, Berlin, 12.08.2016 Peldszus, Stede (Uni


  1. Rhetorical structure and argumentation structure in monologue text Andreas Peldszus Manfred Stede Applied Computational Linguistics, University of Potsdam 3rd Workshop on Argument Mining @ACL 2016, Berlin, 12.08.2016 Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 1 / 24

  2. Outline 1 Introduction 2 Matching RST and argumentation: Qualitative analysis 3 Automatically deriving ARG from RST Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 2 / 24

  3. Outline 1 Introduction 2 Matching RST and argumentation: Qualitative analysis 3 Automatically deriving ARG from RST Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 3 / 24

  4. RST in a nutshell Key ideas and principles [Mann and Thompson, 1988] • text coherent <=> a plausible RST tree exists • 25 relations: presentational (pragmatic) vs. subject-matter (semantic) • most relations: nucleus (main info/act) + satellite (support info/act) • same relation set applies to minimal units and recursively to text spans • every unit/span takes part in the analysis • no crossing edges • (annotation guidelines in [Stede, 2016] ) Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 4 / 24

  5. Argumentation structure in a nutshell Freeman’s theory, revised & slightly generalized: [e1] Health insurance [Freeman, 1991, 2011] [Peldszus and Stede, 2013] companies should naturally cover alternative medical treatments. • node types = argumentative role [e2] Not all practices and approaches that are lumped proponent (presents and defends claims) together under this term may 2 have been proven in clinical trials, opponent (critically questions) 1 c2 [e3] yet it's precisely their 3 c3 positive effect when • link types = argumentative function accompanying conventional 'western' medical therapies that's been demonstrated as support own claims (normally, by example) beneficial. [e4] Besides many general attack other’s claims (rebut, undercut) practitioners offer such 4 c4 counselling and treatments in parallel anyway - • (annotation guidelines in [Stede, 2016] ) [e5] and who would want to 5 question their broad expertise? Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 5 / 24

  6. Outline 1 Introduction 2 Matching RST and argumentation: Qualitative analysis 3 Automatically deriving ARG from RST Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 6 / 24

  7. Dataset: argumentative microtexts Properties: • about 5 segments long • each segment is arg. relevant • explicit main claim • at least one possible objection considered Texts: • 23 texts: hand-crafted, covering different arg. configurations • 92 texts: collected in a controlled text generation experiment • with professional parallel translation to English • all annotated with argumentation structure • freely available, CC-by-nc-sa license; see [Peldszus and Stede, 2016] Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 7 / 24

  8. Dataset: argumentative microtexts Properties: • about 5 segments long • each segment is arg. relevant • explicit main claim • at least one possible objection considered Texts: • 23 texts: hand-crafted, covering different arg. configurations • 92 texts: collected in a controlled text generation experiment • with professional parallel translation to English • all annotated with argumentation structure • freely available, CC-by-nc-sa license; see [Peldszus and Stede, 2016] Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 7 / 24

  9. Multi-layer discourse annotation How does argumentation structure relate to other discourse structures? • Rhetorical Structure Theory (RST) [Mann and Thompson, 1988] • Segmented Discourse Structure Theory (SDRT) [Asher and Lascarides, 2003] Joint work with Stergos Afantenos, Nicholas Asher, Jérémy Perret [Stede et al., 2016] Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 8 / 24

  10. Multi-layer discourse annotation: Harmonize segmentation [e3] for some a day [e8] For those [e1] Supermarket of introspection, [e5] People, people the late employees and people [e2] Likewise public [e4] Hence it is for others a paid however, who work opening hours, which who work in shopping holidays should good when shops are [e6] everyone else day off that is not during the week and [e7] but they can't. meanwhile already centres also have remain what they not open on Sundays can shop weekdays, taken away from the on Saturdays then extend to 12:00 the right to a are: and public holidays. annual paid leave have a problem: midnight, present a Sunday off work. proper. good alternative. 1 2+3 5+6+7 8 2+3 5+6+7 c14 c12 c11 c13 4 Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 9 / 24

  11. Qualitative: Central Claim Total: 115 CCs in ARG (one per text) • Canonical: In 95 texts (85%), central nucleus in RST corresponds to central claim in ARG • In 5 texts, they are disjoint • multiple statements of the CC • no explicit CC • In 12 texts, they overlap • ARG CC has more fine-grained RST analysis (e.g., Condition) • multinuclear RST relations yield multiple RSTnuc for the text Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 10 / 24

  12. Qualitative: Support Total: 261 Support relations in ARG • Canonical: 132 correspond to RST Reason, Justify, Evidence, Motivation, Cause • But: 77% of the texts contain at least one non-canonical Support • 12 Supports correspond to another (mostly ‘informational’) RST relation • 117 Supports have no corresponding RST relation • RST segment is in a multinuclear relation (70) • RST segment is related to a different segment via an informational relation (21) • Mismatch in Support transitivity (16) • Other (18) Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 11 / 24

  13. Qualitative: Attack Total: 98 Attack relations in ARG • Simple: A single attacking node (either leaf or supported) • Canonical: (24/31) Attack corresponds to Antithesis, Contrast, Concession • (7/31) opponent voice absent in RST, or segment connected otherwise • Medium: Multiple individual attacks in ARG • Canonical: In all 7 cases, RST groups them via Conjunction • Complex: Attack and Counterattack • Canonical: (47/60) Attack corresponds to a backward Concession, Antithesis (different levels of complexity) • (13/60) Annotator did not see this argumentative function as primary Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 12 / 24

  14. Qualitative: Attack Total: 98 Attack relations in ARG • Simple: A single attacking node (either leaf or supported) • Canonical: (24/31) Attack corresponds to Antithesis, Contrast, Concession • (7/31) opponent voice absent in RST, or segment connected otherwise • Medium: Multiple individual attacks in ARG • Canonical: In all 7 cases, RST groups them via Conjunction • Complex: Attack and Counterattack • Canonical: (47/60) Attack corresponds to a backward Concession, Antithesis (different levels of complexity) • (13/60) Annotator did not see this argumentative function as primary Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 12 / 24

  15. Qualitative: Attack Total: 98 Attack relations in ARG • Simple: A single attacking node (either leaf or supported) • Canonical: (24/31) Attack corresponds to Antithesis, Contrast, Concession • (7/31) opponent voice absent in RST, or segment connected otherwise • Medium: Multiple individual attacks in ARG • Canonical: In all 7 cases, RST groups them via Conjunction • Complex: Attack and Counterattack • Canonical: (47/60) Attack corresponds to a backward Concession, Antithesis (different levels of complexity) • (13/60) Annotator did not see this argumentative function as primary Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 12 / 24

  16. Outline 1 Introduction 2 Matching RST and argumentation: Qualitative analysis 3 Automatically deriving ARG from RST Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 13 / 24

  17. Task Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 14 / 24

  18. Task [e3] yet it's [e2] Not all precisely their [e1] Health practices and positive effect [e4] Besides insurance approaches that when many general [e5] and who companies are lumped accompanying practitioners would want to should together under conventional offer such question their naturally cover this term may 'western' counselling and broad alternative have been medical treatments in expertise? medical proven in therapies parallel anyway treatments. clinical that's been - trials, demonstrated as beneficial. ⇒ 3 4 5 2 c9 c7 c6 1 Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 14 / 24

  19. Task reason support reason ⇒ rebut undercut link concession joint 1 2 3 4 5 1 2 3 4 5 Common dependency format [Stede et al., 2016] Peldszus, Stede (Uni Potsdam) Rhetorical structure and argumentation structure ArgMin WS 3 14 / 24

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend