--- title: "Implications for Generating Clarification Requests in" description: "The paper asks how a spoken dialogue system should formulate clarification requests (CRs) so that… 15 references, cited by 22 papers here." authors: ["Verena Rieser", "Johanna Moore"] year: 2005 venue: "Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)" source: "https://aclanthology.org/P05-1030/" doi: "10.3115/1219840.1219870" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/rieser-2005-implications-generating-clarification-requests-task/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/rieser-2005-implications-generating-clarification-requests-task/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2005](https://md.research.elamur.ai/free/en/papers/2005/) / Implications for Generating Clarification Requests in Task-Oriented Dialogues # Implications for Generating Clarification Requests in Task-Oriented Dialogues **Authors:** [Verena Rieser](https://md.research.elamur.ai/free/en/authors/verena-rieser/) and [Johanna Moore](https://md.research.elamur.ai/free/en/authors/johanna-d-moore/) · **Year:** 2005 · **Venue:** [Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2005](https://md.research.elamur.ai/free/en/venues/acl/2005/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/P05-1030/) · [PDF](https://aclanthology.org/P05-1030.pdf) · [DOI 10.3115/1219840.1219870](https://doi.org/10.3115/1219840.1219870) · [OpenAlex](https://openalex.org/W2136449704) **Citations:** 51 citations (OpenAlex, 2026-10-14) · [22](https://md.research.elamur.ai/free/en/papers/rieser-2005-implications-generating-clarification-requests-task/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper asks how a spoken dialogue system should formulate clarification requests (CRs) so that they show *what* went wrong in understanding. Rieser and Moore annotated the human-human travel-booking dialogues of the Carnegie Mellon Communicator Corpus. They used an extended version of the multidimensional Rodriguez and Schlangen (R&S) scheme, in which form features (mood, completeness, relation to antecedent, boundary tone) are kept apart from function features (source, severity, extent, answer, satisfaction). Source follows Clark's four grounding levels. They compared their counts with R&S's study of the German Bielefeld Corpus and with Purver, Ginzburg and Healey's BNC study. The two task-oriented corpora showed no significant differences, but both differed clearly from everyday conversation. This suggests that dialogue type, modality and channel quality shape when and at which level people clarify. In task dialogues, people tend to clarify immediately and to offer a hypothesis for confirmation rather than ask for repetition. Chi-square tests found significant form–function correlations, which can serve as rules for generating natural CRs that signal the problem source. ## Key points - **Data:** - 31 Communicator dialogues: 2098 turns and 19,395 words of transcribed telephone speech. - 98 CRs in total, which is 4.6% of turns. - **Extensions to the R&S scheme:** - Relation-antecedent now separates `add` from `repet-add`. - Source gains the values `belief` and `ambiguity refinement`. - Severity gains `cont-disamb`, following Gabsdil. - **Most common form:** partial declarative questions, at 53.1% of CRs. Rising boundary tone accounts for about 74%. - **Function distribution:** - Source: np-reference 40%, acoustic 31%. - Severity: about 73% ask for confirmation of a hypothesis. - Extent: 80% point to a specific element. - **Form–function tests:** Pearson's χ² with Yates correction. - Source correlates with relation-antecedent and mood. - Severity and answer correlate with mood. - Extent correlates with completeness. - Acoustic problems lead to literal repetition. Reference problems lead to reformulation or repetition-with-addition. ## Interesting ideas - Describe a clarification act along two separate axes, function (why) and form (how), then learn the mapping between them; this keeps the generator's decision step independent of its surface realisation step. - Tie the source of a problem to grounding levels (contact, acoustic, reference, intention) so that a request reveals which level failed; an error label then carries diagnostic information rather than just "not understood". - Prefer offering the most plausible hypothesis, drawn from dialogue history and world knowledge, over asking for repetition; humans do this to stay efficient while still checking. - Annotate a request's meaning partly by what happens next, using the addressee's reply and whether the asker renews the request, instead of fixing its reading in advance. - Compare behaviour across corpora that differ in genre and channel quality to see which regularities hold and which are domain-specific. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (back): When Mova cannot resolve something, it could first pick a function (source plus severity), then choose a surface pattern from a function→form table, so each generated question stays explainable. - **I2** (frames): Failed coreference or role assignment could be labelled with the level where it broke, such as np-reference versus intention, and passed on as an explanation instead of a silent fallback. - **I3** (world): When an entity or date is underspecified (e.g., a day without a month), the world model could fill in the most reasonable value and mark it as a confirmable assumption rather than leaving a gap. - **I4** (learn): Ambiguous silver annotations could be resolved by downstream consequences, for example whether the follow-up text confirms an interpretation, as a contextual check on witness disagreement. - **I5** (learn): Evaluation could compare rule statistics across fables, school texts and dialogue, flagging rules whose distribution shifts as genre-dependent rather than universal. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [University of Edinburgh](https://md.research.elamur.ai/free/en/universities/university-of-edinburgh/) — University, Edinburgh, United Kingdom · 359 works · 77,352 citations - [Saarland University](https://md.research.elamur.ai/free/en/universities/saarland-university/) — University, Saarbrücken, Germany · 148 works · 18,287 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works 🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works ## Cite Cite as: Verena Rieser and Johanna Moore. 2005. Implications for Generating Clarification Requests in Task-Oriented Dialogues. Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{rieser2005implications, title = {{Implications for Generating Clarification Requests in Task-Oriented Dialogues}}, author = {Verena Rieser and Johanna Moore}, booktitle = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)}, year = {2005}, doi = {10.3115/1219840.1219870}, url = {https://doi.org/10.3115/1219840.1219870} } ``` - [← previous POS Tagging of Dialectal Arabic: A Minimally Supervised Approach](https://md.research.elamur.ai/free/en/papers/duh-2005-pos-tagging-dialectal-arabic-minimally/) - [next → Using Semantic Relations to Refine Coreference Decisions](https://md.research.elamur.ai/free/en/papers/ji-2005-semantic-relations-refine-coreference-decisions/) - [↑ back to papers of 2005](https://md.research.elamur.ai/free/en/papers/2005/) ## References 15 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Christina L. Bennett and Alexander I. Rudnicky. 2002. The Carnegie Mellon Communicator Corpus. In Proceedings of the International Conference of Spoken Language Processing (ICSLP02). [find](https://scholar.google.com/scholar?q=Christina+L%2E+Bennett+and+Alexander+I%2E+Rudnicky%2E+2002%2E+The+Carnegie+Mellon+Communicator+Corpus%2E+In+Proceedings+of+the+International+Conference+of+Spoken+Language+Processing+%28ICSLP02%29%2E) 2. Lou Burnard. 2000. The British National Corpus Users Reference Guide. Technical report, Oxford Universiry Computing Services. [find](https://scholar.google.com/scholar?q=Lou+Burnard%2E+2000%2E+The+British+National+Corpus+Users+Reference+Guide%2E+Technical+report%2C+Oxford+Universiry+Computing+Services%2E) 3. Herbert Clark. 1996. Using Language. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Herbert+Clark%2E+1996%2E+Using+Language%2E+Cambridge+University+Press%2E) 4. Malte Gabsdil. 2003. Clarification in Spoken Dialogue Systems. Proceedings of the 2003 AAAI Spring Symposium. Workshop on Natural Language Generation in Spoken and Written Dialogue. [find](https://scholar.google.com/scholar?q=Malte+Gabsdil%2E+2003%2E+Clarification+in+Spoken+Dialogue+Systems%2E+Proceedings+of+the+2003+AAAI+Spring+Symposium%2E+Workshop+on+Natural+Language+Generation+in+Spoken+and+Written+Dialogue%2E) 5. Jonathan Ginzburg and Robin Cooper. 2001. Resolving Ellipsis in Clarification. In Proceedings of the 39th Function extent χ 2 (5) = 24.25 df = p \< 0.005 indep. answer χ 2 (5) = 25.19 p \< 0.001 indep. χ 2 (4) = 42.58 p \< 0.001 χ 2 (1) = 27.39 p \< 0.001 indep. indep. meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jonathan+Ginzburg+and+Robin+Cooper%2E+2001%2E+Resolving+Ellipsis+in+Clarification%2E+In+Proceedings+of+the+39th+Function+extent+%CF%87+2+%285%29+%3D+24%2E25+df+%3D+p+%3C+0%2E005+indep%2E+answer+%CF%87+2+%285%29+%3D+25%2E19+p+%3C+0%2E001+indep%2E+) 6. Staffan Larsson. 2002. Issue-based Dialogue Management. Ph.D. thesis, Goteborg University. [find](https://scholar.google.com/scholar?q=Staffan+Larsson%2E+2002%2E+Issue%2Dbased+Dialogue+Management%2E+Ph%2ED%2E+thesis%2C+Goteborg+University%2E) 7. Tim Paek and Eric Horvitz. 2000. Conversation as Action Under Uncertainty. In Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Tim+Paek+and+Eric+Horvitz%2E+2000%2E+Conversation+as+Action+Under+Uncertainty%2E+In+Proceedings+of+the+Sixteenth+Conference+on+Uncertainty+in+Artificial+Intelligence%2E) 8. Tim Paek. 2003. Toward a Taxonomy of Communication Errors. In ISCA Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems. [find](https://scholar.google.com/scholar?q=Tim+Paek%2E+2003%2E+Toward+a+Taxonomy+of+Communication+Errors%2E+In+ISCA+Tutorial+and+Research+Workshop+on+Error+Handling+in+Spoken+Dialogue+Systems%2E) 9. Matthew Purver, Jonathan Ginzburg, and Patrick Healey. 2003. On the Means for Clarification in Dialogue. In R. Smith and J. van Kuppevelt, editors, Current and New Directions in Discourse and Dialogue. [↗](https://doi.org/10.1007/978-94-010-0019-2_11) 10. Matthew Purver. 2004. CLARIE: The Clarification Engine. In Proceedings of the Eighth Workshop on Formal Semantics and Dialogue. [find](https://scholar.google.com/scholar?q=Matthew+Purver%2E+2004%2E+CLARIE%3A+The+Clarification+Engine%2E+In+Proceedings+of+the+Eighth+Workshop+on+Formal+Semantics+and+Dialogue%2E) 11. Verena Rieser. 2004. Fragmentary Clarifications on Several Levels for Robust Dialogue Systems. Master’s thesis, School of Informatics, University of Edinburgh. [find](https://scholar.google.com/scholar?q=Verena+Rieser%2E+2004%2E+Fragmentary+Clarifications+on+Several+Levels+for+Robust+Dialogue+Systems%2E+Master%E2%80%99s+thesis%2C+School+of+Informatics%2C+University+of+Edinburgh%2E) 12. Kepa J. Rodriguez and David Schlangen. 2004. Form, Intonation and Function of Clarification Requests in German Task-orientaded Spoken Dialogues. In Proceedings of the Eighth Workshop on Formal Semantics and Dialogue. [find](https://scholar.google.com/scholar?q=Kepa+J%2E+Rodriguez+and+David+Schlangen%2E+2004%2E+Form%2C+Intonation+and+Function+of+Clarification+Requests+in+German+Task%2Dorientaded+Spoken+Dialogues%2E+In+Proceedings+of+the+Eighth+Workshop+on+Formal+Semanti) 13. David Schlangen. 2004. Causes and Strategies for Re-question Clarification in Dialogue. Proceedings of the 5th SIGdial Workshop on Discourse and Dialogue. [find](https://scholar.google.com/scholar?q=David+Schlangen%2E+2004%2E+Causes+and+Strategies+for+Re%2Dquestion+Clarification+in+Dialogue%2E+Proceedings+of+the+5th+SIGdial+Workshop+on+Discourse+and+Dialogue%2E) 14. Gabriel Skantze. 2003. Exploring Human Error Handling Strategies: Implications for Spoken Dialogue Systems. In ISCA Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems. [find](https://scholar.google.com/scholar?q=Gabriel+Skantze%2E+2003%2E+Exploring+Human+Error+Handling+Strategies%3A+Implications+for+Spoken+Dialogue+Systems%2E+In+ISCA+Tutorial+and+Research+Workshop+on+Error+Handling+in+Spoken+Dialogue+Systems%2E) 15. David R. Traum. 1999. Computational Models of Grounding in Collaborative Systems. In Proceedings of the AAAI Fall Symposium on Psychological Models of Communication. [find](https://scholar.google.com/scholar?q=David+R%2E+Traum%2E+1999%2E+Computational+Models+of+Grounding+in+Collaborative+Systems%2E+In+Proceedings+of+the+AAAI+Fall+Symposium+on+Psychological+Models+of+Communication%2E) *Updated 1 November 2026*