| 1. |
- Axelsson Nord, Ebba, et al.
(author)
-
What do you mean? Eliciting enthymemes in text-based dialogue
- 2021
-
In: The 25th Workshop of the Semantics and Pragmatics of Dialogue, September 20–22, 2021, Potsdam / The Internet.. - 2308-2275.
-
Conference paper (other academic/artistic)abstract
- We report a proof of concept text-based chat study which inserts spoof questions in a real time conversation in order to elicit participants reasoning. The results show that different questions are more or less effective at elicit- ing explicit enthymematic reasons, which is a technique that could be employed to augment conversational artificial intelligence systems to improve their reasoning abilities.
|
|
| 2. |
- Bernardy, Jean-Philippe, 1978, et al.
(author)
-
Rational Speech Act models are utterance-independent updates of world priors
- 2022
-
In: Proceedings of SemDial 2022 (DubDial): The 26th Workshop on the Semantics and Pragmatics of Dialogue, August, 22-24, 2022, Dublin / Eleni Gregoromichelaki, Julian Hough, John D. Kelleher (Editors). - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- A popular framework for modelling pragmatic effects is the “rational speech act” (RSA) model introduced by Frank and Goodman (2012). The idea behind RSA is that, to interpret an utter- ance, a rational (pragmatic) listener reasons about a speaker who chooses their utterance by reasoning about the listener, using a literal se- mantic model. In the present work, we take the RSA model at face value, but we reformulate it in information-theoretic terms. We find that the pragmatic listener model can be reconceived as an update of the prior over worlds that can be provided independently of the speaker’s actual utterance. This update consists in a preference for world states which are the most specific to a given utterance in the set of possible ut- terances given by the pragmatic context. Our reformulation allows us to deduce general prop- erties of pragmatic reasoning problems. As an example, we show that RSA does not predict certain quantity implicatures in the presence of bell-curve priors.
|
|
| 3. |
- Breitholtz, Ellen, et al.
(author)
-
Communicable reasons: How children learn topoi through dialogue
- 2020
-
In: Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue, Waltham, Massachusetts, July 18-19, 2020, (online) / Sophia Malamud, James Pustejovsky, Jonathan Ginzburg (Editors). - : SEMDIAL. - 2308-2275.
-
Conference paper (peer-reviewed)
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
- Cano Santín, José Miguel, 1990, et al.
(author)
-
Interactive visual grounding with neural networks
- 2019
-
In: Proceedings of LondonLogue - Semdial 2019: The 23rd Workshop on the Semantics and Pragmatics of Dialogue, London, 4-6 September 2019. - London, UK : Queen Mary University of London. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- Training strategies for neural networks are not suitable for real time human-robot interaction. Few-shot learning approaches have been developed for low resource scenarios but without the usual teacher/learner supervision. In this work we present a combination of both: a situated dialogue system to teach object names to a robot from its camera images using Matching Networks (Vinyals et al., 2016). We compare the performance of the system with transferred learning from pre-trained models and different conversational strategies with a human tutor.
|
|
| 8. |
- Carrion del Fresno, Andrea, et al.
(author)
-
Dialogue strategies for... cómo se dice entrenamiento de vocabulario?
- 2022
-
In: Eleni Gregoromichelaki, Julian Hough & John D. Kelleher (eds.): Proceedings of the 26th Workshop On the Semantics and Pragmatics of Dialogue. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- We carry out a small-scale empirical study of a dialogue strategy (conversational pattern) found in second language learner dialogues where a language-assisting teacher is present, allowing learners to pick up new words and train on them while maintaining a conversation. We also provide a formal model of the observed conversational pattern including several frequently occurring variants, as well as a demonstration implementation which is able to reproduce the most common variant of the pattern.
|
|
| 9. |
|
|
| 10. |
- Cooper, Robin, 1947
(author)
-
Phrase structure rules as dialogue update rules
- 2014
-
In: Proceedings of The 18th Workshop on the Semantics and Pragmatics of Dialogue, Edinburgh, September 1-3, 2014, ed. by Verena Rieser and Philippe Muller, Heriot-Watt University. - 2308-2275. ; , s. 26-34
-
Conference paper (peer-reviewed)
|
|
| 11. |
|
|
| 12. |
- de Graaf, Erik Wouter, 1991, et al.
(author)
-
KILLE: Learning Objects and Spatial Relations with Kinect
- 2015
-
In: Proceedings of goDIAL - Semdial 2015: The 19th Workshop on the Semantics and Pragmatics of Dialogue. Gothenburg, 24–26 August 2015 / Christine Howes and Staffan Larsson (eds.). - 2308-2275.
-
Conference paper (other academic/artistic)abstract
- We present a situated dialogue system designed to learn objects and spatial relations from relatively few examples, based on camera imagery and dialogue interaction with a human partner. We also report on the baseline evaluation of the system.
|
|
| 13. |
- Decker, Amandine, 2000, et al.
(author)
-
Topic and genre in dialogue
- 2023
-
In: Proceedings of the 27th Workshop on the Semantics and Pragmatics of Dialogue - Poster Abstracts, August 16–17, 2023, Maribor, Slovenia / Andy Lücking, Chiara Mazzocconi & Darinka Verdonik (eds.). - 2308-2275.
-
Conference paper (peer-reviewed)
|
|
| 14. |
- Dobnik, Simon, 1977, et al.
(author)
-
A Model for Attention-Driven Judgements in Type Theory with Records
- 2016
-
In: JerSem: The 20th Workshop on the Semantics and Pragmatics of Dialogue. J. Hunter, M. Simons, and M. Stone (eds.). New Brunswick, NJ USA, July 16–18 2016.. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- This paper makes three contributions to the discussion on the applicability of Type Theory with Records (TTR) to embodied dialogue agents. First, it highlights the problem of type assignment or judgements in practical implementations which is re- source intensive. Second, it presents a judgement control mechanism, which con- sists of grouping of types into clusters or states by their thematic relations and selec- tion of types following two mechanisms inspired by the Load Theory of selective attention and cognitive control (Lavie et al., 2004), that addresses this problem. Third, it presents a computational frame- work, based on Bayesian inference, that offers a basis for future practical exper- imentation on the feasibility of the pro- posed approach.
|
|
| 15. |
- Dobnik, Simon, 1977, et al.
(author)
-
Categorisation of conversational games in free dialogue over spatial scenes
- 2018
-
In: Proceedings of AixDial - Semdial 2018: The 22st Workshop on the Semantics and Pragmatics of Dialogue, Aix-en-Provence, 8-10 November 2018 / Laurent Prévot, Magalie Ochs and Benoît Favre (eds.). - Aix-en-Provence, France : Semdial. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- We describe an extension of a corpus of dialogues over perceptual scenes with the annotation of conversational games in which particular interactive strategies are adopted by conversational partners which result in regularities of dialogue features. We hope these will be useful for computational modelling of perceptual dialogue.
|
|
| 16. |
- Dobnik, Simon, 1977, et al.
(author)
-
Changing perspective: Local alignment of reference frames in dialogue
- 2015
-
In: Proceedings of SemDial 2015 (goDIAL): The 19th Workshop on the Semantics and Pragmatics of Dialogue. Christine Howes and Staffan Larsson (eds.). Gothenburg, 24–26 August 2015. - 2308-2275. ; , s. 24-32
-
Conference paper (peer-reviewed)
|
|
| 17. |
- Dobnik, Simon, 1977, et al.
(author)
-
Chat-o-matic: an online chat tool for collecting conversations of situated dialogue
- 2022
-
In: Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue, August, 22-24, 2022, Dublin. - Poster Abstracts. - 2308-2275.
-
Conference paper (other academic/artistic)abstract
- We present a demo of an online chat tool that we have developed to collect conversational data from situated dialogue called Semant-o-matic chat or Chat-o-matic. This allows us to setup data collection experiments both with targeted participants and with online crowd-sourcing platforms.
|
|
| 18. |
- Dobnik, Simon, 1977, et al.
(author)
-
Investigating the role of priming and alignment of perspective in dialogue
- 2013
-
In: Proceedings of the 17th Workshop on the Semantics and Pragmatics of Dialogue, Amsterdam, 16–18 December 2013, Amsterdam. - 2308-2275. ; 17, s. 182-184
-
Conference paper (other academic/artistic)abstract
- We examine the alignment of the primed frame of reference (FoR) for spatial descriptions over several utterances of a situated dialogue. We confirm the tendency of FoR alignment and that the intrinsic FoR is the most popular one independent of the priming.
|
|
| 19. |
- Dobnik, Simon, 1977, et al.
(author)
-
On visual coreference chains resolution
- 2019
-
In: Proceedings of LondonLogue - Semdial 2019: The 23rd Workshop on the Semantics and Pragmatics of Dialogue, 4-6 September, 2019, London. - London, UK : Queen Mary University of London. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- We explore to what degree an existing textual coreference resolution tools can be applied to visual dialogue data. The analysis of error of the coreference system (i) demonstrates the extent to which such data differs from the writ- ten document texts that these tools are typically applied on; (ii) informs about the relation between information expressed in language and vision; and (iii) suggests further directions in which coreference tools should be adapted for visual dialogue.
|
|
| 20. |
- Dobnik, Simon, 1977, et al.
(author)
-
Pattern recognition is not enough: representing language, action and perception with modular neural networks
- 2019
-
In: Proceedings of LondonLogue - Semdial 2019: The 23rd Workshop on the Semantics and Pragmatics of Dialogue, 4-6 September 2019, London / Christine Howes, Julian Hough, Casey Kennington (Editors). - London, UK : Queen Mary University of London. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- Current deep learning approaches to modelling of spatial language in generating image captions have shortcomings because they are focused on recognition of visual patterns. The multiplicity of factors that influence spatial language which also include aspects of interaction between speakers and between speakers and their environment invites a modular approach where the solution can be built in a piece-wise manner and then integrated. We call this approach where deep learning is assisted with domain knowledge expressed as modules that are trained on data a top-down or mechanistic approach to otherwise a bottom-up phenomenological approach.
|
|
| 21. |
- Dobnik, Simon, 1977, et al.
(author)
-
(Perceptual) grounding as interaction
- 2017
-
In: Proceedings of Saardial (Semdial 2017): The 21st Workshop on the Semantics and Pragmatics of Dialogue, Saarbrücken, August 15–17, 2017 / Volha Petukhova and Ye Tian (eds.). - Saarbrücken, Germany : SemDial. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- We examine how changing perceptual contexts affects grounding of words, in particular spatial descriptions, in perceptual features and argue that grounding is interactive. We discuss two effects of perceptual context. Grounding of spatial de- scriptions may be affected by the richness of the perceptual context which allows us to build more complex representations of scenes. Secondly, perceptual grounding is dependent on the task (and associated attention) which affects the preference of features. The second property connects perceptual grounding closely to linguistic grounding in dialogue. We argue that dynamic perceptual grounding has implica- tions for the words-as-classifiers approach to semantics.
|
|
| 22. |
- Dobnik, Simon, 1977, et al.
(author)
-
Priming and Alignment of Frame of Reference in Situated Conversation
- 2014
-
In: Proceedings of SemDial 2014 (DialWatt): The 18th Workshop on the Semantics and Pragmatics of Dialogue, Edinburgh, September 1-3, 2014. - 2308-2275. ; , s. 43-52
-
Conference paper (peer-reviewed)abstract
- In this paper, we study how the frame of reference (FoR) or perspective is communicated in dialogue through mechanisms such as linguistic priming and alignment (Pickering and Garrod, 2004). In order to isolate the contribution of these mechanisms we deliberately work with a constrained artificial dialogue scenario. First we collect data that deal with human behaviour in interpreting descriptions that are ambiguous in terms of the FoR. From these interpretations we extract and identify strategies for FoR assignment in conversations which we then apply to generate descriptions and measure human agreement with the system. Our findings confirm that both speakers and hearers rely on such mechanisms in conversation.
|
|
| 23. |
- Dobnik, Simon, 1977, et al.
(author)
-
The red cup on the left: Reference, coreference and attention in visual dialogue
- 2021
-
In: Proceedings of the 25th Workshop on the Semantics and Pragmatics of Dialogue, September 20–22, 2021, Potsdam / The Internet / edited by Ellen Breitholtz, Kallirroi Georgila and David Schlangen. - Potsdam, Germany : SemDial. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- We examine how conversational partners refer, corefer and direct attention in conversations over a visual scene. Using an extension of the CoNLL annotation scheme for coreference for the visual domain we annotate the Swedish part of the Cups corpus. The annotation consists of identifying noun phrases and assigning them IDs of entities in the visual scene. We perform quantitative and qualitative linguistic analyses of the annotated data which point towards interesting observations of how conversational participants direct attention: it is likely that entities are co-referred to within the same conversational game, for spatial descriptions there is a preference for lateral dimensions over front and back and more attention is directed towards entities that are visually ambiguous or those that are part of the task. Overall, we demonstrate that referential attention is driven by both visual and conceptual, task-related information.
|
|
| 24. |
- Dobnik, Simon, 1977, et al.
(author)
-
What to refer to and when? Reference and re-reference in two language-and-vision tasks
- 2022
-
In: Proceedings of DubDial - Semdial 2022: The 26th Workshop on the Semantics and Pragmatics of Dialogue. - Dublin, Ireland : Semdial. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- How do we refer to scene entities in interactive language-and-vision tasks? We explore refer- ence and re-reference in two tasks, link them to a model of attention and discuss our findings in relation to modelling situated interaction.
|
|
| 25. |
|
|
| 26. |
|
|
| 27. |
|
|
| 28. |
- Howes, Christine, 1978, et al.
(author)
-
Good call! Grounding in a Directory Enquiries Corpus
- 2019
-
In: Proceedings of the 23rd Workshop on the Semantics and Pragmatics of Dialogue - Full papers, 4-6 September, London, UK / Christine Howes, Julian Hough, Casey Kennington (Editors). - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- This paper describes the collection of a corpus of telephone directory enquiries conversations. We analyse the feedback used in the corpus and discuss implications for dialogue systems.
|
|
| 29. |
- Ioussef, Denis, et al.
(author)
-
Don't you think that a rhetorical question can convey an argument?
- 2021
-
In: Proceedings of the 25th Workshop on the Semantics and Pragmatics of Dialogue September 20–22, 2021, Potsdam / The Internet / Ellen Breitholtz, Kallirroi Georgila, David Schlangen (Editors). - Potsdam : University of Potsdam. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- Rhetorical questions have been addressed from many different linguistic perspectives, however, their interactional role has been hith- erto underexplored. We here present an ex- ploratory study of rhetorical questions in a cor- pus of dialogues discussing a moral dilemma from an interactional perspective, using the notions of enthymemes and topoi. Results show that rhetorical questions are used to introduce enthymematic arguments and to facilitate link- ing together parts of arguments over several ut- terances.
|
|
| 30. |
- Kempson, Ruth, et al.
(author)
-
How Mechanistic Can Accounts Of Interaction Be?
- 2009
-
In: Proceedings of the 13th SEMDIAL Workshop on the Semantics and Pragmatics of Dialogue (DiaHolmia). - Stockholm, Sweden. - 2308-2275. ; , s. 67-74
-
Conference paper (peer-reviewed)
|
|
| 31. |
- Kronlid, Fredrik, 1973, et al.
(author)
-
Using Learned Predictions of User Utterances to Decrease Distraction
- 2013
-
In: Proceedings of the Workshop on the Semantics and Pragmatics of Dialogue. - Amsterdam. - 2308-2275. ; 17, s. 210-212, s. 210-212
-
Journal article (peer-reviewed)abstract
- Driver distraction is one of the most common causes of accidents. By having a dialogue manager request predicted user answers from a user model instead of asking the user, we can reduce the number of utterances in the dialogue and thereby reduce the time that the user is distracted.
|
|
| 32. |
- Künkele, Dominik, 1999, et al.
(author)
-
Referring as a collaborative process: learning to ground language through language games
- 2023
-
In: Proceedings of MariLogue - Semdial 2023: The 27th Workshop on the Semantics and Pragmatics of Dialogue. - Maribor, Slovenia : University of Maribor, Faculty of Eelectrical Engineering and Computer Science. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- How do artificial agents based on neural networks coordinate on a new language through referential games over 3-d scenes? We extend a popular CLEVR dataset to control for different combinations of features of target and distractor objects and examine the success of referential grounding learned by the agents.
|
|
| 33. |
- Larsson, Staffan, 1969, et al.
(author)
-
Dialogue Acts and Updates for Semantic Coordination
- 2017
-
In: Proceedings of the 21st Workshop on the Semantics and Pragmatics of Dialogue, Saarbrücken, 15–17 August 2017 / Volha Petukhova and Ye Tian (eds.). - Saarbrücken. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- This paper outlines an account of semantic coordination, focusing on word meaning negotiation, formalised in Type Theory with Records (TTR). The account combines parts of two dialogue act taxonomiesrelated to semantic coordination, and relate these to meaning updates both on an abstract level and at a more detailed level.
|
|
| 34. |
- Larsson, Staffan, 1969, et al.
(author)
-
Effects of Speech Cursor on Visual Distraction in In-vehicle Interaction: Preliminary Results
- 2014
-
In: DialWatt — Semdial 2014 The 18th Workshop on the Semantics and Pragmatics of Dialogue, Edinburgh, September 1-3, 2014 /edited by Verena Rieser and Philippe Muller. - 2308-2275. ; , s. 208-210
-
Conference paper (peer-reviewed)abstract
- This paper presents preliminary results on visual distraction tests concerning various multimodality solutions for in-vehicle dialogue systems in the SIMSI project. In particular, the Speech Cursor concept is evaluated in comparison to other solutions and is found to decrease visual distraction, especially for tasks involving list browsing.
|
|
| 35. |
- Larsson, Staffan, 1969
(author)
-
Extensions Are Indeterminate if Intensions Are Classifiers
- 2020
-
In: Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue, Held virtually at Brandeis University, Waltham, Massachusetts July 18-19 2020 / Sophia Malamud, James Pustejovsky & Jonathan Ginzburg (eds.). - : Semidal. - 2308-2275.
-
Conference paper (peer-reviewed)
|
|
| 36. |
- Larsson, Staffan, 1969
(author)
-
Meaning as Coordinated Compositional Classification
- 2019
-
In: Proceedings of the 23rd Workshop on the Semantics and Pragmatics of Dialogue, Dialogue - Invited Talks, / Christine Howes, Julian Hough, Casey Kennington (Editors). London, 4-6 september 2019. - 2308-2275.
-
Conference paper (other academic/artistic)
|
|
| 37. |
|
|
| 38. |
- Larsson, Staffan, 1969
(author)
-
The State of the Art in Dealing with User Answers
- 2015
-
In: SEMDIAL 2015 (goDIAL). Proceedings of the 19th Workshop on the Semantics and Pragmatics of Dialogue. Christine Howes and Staffan Larsson (eds.) Gothenburg, 24–26 August 2015. - 2308-2275. ; 19, s. 190-191
-
Conference paper (peer-reviewed)abstract
- This paper takes an in-depth look at how dialogue systems from the major players on the market actually deal with some conversational behaviours frequently encountered in human-human dialogue, in particular with respect to dealing with different variants of user answers to system questions. It is found that no existing commercial system deals with all the behaviours investigated in an appropriate manner.
|
|
| 39. |
- Larsson, Staffan, 1969, et al.
(author)
-
Visual distraction test setup for an multimodal in-vehicle dialogue system
- 2013
-
In: Proceedings of the Workshop on the Semantics and Pragmatics of Dialogue. - 2308-2275. ; 17, s. 215-217
-
Journal article (peer-reviewed)abstract
- The goal of the SIMSI (Safe In-vehicle Multimodal Speech Interaction) project is threefold. Firstly, to integrate a dialogue system for menu-based dialogue with a GUI-driven in-vehicle infotainment system. Secondly, to further improve the integrated system with respect to driver distraction, thus making the system safer to use while driving. Thirdly, to verify that the resulting system decreases visual distraction and cognitive load during interaction. This demo paper describes the test environment designed to enable evaluation of the system, and the planned visual distraction tests.
|
|
| 40. |
- Lundholm Fors, Kristina, 1977, et al.
(author)
-
Are you mocking me or are you laughing with me?
- 2016
-
In: SEMDIAL 2016, JerSem, Proceedings of the 20th Workshop on the Semantics and Pragmatics of Dialogue, 16-18 July 2016 Rutgers, New Brunswick, NJ, USA / Julie Hunter, Mandy Simons, and Matthew Stone (eds.). - 2308-2275.
-
Conference paper (other academic/artistic)
|
|
| 41. |
- Maraev, Vladislav, 1986, et al.
(author)
-
Dialogue act classification is a laughing matter
- 2021
-
In: Proceedings of the 25th Workshop on the Semantics and Pragmatics of Dialogue, Potsdam & The Internet, 20–22 September 2021 / Ellen Breitholtz, Kallirroi Georgila and David Schlangen (eds.). - Potsdam : Semdial. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- In this paper we explore the role of laughter in attributing communicative intents to utterances, i.e. detecting the dialogue act performed by them. We conduct a corpus study in adult phone conversations showing how different dialogue acts are characterised by specific laughter patterns, from both the speaker and from the partner. Furthermore, we show that laughs can positively impact the performance of Transformer-based models in a dialogue act recognition task. Our results highlight the importance of laughter for meaning construction and disambiguation in interaction.
|
|
| 42. |
- Maraev, Vladislav, 1986, et al.
(author)
-
Towards KoS/TTR-based proof-theoretic dialogue management
- 2018
-
In: Proceedings of SemDial 2018 (AixDial): The 22nd Workshop on the Semantics and Pragmatics of Dialogue, Aix-en-Provence, 8-10 November 2018 / Laurent Prévot, Magalie Ochs and Benoît Favre (eds.). - 2308-2275.
-
Conference paper (peer-reviewed)
|
|
| 43. |
- Mazzocconi, Chiara, et al.
(author)
-
Laughter Repair
- 2018
-
In: Proceedings of SemDial 2018 (AixDial): The 22nd Workshop on the Semantics and Pragmatics of Dialogue. Laurent Prévot, Magalie Ochs and Benoît Favre (eds.), 8-10 November 2018, Aix-en-Provence, France. - Aix-en-Provence : Aix Marseille Université. - 2308-2275.
-
Conference paper (peer-reviewed)
|
|
| 44. |
- Noble, Bill, et al.
(author)
-
What do you mean by negotiation? Annotating social media discussions about word meaning
- 2021
-
In: Proceedings of the 25th Workshop on the Semantics and Pragmatics of Dialogue, September 20–22, 2021, Potsdam / The Internet. - Potsdam : SemDial. - 2308-2275.
-
Conference paper (peer-reviewed)abstract
- We present a formalisation and annotation protocol for word meaning negotiation (WMN), a conversational routine in which speakers explicitly discuss the meaning of a word or phrase. WMN is formalised as an interaction game with a shared game board and rules for subsequent contributions, as well as a semantic update function based on the state of the game board. We develop an annotation schema based on this formalisation and present the
|
|
| 45. |
- Sandahl, Magdalena, 1976, et al.
(author)
-
A corpus of Swedish conversations with a librarian
- 2020
-
In: Proceedings of WatchDial - Semdial 2020: The 24th Workshop on the Semantics and Pragmatics of Dialogue, 18-19 July 2020, Brandeis, Waltham, New Jersey (Online). - 2308-2275.
-
Conference paper (other academic/artistic)abstract
- We describe a novel Swedish corpus of social and task related dialogues that has been collected from the interactions of library patrons with the library staff. The corpus is intended to aid the development of language technology tools, including a dialogue system, that can be incorporated in the existing chat solution to facilitate and improve interaction between patrons and library staff. We describe the properties of the corpus collected so far, its annotation with topics and evaluation of annotation.
|
|
| 46. |
- Schlöder, Julian, 1989, et al.
(author)
-
Why?
- 2016
-
In: Semdial 2016 JerSem, Proceedings of the 20th Workshop on the Semantics and Pragmatics of Dialogue, Julie Hunter, Mandy Simons, and Matthew Stone (eds.) New Brunswick, NJ, 16–18 July 2016. - 2308-2275. ; , s. 5-14
-
Conference paper (peer-reviewed)
|
|
| 47. |
|
|
| 48. |
|
|
| 49. |
- Strand, Linnea, 1994, et al.
(author)
-
Topic modelling for a virtual librarian assistant tool
- 2020
-
In: Proceedings of WatchDial - Semdial 2020: The 24the Workshop on the Semantics and Pragmatics of Dialogue, 18-19 July 2020, Brandeis, Waltham, New Jersey, (Online). - 2308-2275.
-
Conference paper (other academic/artistic)abstract
- We outline a topic classifier for a virtual librarian assistant trained on a corpus of conversations between patrons and librarians. Because this conversation data is limited, we explore the possibility of training the system on a domain of artificial data generated from distilled versions of real chats and applying transfer learning techniques to augment learning on real data. By training the model on artificial dialogues and fine-tuning it on real data, we hope to achieve better overall performance for the classifier even when little data is available. This abstract describes the data generation (augmentation) process, the model architecture and presents some preliminary results.
|
|
