I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation

Arabella Sinclair; Rafael Ferreira; Dragan Gasevic; Christopher Lucas; Adam Lopez

doi:10.1007/978-3-030-23207-8_48

I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation

Arabella Sinclair, Rafael Ferreira, Dragan Gasevic, Christopher Lucas, Adam Lopez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

We present a novel method for analysing speaker alignment in second language conversational practice dialogue. In particular, we represent utterances as Dialogue Acts, and use Epistemic Network Analysis to analyse their usage patterns. We hypothesise convergence between speakers will be visible at this level, and influenced by learner ability and tutor strategy. We find as student ability increases, the distribution of student and tutor Dialogue Acts is both initially closer, and converges more over the course of the dialogue. We also find that the type of Dialogue Act use changes both with ability and throughout an interaction. Our results contribute a novel method for the automatic analysis of both learner ability and tutor strategy, which can inform both the development of personalised automatic tutoring tools, and formative assessment and feedback in an educational setting.

Original language	English
Title of host publication	Proceedings of the 20th International Conference on Artificial Intelligence in Education
Editors	Seiji Isotani, Eva Millán, Amy Ogan, Bruce McLaren, Rose Luckin
Publisher	Springer
Chapter	Part II
Pages	257-262
Number of pages	5
Volume	11626
ISBN (Electronic)	978-3-030-23207-8
ISBN (Print)	978-3-030-23206-1
DOIs	https://doi.org/10.1007/978-3-030-23207-8_48
Publication status	Published - 21 Jun 2019
Event	20th International Conference on Artificial Intelligence in Education - Chicago, United States Duration: 25 Jun 2019 → 29 Jun 2019 https://caed-lab.com/aied2019/index.html

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
Volume	11626
ISSN (Electronic)	0302-9743

Conference

Conference	20th International Conference on Artificial Intelligence in Education
Abbreviated title	AIED 2019
Country/Territory	United States
City	Chicago
Period	25/06/19 → 29/06/19
Internet address	https://caed-lab.com/aied2019/index.html

Keywords / Materials (for Non-textual outputs)

epistemic network analysis
scaffolding
dialogue
natural language processing
alignment
Zone of proximal development

Access to Document

10.1007/978-3-030-23207-8_48

I wanna talk like you_SINCLAIR_DoA250319_AFVAccepted author manuscript, 502 KB

https://rd.springer.com/chapter/10.1007%2F978-3-030-23207-8_48

Cite this

Sinclair, A., Ferreira, R., Gasevic, D., Lucas, C., & Lopez, A. (2019). I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation. In S. Isotani, E. Millán, A. Ogan, B. McLaren, & R. Luckin (Eds.), Proceedings of the 20th International Conference on Artificial Intelligence in Education (Vol. 11626, pp. 257-262). (Lecture Notes in Computer Science; Vol. 11626). Springer. https://doi.org/10.1007/978-3-030-23207-8_48

Sinclair, Arabella ; Ferreira, Rafael ; Gasevic, Dragan et al. / I wanna talk like you : Speaker Adaptation to Dialogue Style in L2 Practice Conversation. Proceedings of the 20th International Conference on Artificial Intelligence in Education. editor / Seiji Isotani ; Eva Millán ; Amy Ogan ; Bruce McLaren ; Rose Luckin. Vol. 11626 Springer, 2019. pp. 257-262 (Lecture Notes in Computer Science).

@inproceedings{a80623e0260a458389c2ff60ab00ac0f,

title = "I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation",

abstract = "We present a novel method for analysing speaker alignment in second language conversational practice dialogue. In particular, we represent utterances as Dialogue Acts, and use Epistemic Network Analysis to analyse their usage patterns. We hypothesise convergence between speakers will be visible at this level, and influenced by learner ability and tutor strategy. We find as student ability increases, the distribution of student and tutor Dialogue Acts is both initially closer, and converges more over the course of the dialogue. We also find that the type of Dialogue Act use changes both with ability and throughout an interaction. Our results contribute a novel method for the automatic analysis of both learner ability and tutor strategy, which can inform both the development of personalised automatic tutoring tools, and formative assessment and feedback in an educational setting.",

keywords = "epistemic network analysis, scaffolding, dialogue, natural language processing, alignment, Zone of proximal development",

author = "Arabella Sinclair and Rafael Ferreira and Dragan Gasevic and Christopher Lucas and Adam Lopez",

year = "2019",

month = jun,

day = "21",

doi = "10.1007/978-3-030-23207-8_48",

language = "English",

isbn = "978-3-030-23206-1",

volume = "11626",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "257--262",

editor = "Seiji Isotani and Eva Mill{\'a}n and Amy Ogan and Bruce McLaren and Rose Luckin",

booktitle = "Proceedings of the 20th International Conference on Artificial Intelligence in Education",

address = "United Kingdom",

note = "20th International Conference on Artificial Intelligence in Education, AIED 2019 ; Conference date: 25-06-2019 Through 29-06-2019",

url = "https://caed-lab.com/aied2019/index.html",

}

Sinclair, A, Ferreira, R, Gasevic, D, Lucas, C & Lopez, A 2019, I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation. in S Isotani, E Millán, A Ogan, B McLaren & R Luckin (eds), Proceedings of the 20th International Conference on Artificial Intelligence in Education. vol. 11626, Lecture Notes in Computer Science, vol. 11626, Springer, pp. 257-262, 20th International Conference on Artificial Intelligence in Education, Chicago, Illinois, United States, 25/06/19. https://doi.org/10.1007/978-3-030-23207-8_48

I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation. / Sinclair, Arabella; Ferreira, Rafael; Gasevic, Dragan et al.
Proceedings of the 20th International Conference on Artificial Intelligence in Education. ed. / Seiji Isotani; Eva Millán; Amy Ogan; Bruce McLaren; Rose Luckin. Vol. 11626 Springer, 2019. p. 257-262 (Lecture Notes in Computer Science; Vol. 11626).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - I wanna talk like you

T2 - 20th International Conference on Artificial Intelligence in Education

AU - Sinclair, Arabella

AU - Ferreira, Rafael

AU - Gasevic, Dragan

AU - Lucas, Christopher

AU - Lopez, Adam

PY - 2019/6/21

Y1 - 2019/6/21

N2 - We present a novel method for analysing speaker alignment in second language conversational practice dialogue. In particular, we represent utterances as Dialogue Acts, and use Epistemic Network Analysis to analyse their usage patterns. We hypothesise convergence between speakers will be visible at this level, and influenced by learner ability and tutor strategy. We find as student ability increases, the distribution of student and tutor Dialogue Acts is both initially closer, and converges more over the course of the dialogue. We also find that the type of Dialogue Act use changes both with ability and throughout an interaction. Our results contribute a novel method for the automatic analysis of both learner ability and tutor strategy, which can inform both the development of personalised automatic tutoring tools, and formative assessment and feedback in an educational setting.

AB - We present a novel method for analysing speaker alignment in second language conversational practice dialogue. In particular, we represent utterances as Dialogue Acts, and use Epistemic Network Analysis to analyse their usage patterns. We hypothesise convergence between speakers will be visible at this level, and influenced by learner ability and tutor strategy. We find as student ability increases, the distribution of student and tutor Dialogue Acts is both initially closer, and converges more over the course of the dialogue. We also find that the type of Dialogue Act use changes both with ability and throughout an interaction. Our results contribute a novel method for the automatic analysis of both learner ability and tutor strategy, which can inform both the development of personalised automatic tutoring tools, and formative assessment and feedback in an educational setting.

KW - epistemic network analysis

KW - scaffolding

KW - dialogue

KW - natural language processing

KW - alignment

KW - Zone of proximal development

U2 - 10.1007/978-3-030-23207-8_48

DO - 10.1007/978-3-030-23207-8_48

M3 - Conference contribution

SN - 978-3-030-23206-1

VL - 11626

T3 - Lecture Notes in Computer Science

SP - 257

EP - 262

BT - Proceedings of the 20th International Conference on Artificial Intelligence in Education

A2 - Isotani, Seiji

A2 - Millán, Eva

A2 - Ogan, Amy

A2 - McLaren, Bruce

A2 - Luckin, Rose

PB - Springer

Y2 - 25 June 2019 through 29 June 2019

ER -

Sinclair A, Ferreira R, Gasevic D, Lucas C , Lopez A. I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation. In Isotani S, Millán E, Ogan A, McLaren B, Luckin R, editors, Proceedings of the 20th International Conference on Artificial Intelligence in Education. Vol. 11626. Springer. 2019. p. 257-262. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-23207-8_48

I wanna talk like you: Speaker Adaptation to Dialogue Style in L2 Practice Conversation

Abstract / Description of output

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this