Entrainment in Multi-Party Spoken Dialogues at Multiple Linguistic Levels

@inproceedings{Rahimi2017EntrainmentIM,
  title={Entrainment in Multi-Party Spoken Dialogues at Multiple Linguistic Levels},
  author={Zahra Rahimi and Anish Kumar and Diane J. Litman and Susannah B. F. Paletz and Mingzhi Yu},
  booktitle={INTERSPEECH},
  year={2017}
}
Linguistic entrainment, the phenomena whereby dialogue partners speak more similarly to each other in a variety of dimensions, is key to the success and naturalness of interactions. While there is considerable evidence for both lexical and acoustic-prosodic entrainment, little work has been conducted to investigate the relationship between these two different modalities using the same measures in the same dialogues, specifically in multi-party dialogue. In this paper, we measure lexical and… 

Tables from this paper

Looking for Structure in Lexical and Acoustic-Prosodic Entrainment Behaviors
TLDR
A negative result is presented, finding no meaningful correlations, clusters, or principal components in various entrainment measures, and practical and theoretical implications are discussed.
A Neural Network-Based Linguistic Similarity Measure for Entrainment in Conversations
TLDR
This work proposes to use a neural network model to perform the similarity measure for entrainment, which is context-aware, and further leverages a novel component to learn the shared high-level linguistic features across dialogues.
“Talk to me with left, right, and angles”: Lexical entrainment in spoken Hebrew dialogue
TLDR
Using two existing measures, Hebrew speakers interacting in a Map Task, a popular experimental setup, is analyzed and rich evidence of lexical entrainment is found, with a lack ofEntrainment on hedge words being the main difference.
Entrainment2Vec: Embedding Entrainment for Multi-Party Dialogues
TLDR
A novel graph-based vector representation of multi-party entrainment that incorporates both strength and dynamics of pairwise entrainments relations is proposed and shows promising results at the downstream task of predicting team outcomes.
Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT
TLDR
This work proposes to leverage linguistic coordination to rerank the N-best candidates produced by BERT, a state-of-the-art pre-trained language model, demonstrating the utility of repairing machine-generated outputs by leveraging a linguistic theory.
Convergence is predicted by particular interlocutors, not speakers
Do characteristics of individuals affect how much they converge, such that some speakers consistently convergemore than others? Are there aspects of conversations or interlocutors that elicit more or
Investigating the Relationship between Multi-Party Linguistic Entrainment, Team Characteristics and the Perception of Team Social Outcomes
TLDR
This work developed new measures of multi-party entrainment on features describing linguistic style, and examined the relationship between entrainments and team characteristics in terms of gender composition, team size, and diversity.
Natural Leaders: Some Interlocutors Elicit Greater Convergence Across Conversations and Across Characteristics
TLDR
There are natural leaders of convergence, who elicit more convergence than others across characteristics and across conversations, and the lack of similar evidence for speakers who converge more than others suggests that social factors have a stronger effect in mediating convergence than putative individual tendencies.
Studying Alignment in a Collaborative Learning Activity via Automatic Methods: The Link Between What We Say and Do
A dialogue is successful when there is alignment between the speakers, at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a
...
1
2
...

References

SHOWING 1-10 OF 34 REFERENCES
The Teams Corpus and Entrainment in Multi-Party Spoken Dialogues
TLDR
A corpus where teams of three or four speakers play two rounds of a cooperative board game is created, which consists of audio, video, transcriptions, and questionnaire data for 63 teams and is illustrated as a novel resource for studying team entrainment.
High Frequency Word Entrainment in Spoken Dialogue
TLDR
The results show that such entrainment is predictive of the perceived naturalness of dialogues and is significantly correlated with task success; in overall interaction flow, higher degrees ofEntrainment are associated with more overlaps and fewer interruptions.
Measuring Acoustic-Prosodic Entrainment with Respect to Multiple Levels and Dimensions
TLDR
This work investigates entrainment in four acoustic and prosodic dimensions and explores whether speakers coordinate with each other in these dimensions over the conversation as a whole as well as on a turn-by-turn basis and in both relative and absolute terms.
Acoustic-Prosodic Entrainment and Rapport in Collaborative Learning Dialogues
TLDR
It is found that entrainment does correlate to rapport; speakers appear to entrain primarily by matching their prosody on a turn-by-turn basis, and pitch is the most significant acoustic-prosodic feature people entrain on when rapport is present.
Entrainment in Spoken Dialogue Systems: Adopting, Predicting and Influencing User Behavior
TLDR
This thesis proposal presents a comprehensive look at entrainment in human conversations and howEntrainment may be incorporated into the design of spoken dialogue systems in order to improve system performance and user satisfaction.
Entrainment in Speech Preceding Backchannels.
TLDR
The results show that speaking partners entrain on BPCs; that is, they tend to use similar sets of B PCs; this similarity increases over the course of a dialogue; and this similarity is associated with measures of dialogue coordination and task success.
Implementing Acoustic-Prosodic Entrainment in a Conversational Avatar
TLDR
An architecture and algorithm for implementing acoustic-prosodic entrainment in SDS is presented and it is shown that speech produced under this algorithm conforms to the feature targets, satisfying the properties ofEntrainment behavior observed in human-human conversations.
Naturalness and rapport in a pitch adaptive learning companion
TLDR
This paper proposes three methods of pitch adaptation based on analysis of human entrainment, and proposes and designs a system which can manipulate the pitch of text-to-speech output adaptively and finds a clear relationship between perceptions of rapport and different forms of pitch adaptations.
Acoustic-Prosodic Entrainment and Social Behavior
TLDR
It is found that entrainment is more pronounced when intensity or speaking rate is especially high or low, and it is more important to the smoothness and flow of male-male dialogue than it is for female-female or mixed-gender pairs.
How Entrainment Increases Dialogical Effectiveness
TLDR
It is shown that in certain dialogical situations it is important to adapt linguistically towards the users, and entrainment, as such, is firstly examined in the domain of multimodal dialogical assi stance systems.
...
1
2
3
4
...