An analytical evaluation of search by content and interaction patterns on multimodal meeting records

Bouamrane, Matt-M.; Luz, Saturnino

doi:10.1007/s00530-007-0087-8

Cited by 11 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One might object to our methods arguing that it is wholly un-natural to consider transcripts instead of underlying audio recordings, or better, full-multimodal corpora such as Campbell [5] collected, or more fruitful to ignore text [3]. Researchers have demonstrated that very rich data sources can be tapped to measure interlocutor involvement in conversation, measuring articulation rates, voice intensity, etc.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Measuring Synchrony in Dialog Transcripts

Vogel

Behan

2012

Cognitive Behavioural Systems

View full text Add to dashboard Cite

Abstract. A finite register method of processing dialog transcripts is used to measure interlocutor synchrony. Successive contributions by participants are measured for word n-gram repetitions and temporal overlaps. The Zipfian distribution of words in language use leads to a natural expectation that random re-orderings of dialog contributions will unavoidably exhibit repetition -one might reasonably expect that the frequency of repetition in actual dialog is in fact best explained as a random effect. Accordingly, significance is assessed with respect to randomized contrast values. The contrasts are obtained from averages over randomized reorderings of dialog contributions with temporal spans of the revised dialogs guided by the original durations. Benchmark distributions for allo-repetition and self-repetition are established from existing dialog transcripts covering a pair of pragmatically different circumstances: ATR English language "lingua franca" discussions, Air-Traffic communications (Flight 1549 over the Hudson River). Repetition in actual dialog exceeds the frequency one might expect from a random process. Perhaps surprisingly from the perspective of using repetition as an index of synchrony, self-repetition significantly exceeds allo-repetition. BackgroundResearch into synchrony in dialog has deployed methods such as introducing delay, by using video to mediate communication, in a way that allows manipulation of whether interlocutors have access to partner contributions in real-time or with constructed delay. One type of study involves mother-infant communications mediated by video. The experimental paradigm makes the delay absolute, with a re-play condition seamlessly edited in between live interaction phases [15]. The striking effect is the disinterest expressed by the infant when the delay costs the illusion of interaction.We focus here on two potential factors in the perception of interaction. It would be unsurprising if a politician revealed tactics for seeming engaged during meetings with the public, even when thinking about other matters entirely, as including occasionally repeating words or phrases uttered by their interlocutor or timing contributions to occasionally seem so interested in the content of the conversation to intervene through interruption or talk at the same time as interlocutors without actually taking the floor. In fact, repetition as an indication of

show abstract

Section: Discussionmentioning

confidence: 99%

“…3 The conversations are relatively balanced in the contributions made by participants, and when watches the accompanying video, one notices a high level of mutual engagement. It is reasonable to take these conversations as representative of engaged, balanced conversation.…”

Section: Case Study 1: English As Lingua Franca In Balanced Chatmentioning

confidence: 99%

Measuring Synchrony in Dialog Transcripts

Vogel

Behan

2012

Cognitive Behavioural Systems

View full text Add to dashboard Cite

show abstract

“…This may be at the rich level of description afforded by conversational analysis [18] or at more abstract levels [14,2]. For example, the temporal flow of patterns of silence and non-silence are useful in explicating the structure of discussions and their social dynamics [3]. Consider the regular grammar in (1).…”

Section: Dialogue Symbol Sequencesmentioning

confidence: 99%

“…Another interpretation is that v i is the proposition that a total vocalization of some sort is happening. 3 On this interpretation, because the proposition is stative, each proper sub-interval of the duration of v i is also an interval in which the total vocalization is happening, and v i holds true, even if the total vocalization is incomplete over the sub-interval. This property does not hold as cleanly for the first interpretation, as at a proper sub-interval of the duration of v i , v i itself cannot be correctly said to have been vocalized; rather, a proper part of v i is vocalized over the sub-interval.…”

Section: S {Pmentioning

confidence: 99%

Communication Sequences and Survival Analysis

Vogel

2016

Toward Robotic Socially Believable Behaving Systems - Volume II

View full text Add to dashboard Cite

Two new methods of analyzing dialogue interactions are outlined. One method depends on abstract representations of dialogue events as symbols in a formal language. This method invites analysis of the expressivity requirements of dialogue grammar, as well as distribution analysis of dialogue event symbol sequences. The method is presented in relation to a temporal construction of regular languages, one which supports increasingly fine granularity of temporal analysis. The other method proposed is also temporally oriented. It also depends on dialogue events and dialogue states, and proposes to analyze causal relations among dialogue events through survival analysis. These methods are suggested as additions to the extant repertoire of approaches to understanding the structure and temporal flow of natural dialogue. Additional methods of analysis of natural dialogue may contribute to deeper understanding of the phenomena. With deeper undertanding of natural dialogue one may hope to more fully inform the construction of believable artificial systems that are intended to engage in dialogue with a manner close to human interaction in dialogue.

show abstract

“…Metadata tags also for search optimisation have been stored in an extensible markup language (XML) file to contain timestamps of when a participant types a document during a meeting [18,19]. Attempts have been made to automatically identify where decisions are made during a meeting [20].…”

Section: State-of-the-artmentioning

confidence: 99%

Development of a face-to-face meeting capture and indexing process

Piorkowski

Gao

2011

Proceedings of the 2011 15th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

View full text Add to dashboard Cite

Abstract-A face-to-face (F2F) meeting capture and indexing process could provide an internal feedback mechanism so that results can be monitored against change interventions decided at product lifecycle management (PLM) or performance development review (PDR) meetings. It could also assist people who do not currently have the knowledge or authority to act on what was discussed to share and reflect on the F2F meeting content after the event. In this paper a prototype is described in use with the continuous improvement Plan-Do-Check-Act (PDCA) cycle as a proof-of-concept in BAE Systems. More work should be completed to make the captioning of the F2F meeting content automatic or semi automatic. The presentation of the content in the groupware webpage may also be developed so that there is easier navigation. It would also be useful to have the variables that influence the profitability of the products to be displayed on the webpage so that changes can be tracked against business performance.

show abstract

An analytical evaluation of search by content and interaction patterns on multimodal meeting records

Cited by 11 publications

References 19 publications

Measuring Synchrony in Dialog Transcripts

Measuring Synchrony in Dialog Transcripts

Communication Sequences and Survival Analysis

Development of a face-to-face meeting capture and indexing process

Contact Info

Product

Resources

About