Stitching together the conversation - considerations in the design of extended social talk
Bibliographic record
Abstract
Spoken interaction mediates much human social and practical activity. Talk is not monolithic in form but rather weaves in and out of different genres. Practical tasks are peppered with lubricating social talk, while casual conversation proceeds in phases of interactive chat and longer almost monologue chunks. There is increasing interest in building applications which enable convincing human-machine spoken or text interactions, not only to facilitate immediate practical tasks but also to build a longer term relationships within which conversation can take place in order to entertain, provide companionship and care, and build a user model which will facilitate future tasks through an ‘always on’ conversational interface. Such applications will require modelling of the different subgenres of talk, and of how these can be convincingly joined to form a coherent ongoing conversation. In this paper we describe our work towards modelling such talk, focussing on theories of casual talk, insights gleaned from human-human corpora, and implications for dialog system design.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.008 |
| Scholarly communication | 0.007 | 0.010 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.009 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".