UvA-DARE (Digital Academic Repository) Speakers

How To Do Things With Prompts

This paper applies speech act and politeness theory to a corpus-pragmatic analysis of 2,000 English-language prompts drawn from publicly shared ChatGPT conversations, showing a consistent movement toward indirect, implicit, and fragmentary realizations of directive force, accompanied by a decline in politeness marking.

An Integrated Methodology for Identifying and Classifying Questions and Answers in Spoken Conversation

Questions provide speakers with a means of managing turn-taking, demonstrating engagement, and giving the communicative ‘floor’ to their interlocutor, among a range of other functions. When English interrogatives function as direct questions, they are typically identifiable via their subject-verb inversion (regardless...

You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding

The results show that CoRG remains challenging for current agents, even the best agent reaches only 67.0% success rate, leaving one third of references unresolved, and position CoRG as a concrete benchmark for studying how agents search, inspect, and verify information in realistic multi-tool environments.

Multi-party Conversational Corpus of L1 and L2 for Speech Alignment Research (Teams-SK): Methodological Approach

DISCOURSE MARKERS IN CASUAL CONVERSATIONS: A CONVERSATION ANALYSIS APPROACH

Discourse markers, such as well, you know, so, and right, are ubiquitous in everyday spoken English, yet they are often perceived as semantically empty elements. Adopting a Conversation Analysis (CA) approach, this study investigates the roles and functions of discourse markers in casual interactions between speakers....

TEIDAN: A Multilingual Multiparty Dialogue Corpus

This paper describes the collection design, participants, recording setup, transcription format, and corpus statistics, and provides preliminary analyses to illustrate how TEIDAN can support research on turn-taking, addressee recognition, and multimodal grounding in human-human and human-agent interaction.