Speech act information is used as an auxiliary learning signal alongside textual semantics in pragmatic representations of conversations to reduce lexical noise and improve generalizability in conversational derailment forecasting.
Abstract
Conversational derailment forecasting aims to predict when online discussions will escalate into hostility, enabling proactive moderation. Existing approaches often struggle in low-data settings and to generalize across domains. This poses a challenge for new platforms and smaller communities where annotated data is limited. We propose modeling pragmatic representations of conversations to reduce lexical noise and improve generalizability. Specifically, speech act information is used as an auxiliary learning signal alongside textual semantics. Experimental results show improved performance across three datasets, particularly in low-data and cross-domain settings.
Turn-transition entropy is introduced, a self-supervised target computed from the sequence of speaker transitions, which quantifies the predictability of interaction patterns and can be learned as a single-task objective.
Galo Castillo-L'opez, Alexis Lombard, Gaël de Chalendar et al.· 0 citations
Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While ma...
Sameep Chattopadhyay, Alexander Erdmann, Mari Ostendorf· 0 citations
Conversational and multimodal corpora are central to affective computing, yet their analysis remains challenging due to heterogeneous data formats, modality-specific signals, and interactional dynamics such as speaker turns and temporal variation. Existing approaches often rely on ad hoc toolchains, making workflows di...
Parth Kapur, Shubh Sehgal, Ajay Gopi et al.· 2026 14th International Conf...· 0 citations
In this study, a longitudinal dataset of more than 23 million news headlines from 47 U.S.-based media outlets is used to investigate the use of large language models (LLMs) for sentiment detection. Recent developments in LLMs offer potential gains in contextual understanding, adaptability, and generalization, even thou...
Conversational database interfaces face a critical challenge: users naturally embed queries in conversational noise (greetings, politeness, off-topic remarks), which degrades intent classification accuracy and wastes computational resources. Despite advances in orchestration and retrieval strategies, a fundamental ques...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
