SPEAKER Project (2020-2023)

Apr 1, 2020
Go to Project Site
dialogue systems conversational AI industrial NLP
Alessandra Zarcone
Alessandra Zarcone
Professor of Language Technologies and Cognitive Assistants

Computational linguist with a background in NLP and in psycholinguistics, working on AI, NLP and human-machine interaction.

Publications

GiCCS: A German in-Context Conversational Similarity Benchmark
The Semantic textual similarity (STS) task is commonly used to evaluate the semantic representations that language models (LMs) learn …
Shima Asaadi, Zahra Kolagar, Alina Liebel, Alessandra Zarcone
PDF Cite Dataset Project Poster ACL Anthology
Small Data in NLU: Proposals towards a Data-Centric Approach
Domain-specific voice assistants often suffer from the problem of data scarcity. Publicly available, annotated datasets are in short …
Alessandra Zarcone, Jens Lehmann, Emanuël A.P. Habets
PDF Cite Project
Not So Fast, Classifier – Accuracy and Entropy Reduction in Incremental Intent Classification
Incremental intent classification requires the assignment of intent labels to partial utterances. However, partial utterances do not …
Lianna Hrycyk, Alessandra Zarcone, Luzian Hahn
PDF Cite Dataset Project Poster ACL Anthology
Not So Fast, Classifier – Accuracy and Entropy Reduction in Incremental Intent Classification
Crowdsourcing ecologically-valid dialogue data for German
Despite their increasing success, user interactions with smart speech assistants (SAs) are still very limited compared to human-human …
Yannick Frommherz, Alessandra Zarcone
PDF Cite Dataset Project DOI EPUB
Crowdsourcing ecologically-valid dialogue data for German
New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain
Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L’Osteria for Sunday evening) is a central requirement for Voice …
Touhidul Alam, Alessandra Zarcone, Sebastian Padó
PDF Cite Project Poster Video ACL Anthology
New Domain, Major Effort? How Much Data is Necessary to Adapt a Temporal Tagger to the Voice Assistant Domain