Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?

1 code implementation • 24 Oct 2023 • Dominic Petrak, Nafise Sadat Moosavi, Ye Tian, Nikolai Rozanov, Iryna Gurevych

Learning from free-text human feedback is essential for dialog systems, but annotated data is scarce and usually covers only a small fraction of error types known in conversational AI.

Chatbot Response Generation +1

MATILDA - Multi-AnnoTator multi-language InteractiveLight-weight Dialogue Annotator

1 code implementation • EACL 2021 • Davide Cucurnia, Nikolai Rozanov, Irene Sucameli, Augusto Ciuffoletti, Maria Simi

Dialogue Systems are becoming ubiquitous in various forms and shapes - virtual assistants(Siri, Alexa, etc.

Management

Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers

1 code implementation • EMNLP (DeeLIO) 2020 • Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro, Iryna Gurevych, Nikolai Rozanov, Goran Glavaš

Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models.

Common Sense Reasoning World Knowledge

LIDA: Lightweight Interactive Dialogue Annotator

1 code implementation • IJCNLP 2019 • Edward Collins, Nikolai Rozanov, Bingbing Zhang

Dialogue systems have the potential to change how people interact with machines but are highly dependent on the quality of the data used to train them.

Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks

1 code implementation • CONLL 2018 • Edward Collins, Nikolai Rozanov, Bingbing Zhang

In this paper we analyse exactly which characteristics of a dataset best determine how difficult that dataset is for the task of text classification.

General Classification text-classification +1