[Archimedes NLP Theme Meeting] Human-centered Natural Language Processing with Deep Learning

Archimedes NLP Theme Meeting: PhD thesis presentation, Monday 28 April, 17:30-18:30 (Greek time)

Presenter: Tatiana Passali

Moderator: Grigorios Tsoumakas

Title: "Human-centered Natural Language Processing with Deep Learning"

Room: Theano, Archimedes Unit (1 Artemidos str., ART1 building, first floor)

and virtually via Zoom Meetings - https://zoom.us/j/92948800857?pwd=nhpovaUnRAY8DEOQuRK1bodjeis3ba.1

• Meeting ID: 929 4880 0857

• Passcode: On8CXk

Check for additional ways to participate/dial in at the bottom of the announcement.

 

Abstract:

Despite the impressive progress of Natural Language Processing (NLP) with the advent of Large Language Models (LLMs), building truly human-centered systems remains a pressing challenge. In the context of automated summarization, recent advances have moved beyond generic summaries towards controllable and topic-controllable summarization models, enabling users to guide the content and focus of generated summaries. Alongside, text simplification and plain language summarization have gained importance to make information more accessible to audiences with varying levels of expertise, literacy or cognitive needs. Deep learning methods have shown remarkable capabilities in these tasks, yet current models often lack control and adaptability with diverse user requirements. Another related challenge lies in processing spontaneous speech, where disfluency detection improves the quality and robustness of downstream applications. However, the lack of annotated datasets, particularly in low-resource conversational settings, limits the development of accurate and robust disfluency detection models. This thesis introduces and explores methods for controllable summarization, text simplification and disfluency detection to advance NLP methods toward a more human-centered design.

 

Stay tuned!

For ways to receive news about the NLP Group and its meetings, as well as to get check the latest information about the meetings of Archimedes NLP Theme and AUEB NLP Group, check http://nlp.cs.aueb.gr/news.html. To subscribe to the mailing list of AUEB NLP Group, send a message with subject "subscribe" to This email address is being protected from spambots. You need JavaScript enabled to view it.. If you have an AUEB account and want to receive announcements about AUEB NLP Group Meetings through MS Teams, subscribe to "AUEB NLP Group meetings" group on MS Teams (code: 01j65ny). Team members can also send text messages (chat) to other team members.

If you are an AI researcher or practitioner, please consider becoming a member of the Hellenic Artificial Intelligence Society (EETN, http://www.eetn.gr/en/).

Dial-in information:

One tap mobile

+302311180599,,92948800857#,,,,*101023# Greece

+302111984488,,92948800857#,,,,*101023# Greece

Dial by your location

• +30 231 118 0599 Greece

• +30 211 198 4488 Greece

Meeting ID: 929 4880 0857

Passcode: 101023

Find your local number: https://zoom.us/u/abqh0qsBIN