Practical and Specialised NLP Solutions: The Case of Social Media

Add to your list(s) Download to your calendar using vCal

• Jose Camacho Collados, Cardiff University
• Thursday 30 May 2024, 11:00-12:00
• Faculty of English, Room SR24.

If you have a question about this talk, please contact Panagiotis Fytas.

Large generative language models (LLMs) are currently ubiquitous in NLP research. However, when it comes to specific applications, these powerful models are often impractical and not always the optimal choice, and there may be more adequate solutions for specific problems.

In this talk, I will advocate for practical and effective solutions in NLP . I will try to revisit the importance of high-quality data (including labelled data) and reliable evaluation benchmarks in the current LLM landscape. Using social media as a case study, I will explain some of the challenges arising from processing content in these platforms. The multilingual, dynamic, informal and multimodal nature of social media, as well as the constant influx of new content, means that standard techniques are seldom optimal, and specialised models are often required.

This talk is part of the Language Technology Lab Seminars series.

This talk is included in these lists:

• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Faculty of English, Room SR24
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• Language Technology Lab Seminars
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.