Aalto computer scientists in EMNLP 2024
Empirical Methods in Natural Language Processing (EMNLP) is one of the leading conferences in the area of natural language processing and artificial intelligence. This year 1271 papers were accepted for the main conference and 1029 papers as Findings of EMNLP.
The conference is organised on 12-16 November 2024 in Miami, Florida.
Accepted papers
Click the title to see the authors and the abstract. Link to the paper open on different website.
Authors
Sam Spilsbury, Pekka Marttinen, Aleksander Ilin
Abstract
In-Context-learning and few-shot prompting are viable methods compositional output generation. However, these methods can be very sensitive to the choice of support examples used. Retrieving good supports from the training data for a given test query is already a difficult problem, but in some cases solving this may not even be enough. We consider the setting of grounded language learning problems where finding relevant supports in the same or similar states as the query may be difficult. We design an agent which instead generates possible supports inputs and targets current state of the world, then uses them in-context-learning to solve the test query. We show substantially improved performance on a previously unsolved compositional generalization test without a loss of performance in other areas. The approach is general and can even scale to instructions expressed in natural language.
Department of Computer Science
We are an internationally-oriented community and home to world-class research in modern computer science.
School of Science
Science for tomorrow’s technology, innovations and businesses
- Published:
- Updated: