Department of Computational and Data Sciences
SPEAKER : Priyanka Agrawal (Google Deepmind)
TITLE : “QAmeleon: Multilingual QA with Only 5 Examples“
Date & Time : August 24, 2023, 12:30 PM
Venue : # 102, CDS Seminar Hall
The availability of large, high-quality datasets has been one of the main drivers of recent progress in question answering (QA). Such annotated datasets however are difficult and costly to collect, and rarely exist in languages other than English, rendering QA technology inaccessible to underrepresented languages. An alternative to building large monolingual training datasets is to leverage pre-trained language models (PLMs) under a few-shot learning setting. Our approach, QAmeleon, uses a PLM to automatically generate multilingual data upon which QA models are trained, thus avoiding costly annotation. Prompt tuning the PLM for data synthesis with only five examples per language delivers accuracy superior to translation-based baselines, bridges nearly 60% of the gap between an English-only baseline and a fully supervised upper bound trained on almost 50,000 hand labeled examples, and always leads to substantial improvements compared to fine-tuning a QA model directly on labeled examples in low resource settings. Experiments on the TyDiQA-GoldP and MLQA benchmarks show that few-shot prompt tuning for data synthesis scales across languages and is a viable alternative to large-scale annotation.
Priyanka Agrawal is a Research Scientist at the Google Deepmind in London, formally part of Google Brain, and is focused on building responsible Generative AI models and scaling them to underrepresented languages. Prior to that she was a Senior Researcher and Lead at Booking.com and IBM Research Labs, where she was driving work in cross-domain transfer and representation learning. She is also an alumni from IISc from the CSA department. Her work is published at top tier ML and NLP conferences like NeurIPS, ACL and she holds 25+ US Patents. Priyanka also serves as Area Chair and PC member at these conferences and has been an invited panelist and speaker at various ML/NLP and diversity forums.
Host Faculty: Dr. Danish Pruthi
ALL ARE WELCOME