2023
pdf
bib
abs
Meta-training with Demonstration Retrieval for Efficient Few-shot Learning
Aaron Mueller
|
Kanika Narang
|
Lambert Mathias
|
Qifan Wang
|
Hamed Firooz
Findings of the Association for Computational Linguistics: ACL 2023
Large language models show impressive results on few-shot NLP tasks. However, these models are memory and computation-intensive. Meta-training allows one to leverage smaller models for few-shot generalization in a domain-general and task-agnostic manner; however, these methods alone results in models that may not have sufficient parameterization or knowledge to adapt quickly to a large variety of tasks. To overcome this issue, we propose meta-training with demonstration retrieval, where we use a dense passage retriever to retrieve semantically similar labeled demonstrations to each example for more varied supervision. By separating external knowledge from model parameters, we can use meta-training to train parameter-efficient models that generalize well on a larger variety of tasks. We construct a meta-training set from UnifiedQA and CrossFit, and propose a demonstration bank based on UnifiedQA tasks. To our knowledge, our work is the first to combine retrieval with meta-training, to use DPR models to retrieve demonstrations, and to leverage demonstrations from many tasks simultaneously, rather than randomly sampling demonstrations from the training set of the target task. Our approach outperforms a variety of targeted parameter-efficient and retrieval-augmented few-shot methods on QA, NLI, and text classification tasks (including SQuAD, QNLI, and TREC). Our approach can be meta-trained and fine-tuned quickly on a single GPU.
2022
pdf
bib
Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
Kanika Narang
|
Aida Mostafazadeh Davani
|
Lambert Mathias
|
Bertie Vidgen
|
Zeerak Talat
Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
2020
pdf
bib
abs
Abusive Language Detection using Syntactic Dependency Graphs
Kanika Narang
|
Chris Brew
Proceedings of the Fourth Workshop on Online Abuse and Harms
Automated detection of abusive language online has become imperative. Current sequential models (LSTM) do not work well for long and complex sentences while bi-transformer models (BERT) are not computationally efficient for the task. We show that classifiers based on syntactic structure of the text, dependency graphical convolutional networks (DepGCNs) can achieve state-of-the-art performance on abusive language datasets. The overall performance is at par with of strong baselines such as fine-tuned BERT. Further, our GCN-based approach is much more efficient than BERT at inference time making it suitable for real-time detection.
2013
pdf
bib
An Empirical Assessment of Contemporary Online Media in Ad-Hoc Corpus Creation for Social Events
Kanika Narang
|
Seema Nagar
|
Sameep Mehta
|
L V Subramaniam
|
Kuntal Dey
Proceedings of the Sixth International Joint Conference on Natural Language Processing