Yifan Chen


2022

pdf
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Yifan Chen | Qi Zeng | Dilek Hakkani-Tur | Di Jin | Heng Ji | Yun Yang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules. To address this limitation, Linformer and Informer reduce the quadratic complexity to linear (modulo logarithmic factors) via low-dimensional projection and row selection, respectively. These two models are intrinsically connected, and to understand their connection we introduce a theoretical framework of matrix sketching. Based on the theoretical analysis, we propose Skeinformer to accelerate self-attention and further improve the accuracy of matrix approximation to self-attention with column sampling, adaptive row normalization and pilot sampling reutilization. Experiments on the Long Range Arena benchmark demonstrate that our methods outperform alternatives with a consistently smaller time/space footprint.

pdf
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Yifan Chen | Devamanyu Hazarika | Mahdi Namazifar | Yang Liu | Di Jin | Dilek Hakkani-Tur
Findings of the Association for Computational Linguistics: NAACL 2022

The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-efficient transfer learning methods have been proposed to tune only a few parameters during fine-tuning while freezing the rest. This paper looks at existing methods along this line through the kernel lens. Motivated by the connection between self-attention in transformer-based PLMs and kernel learning, we propose kernel-wise adapters, namely Kernel-mix, that utilize the kernel structure in self-attention to guide the assignment of the tunable parameters. These adapters use guidelines found in classical kernel learning and enable separate parameter tuning for each attention head. Our empirical results, over a diverse set of natural language generation and understanding tasks, show that our proposed adapters can attain or improve the strong performance of existing baselines.

pdf
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
Yifan Chen | Devamanyu Hazarika | Mahdi Namazifar | Yang Liu | Di Jin | Dilek Hakkani-Tur
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM), prefix-tuning can obtain strong performance by training only a small portion of parameters. In this paper, we propose to understand and further develop prefix-tuning through the kernel lens. Specifically, we make an analogy between prefixes and inducing variables in kernel methods and hypothesize that prefixes serving as inducing variables would improve their overall mechanism. From the kernel estimator perspective, we suggest a new variant of prefix-tuning—inducer-tuning, which shares the exact mechanism as prefix-tuning while leveraging the residual form found in adapter-tuning. This mitigates the initialization issue in prefix-tuning. Through comprehensive empirical experiments on natural language understanding and generation tasks, we demonstrate that inducer-tuning can close the performance gap between prefix-tuning and fine-tuning.

2020

pdf
A Corpus of Very Short Scientific Summaries
Yifan Chen | Tamara Polajnar | Colin Batchelor | Simone Teufel
Proceedings of the 24th Conference on Computational Natural Language Learning

We present a new summarisation task, taking scientific articles and producing journal table-of-contents entries in the chemistry domain. These are one- or two-sentence author-written summaries that present the key findings of a paper. This is a first look at this summarisation task with an open access publication corpus consisting of titles and abstracts, as input texts, and short author-written advertising blurbs, as the ground truth. We introduce the dataset and evaluate it with state-of-the-art summarisation methods.