Papers by Hangbo Bao

5 papers
Attention Temperature Matters in Abstractive Summarization Distillation (2022.acl-long)

Copied to clipboard

Challenge: Recent progress of abstractive text summarization relies on large pre-trained sequence-to-sequence Transformer models, which are computationally expensive.
Approach: They propose to distill large Transformer summarization models into smaller ones with minimal performance loss by manipulating attention temperatures in Transformers.
Outcome: The proposed method outperforms vanilla pseudo-labeling based methods on three summarization datasets and is shorter and more abstractive.
Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension (D19-58)

Copied to clipboard

Challenge: Experimental results show that unified model outperforms other models that treat encoding and matching separately.
Approach: They evaluate a unified model with Transformer layers for machine reading comprehension . they find that the model learns different modeling strategies compared with previous models .
Outcome: The unified model outperforms models with Transformer layers on the machine reading comprehension task.
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (2022.findings-acl)

Copied to clipboard

Challenge: enabling pre-trained models inference on ciphertext data is difficult due to the complex computations in transformer blocks.
Approach: They propose an approximation approach for transformers which enables inference on ciphertext data.
Outcome: The proposed approach can infer pre-trained models on encrypted data with negligible performance drop but enjoy theory-guaranteed privacy-preserving advantage.
Learning to Sample Replacements for ELECTRA Pre-Training (2021.findings-acl)

Copied to clipboard

Challenge: Experimental results show that ELECTRA pretrains a discriminator to detect replaced tokens . despite compelling performance, there is no direct feedback loop from discriminator and generator to generator, making replacements biased to correct tokens.
Approach: They propose to augment sampling with a hardness prediction mechanism to encourage the discriminator to learn what it has not acquired.
Outcome: The proposed method improves ELECTRA pre-training on various downstream tasks.
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers (2021.findings-acl)

Copied to clipboard

Challenge: Existing work on deep self-attention distillation for natural language processing tasks is limited by computational resources and latency.
Approach: They generalize deep self-attention distillation in MINILM by using only self- attention relation distillation for taskagnostic compression of pretrained Transformers.
Outcome: The proposed model outperforms the state-of-the-art in a multilingual and multilingual teacher model.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations