Papers by Menghan Zhang

4 papers
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model (2023.findings-acl)

Copied to clipboard

Challenge: Pretrained language models have achieved remarkable success in various natural language processing tasks.
Approach: They propose to use end-task knowledge to select a tiny subset of pretraining corpus to influence performance.
Outcome: The proposed model outperforms pretrained models on eight datasets covering four domains with 0.45% of the data and a three-orders-of-magnitude lower computational cost.
Detecting Adversarial Samples through Sharpness of Loss Landscape (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies have shown that adversarial samples are more vulnerable than normal ones to textual adversarials.
Approach: They propose a simple and effective sharpness-based detector that can distinguish adversarial samples by maximizing the loss increment within the region where the inference sample is located.
Outcome: The proposed method outperforms previous detection methods by large margins on three text classification tasks.
Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have implicitly transfer knowledge across languages, but not all languages have such generalization capabilities.
Approach: They propose a meta-learning-based method to learn to align conceptual spaces of different languages to enhance cross-lingual generalization.
Outcome: The proposed method achieves competitive results with state-of-the-art methods and narrows the performance gap between languages.
Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer? (2022.emnlp-main)

Copied to clipboard

Challenge: Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, but it is not well understood what leads to this variation and whether it fairly reflects difference between languages.
Approach: They propose to use multilingual BERT to enable zero-shot cross-lingual transfer of syntactic knowledge between different languages by generating grammatical relations in 24 different languages.
Outcome: The results show that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.

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