Papers by Yiran Zhong

6 papers
CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation methods for text summarization systems are limited to in-domain setting, where supervised pre-trained models are evaluated on the same dataset.
Approach: They propose to use a cross-dataset evaluation approach to evaluate different summarization systems in a multi-domain setting.
Outcome: The proposed model can be used to evaluate text summarization systems on different datasets.
The Devil in Linear Transformer (2022.emnlp-main)

Copied to clipboard

Challenge: Existing linear transformers suffer from performance degradations on various tasks and corpus.
Approach: They propose a new linear attention that replaces scaling with a normalization to stabilize gradients and confine attention to neighbouring tokens in early layers.
Outcome: The proposed model outperforms vanilla transformers on the long-range arena benchmark while being significantly more space-time efficient.
Extractive Summarization as Text Matching (2020.acl-main)

Copied to clipboard

Challenge: Currently, most of the neural extractive summarization systems score and extract sentences individually and model the relationship between sentences.
Approach: They propose to instantiate a neural extractive summarization task as a semantic text matching problem and use it to match a source document and candidate summaries in a semantic space.
Outcome: The proposed framework is faster and more efficient than existing frameworks.
Accelerating Toeplitz Neural Network with Constant-time Inference Complexity (2023.emnlp-main)

Copied to clipboard

Challenge: Toeplitz Neural Networks outperform commonly used Transformer-based models while benefiting from log-linear space-time complexities.
Approach: They propose to convert TNNs to SSMs during inference to combine strengths of TNN and SSM approaches.
Outcome: The proposed method outperforms most Transformer-based models while retaining the advantage of constant inference complexity.
Scaling Laws for Linear Complexity Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing scaling laws for large language models are unclear, but they are useful for scalability.
Approach: They propose scaling laws for linear complexity language models to establish a foundation for their scalability.
Outcome: The proposed models demonstrate superior linguistic proficiency and knowledge retention.
ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models (2023.acl-short)

Copied to clipboard

Challenge: Knowledge distillation (KD) is an effective compression technique to derive a smaller student model from a larger teacher model by transferring the knowledge embedded in the teacher's network.
Approach: They propose a framework and loss function that preserves the semantic similarities of teacher and student training examples to enable the student to retrieve from the knowledge base effectively.
Outcome: The proposed framework preserves the semantic similarities of teacher and student training examples to achieve state-of-the-art performance on the GLUE benchmark.

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