Papers with redundancy problem

3 papers
I already said that! Degenerating redundant questions in open-domain dialogue systems. (2023.acl-srw)

Copied to clipboard

Challenge: Neural text generation models have been successful in short open-domain conversations, but their performance degrades significantly in the long term.
Approach: They propose a method to generate training data without crowdsourcing . they adapt negative training, decoding, and classification methods to mitigate redundancy problem .
Outcome: The proposed method reduces the rate of redundant questions from 27.2% to 8.7% while improving the quality of the original model.
Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to answer long document questions ignore the global structure of the long document, which is essential for long-range understanding.
Approach: They propose a Compressive Graph Selector Network to capture the global structure of the long document in a compressive and iterative manner.
Outcome: The proposed model outperforms existing methods on two datasets.
3R: Enhancing Sentence Representation Learning via Redundant Representation Reduction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to improve sentence representations lack fine-grained guidance on reducing redundant information.
Approach: They propose a method that dynamically identifies redundant information from a dimensional perspective and trains the SRL model to redistribute semantics on different dimensions.
Outcome: The proposed method improves sentence representations on seven semantic text similarity benchmarks.

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