Papers by Yuxiang Nie

6 papers
AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for annotating long-document question answering are based on short documents and can hardly incorporate long-range information.
Approach: They propose an unsupervised method to generate long-document question answering pairs . they propose a method to aggregate and generate answers with long-range dependency .
Outcome: The proposed method outperforms existing methods on NarrativeQA and Qasper.
SciMRC: Multi-perspective Scientific Machine Reading Comprehension (2024.lrec-main)

Copied to clipboard

Challenge: Existing datasets focused on single-perspective question-answer pairs overlooking inherent variation in comprehension levels among different readers.
Approach: They propose a multi-perspective scientific machine reading comprehension dataset . their dataset comprises 741 scientific papers and 6,057 question-answer pairs .
Outcome: The proposed dataset includes questions from beginners, students, and experts.
Reinforced Target-driven Conversational Promotion (2023.emnlp-main)

Copied to clipboard

Challenge: Existing conversational recommendation methods focus on acquiring user preferences while ignoring strategic planning for nudging users towards accepting a designated item.
Approach: They propose a Reinforced Target-driven Conversational Promotion framework that integrates short-term and long-term planning via a balanced gating mechanism.
Outcome: The proposed model outperforms state-of-the-art models on automatic metrics and human evaluation.
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.
Mix-Initiative Response Generation with Dynamic Prefix Tuning (2024.naacl-long)

Copied to clipboard

Challenge: Existing dialogue systems focus on training a holistic response generation model without any distinction between different initiatives.
Approach: They propose a general mix-Initiative Dynamic Prefix Tuning framework to decouple different initiatives from the generation model.
Outcome: The proposed framework outperforms baselines on two public dialogue datasets on human evaluations and automatic metrics.
Unsupervised Question Answering via Answer Diversifying (2022.coling-1)

Copied to clipboard

Challenge: Existing extractive question answering methods use labeled data to train QA models.
Approach: They propose an unsupervised method by diversifying answers by using data construction, data augmentation and denoising filter.
Outcome: The proposed method outperforms previous models on five benchmark datasets . it shows strong performance in the few-shot learning setting .

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