Papers by Yuxiang Nie
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 . |