Enhancing dual-encoders with question and answer cross-embeddings for answer retrieval

[PDF] arxiv.org

A Comprehensive Survey on Retrieval Methods in Recommender Systems

J Huang, J Chen, J Lin, J Qin, Z Feng, W Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
In an era dominated by information overload, effective recommender systems are essential
for managing the deluge of data across digital platforms. Multi-stage cascade ranking …
被引用次数：3 相关文章 所有 2 个版本

Multi-Source Soft Labeling and Hard Negative Sampling for Retrieval Distractor Ranking

J Wang, W Rong, J Bai, Z Sun… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Multiple-choice questions (MCQs) are a kind of widely adopted approaches in learning
assessment. Recently, the automatic generation of MCQs has become a popular research …
被引用次数：3 相关文章 所有 2 个版本

Improving biomedical ReQA with consistent NLI-transfer and post-whitening

J Bai, C Yin, Z Wu, J Zhang, Y Wang… - IEEE/ACM …, 2022 - ieeexplore.ieee.org
Retrieval Question Answering (ReQA) is an essential mechanism of information sharing
which aims to find the answer to a posed question from large-scale candidates. Currently …
被引用次数：8 相关文章 所有 5 个版本

Enhancing Biomedical ReQA With Adversarial Hard In-Batch Negative Samples

B Zhao, J Bai, C Li, J Zhang, W Rong… - IEEE/ACM …, 2023 - ieeexplore.ieee.org
Question answering (QA) plays a vital role in biomedical natural language processing.
Among question answering tasks, the retrieval question answering (ReQA) aims to directly …
被引用次数：1 相关文章 所有 5 个版本
[PDF] arxiv.org

Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking

J Bai, Z Chen, Z Li, H Hong, J Zhang, C Li, C Lin… - arXiv preprint arXiv …, 2024 - arxiv.org
Text ranking has witnessed significant advancements, attributed to the utilization of dual-
encoder enhanced by Pre-trained Language Models (PLMs). Given the proliferation of …
相关文章 所有 2 个版本
[PDF] arxiv.org

Inference-time Re-ranker Relevance Feedback for Neural Information Retrieval

RG Reddy, P Dasigi, MA Sultan, A Cohan, A Sil… - arXiv preprint arXiv …, 2023 - arxiv.org
Neural information retrieval often adopts a retrieve-and-rerank framework: a bi-encoder
network first retrieves K (eg, 100) candidates that are then re-ranked using a more powerful …
相关文章

Graph and Question Interaction Aware Graph2Seq Model for Knowledge Base Question Generation

C Li, J Bai, C Wang, Y Hu, W Rong… - 2022 International Joint …, 2022 - ieeexplore.ieee.org
The Knowledge Base Question Generation (KBQG) is an essential natural language
processing task. Taking knowledge graph and answer entities as input, KBQG aims to …
相关文章

KnowReQA: A Knowledge-aware Retrieval Question Answering System

C Wang, J Bai, X Zhang, C Yan, Y Ouyang… - … on Knowledge Science …, 2022 - Springer
Retrieval question answering (ReQA) is an essential mechanism to automatically satisfy the
users' information needs and overcome the problem of information overload. As a promising …
相关文章 所有 2 个版本

Interdisciplinarity Inference Using a Cross Encoder between Research Projects

T Kanazawa, H Nakawatase… - 2022 Joint 12th …, 2022 - ieeexplore.ieee.org
We propose an inference method that infers the feasibility of interdisciplinary research by
integrating two existing research projects from the brief descriptions of those two projects …
相关文章