62 citations · 176 across the 26 of their papers we have counts for
6 papers · 2 filters
Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA
Junjie Huang, Wanjun Zhong, Qian Liu +3
Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training a…
Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers
Wanjun Zhong, Tingting Ma, Jiahai Wang +4
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual…
Improving Task Generalization via Unified Schema Prompt
Wanjun Zhong, Yifan Gao, Ning Ding +5
Task generalization has been a long standing challenge in Natural Language Processing (NLP). Recent research attempts to improve the task generalization ability of pre-trained lang…
LogiGAN: Learning Logical Reasoning via Adversarial Pre-training
Xinyu Pi, Wanjun Zhong, Yan Gao +2
We present LogiGAN, an unsupervised adversarial pre-training framework for improving logical reasoning abilities of language models. Upon automatic identifying logical reasoning ph…
ProQA: Structural Prompt-based Pre-training for Unified Question Answering
Wanjun Zhong, Yifan Gao, Ning Ding +6
Question Answering (QA) is a longstanding challenge in natural language processing. Existing QA works mostly focus on specific question types, knowledge domains, or reasoning skill…
Reasoning over Hybrid Chain for Table-and-Text Open Domain QA
Wanjun Zhong, Junjie Huang, Qian Liu +4
Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text.…