activity
20162025
most citedAnswering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

5 citations · 13 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CL20225 cited

Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

Fangyu Lei, Shizhu He, Xiang Li +2

In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning probl…

cs.CL2022

ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains

Minjun Zhu, Yixuan Weng, Shizhu He +2

The ability of reasoning over evidence has received increasing attention in question answering (QA). Recently, natural language database (NLDB) conducts complex QA in knowledge bas…

cs.CL20213 cited

Lifelong Intent Detection via Multi-Strategy Rebalancing

Qingbin Liu, Xiaoyan Yu, Shizhu He +2

Conventional Intent Detection (ID) models are usually trained offline, which relies on a fixed dataset and a predefined set of intent classes. However, in real-world applications,…

cs.AI20212 cited

Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion

Yinyu Lan, Shizhu He, Xiangrong Zeng +3

Background Knowledge graphs (KGs), especially medical knowledge graphs, are often significantly incomplete, so it necessitating a demand for medical knowledge graph completion (Med…

cs.CL2020

Pre-trained Language Model Based Active Learning for Sentence Matching

Guirong Bai, Shizhu He, Kang Liu +2

Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly…

cs.CL2019

Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss

Cao Liu, Kang Liu, Shizhu He +2

We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed…