118 citations · 282 across the 23 of their papers we have counts for
24 papers
Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering
Yike Wu, Nan Hu, Sheng Bi +4
Despite their competitive performance on knowledge-intensive tasks, large language models (LLMs) still have limitations in memorizing all world knowledge especially long tail knowl…
An Embedding-based Approach to Inconsistency-tolerant Reasoning with Inconsistent Ontologies
Keyu Wang, Site Li, Jiaye Li +2
Inconsistency handling is an important issue in knowledge management. Especially in ontology engineering, logical inconsistencies may occur during ontology construction. A natural…
An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering
Nan Hu, Yike Wu, Guilin Qi +4
Large-scale pre-trained language models (PLMs) such as BERT have recently achieved great success and become a milestone in natural language processing (NLP). It is now the consensu…
Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family
Yiming Tan, Dehai Min, Yu Li +4
ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge. Therefo…
Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams
Yongrui Chen, Xinnan Guo, Tongtong Wu +3
Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, exi…
Towards Relation Extraction From Speech
Tongtong Wu, Guitao Wang, Jinming Zhao +4
Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is…
Neural Topic Modeling with Deep Mutual Information Estimation
Kang Xu, Xiaoqiu Lu, Yuan-fang Li +5
The emerging neural topic models make topic modeling more easily adaptable and extendable in unsupervised text mining. However, the existing neural topic models is difficult to ret…
Conditional Generation Net for Medication Recommendation
Rui Wu, Zhaopeng Qiu, Jiacheng Jiang +2
Medication recommendation targets to provide a proper set of medicines according to patients' diagnoses, which is a critical task in clinics. Currently, the recommendation is manua…
Active Learning for Event Extraction with Memory-based Loss Prediction Model
Shirong Shen, Zhen Li, Guilin Qi
Event extraction (EE) plays an important role in many industrial application scenarios, and high-quality EE methods require a large amount of manual annotation data to train superv…
Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs
Yongrui Chen, Huiying Li, Guilin Qi +2
Query graph construction aims to construct the correct executable SPARQL on the KG to answer natural language questions. Although recent methods have achieved good results using ne…
Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model
Sheng Bi, Xiya Cheng, Yuan-Fang Li +5
The ability to generate natural-language questions with controlled complexity levels is highly desirable as it further expands the applicability of question generation. In this pap…
Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning
Yongrui Chen, Xinnan Guo, Chaojie Wang +4
Single-table text-to-SQL aims to transform a natural language question into a SQL query according to one single table. Recent work has made promising progress on this task by pre-t…
Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base
Yongrui Chen, Huiying Li, Yuncheng Hua +1
Formal query building is an important part of complex question answering over knowledge bases. It aims to build correct executable queries for questions. Recent methods try to rank…
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection
Shirong Shen, Tongtong Wu, Guilin Qi +3
Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have suffi…
Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain
Waheed Ahmed Abro, Annalena Aicher, Niklas Rach +3
This paper introduces a natural language understanding (NLU) framework for argumentative dialogue systems in the information-seeking and opinion building domain. The proposed frame…
Curriculum-Meta Learning for Order-Robust Continual Relation Extraction
Tongtong Wu, Xuekai Li, Yuan-Fang Li +4
Continual relation extraction is an important task that focuses on extracting new facts incrementally from unstructured text. Given the sequential arrival order of the relations, t…
Revealing Secrets in SPARQL Session Level
Xinyue Zhang, Meng Wang, Muhammad Saleem +3
Based on Semantic Web technologies, knowledge graphs help users to discover information of interest by using live SPARQL services. Answer-seekers often examine intermediate results…
Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
Yuncheng Hua, Yuan-Fang Li, Guilin Qi +3
Question answering is an effective method for obtaining information from knowledge bases (KB). In this paper, we propose the Neural-Symbolic Complex Question Answering (NS-CQA) mod…
Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning
Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari +2
Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach e…
Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases
Sheng Bi, Xiya Cheng, Yuan-Fang Li +2
Question generation over knowledge bases (KBQG) aims at generating natural-language questions about a subgraph, i.e. a set of (connected) triples. Two main challenges still face th…
Knowledge-aware Method for Confusing Charge Prediction
Xiya Cheng, Sheng Bi, Guilin Qi +1
Automatic charge prediction task aims to determine the final charges based on fact descriptions of criminal cases, which is a vital application of legal assistant systems. Conventi…
Overview of the CCKS 2019 Knowledge Graph Evaluation Track: Entity, Relation, Event and QA
Xianpei Han, Zhichun Wang, Jiangtao Zhang +22
Knowledge graph models world knowledge as concepts, entities, and the relationships between them, which has been widely used in many real-world tasks. CCKS 2019 held an evaluation…
A Distance-based Paraconsistent Semantics for DL-Lite
Xiaowang Zhang, Kewen Wang, Zhe Wang +2
DL-Lite is an important family of description logics. Recently, there is an increasing interest in handling inconsistency in DL-Lite as the constraint imposed by a TBox can be easi…
A Revision-Based Approach to Resolving Conflicting Information
Guilin Qi, Weiru Liu, David A. Bell
In this paper, we propose a revision-based approach for conflict resolution by generalizing the Disjunctive Maxi-Adjustment (DMA) approach (Benferhat et al. 2004). Revision operato…