A study of approaches to answering complex questions over knowledge bases

Gomes, Jorão; Mello, Rômulo Chrispim de; Ströele, Victor; Souza, Jairo

doi:10.1007/s10115-022-01737-x

Cited by 5 publications

(3 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 1, we can lock the next triple with the time constraint "2022" and the quantifier constraint "first part". These constraints modify the subject of a natural language question and, thus, change the final answer [12]. KGs, as a structured representation of relationships between entities and concepts in the real world, provide vital support for KGQA tasks [13].…”

Section: Introductionmentioning

confidence: 99%

“…It is worth noting that they highlighted the challenge of the semantic gap in this field, which remains a prominent research trend today. Jr et al [12] employed a systematic mapping methodology to provide an overview of C-KGQA. They offered a methodical mapping of the literature to identify the most popular venues, domains, and KGs utilized in the literature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advancements in Complex Knowledge Graph Question Answering: A Survey

Song,

Li,

Dai

et al. 2023

Electronics

View full text Add to dashboard Cite

Complex Question Answering over Knowledge Graph (C-KGQA) seeks to solve complex questions using knowledge graphs. Currently, KGQA systems achieve great success in answering simple questions, while complex questions still present challenging issues. As a result, an increasing number of novel methods have been proposed to remedy this challenge. In this survey, we proposed two mainstream categories of methods for C-KGQA, which are divided according to their use for knowledge graph representation and construction, namely, graph metric (GM)-Based Methods and graph neural network (GNN)-based methods. Additionally, we also acknowledge the influence of ChatGPT, which has prompted further research into utilizing knowledge graphs as a knowledge source to assist in answering complex questions. We also introduced methods based on pre-trained models and knowledge graph joint reasoning. Furthermore, we have compiled research achievements from the past three years to make it easier for researchers with similar interests to obtain state-of-the-art research. Finally, we discussed the resources and evaluation methods for tackling C-KGQA tasks and summarized several research prospects in this field.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Advancements in Complex Knowledge Graph Question Answering: A Survey

Song,

Li,

Dai

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…QA systems are now extensively utilized in search engines, conversational User Interface mobile, and virtual assistants. It is believed by most that QA systems have relatively good performance at giving answers to simple pieces of information [3]. With more complex questions presented to them, however, users should expect to get possible candidate answers [4] and then find the answer to the question on their end by browsing through the given list.…”

Section: Introductionmentioning

confidence: 99%

Question & answering system based on retrieval

Zhang

Jiang

et al. 2023

ACE

View full text Add to dashboard Cite

The principle of the question and answering system is nowadays one big branch of natural language processing. When a user enters a query, the system should find the question that is most similar to the entered question stored in the datasets. Then directly return the answer corresponding to the found question. Two models are implemented to better calculate the similarity between entered questions and questions in the corpus: TF-IDF and Word2Vec. After one hundred experiments to test the accuracy of these two models, the result shows that the Word2Vec has 81% accuracy and TF-IDF has only 49% accuracy. It is concluded that Word2Vec has a better accurate performance than TF-IDF. There is also an optimized storage method by using the inverted list for the corpus to improve the models efficiency.

show abstract

State-of-the-Art Approaches to Word Sense Disambiguation: A Multilingual Investigation

Habtamu,

Gizachew

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

A study of approaches to answering complex questions over knowledge bases

Cited by 5 publications

References 104 publications

Advancements in Complex Knowledge Graph Question Answering: A Survey

Advancements in Complex Knowledge Graph Question Answering: A Survey

Question & answering system based on retrieval

State-of-the-Art Approaches to Word Sense Disambiguation: A Multilingual Investigation

Contact Info

Product

Resources

About