A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions

Lan, Yunshi; He, Gaole; Jiang, Jinhao; Jiang, Jing; Zhao, Wayne Xin; Wen, Ji-Rong

doi:10.24963/ijcai.2021/611

Cited by 94 publications

(43 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the following, we describe some salient milestone KGQA datasets and their manner of construction. Previous work [7,15,19,31] has surveyed the field of KGQA, which we draw on in our present summary. The KGQA datasets are grounded in one or more of the three most common open-domain knowledge graphs (KGs): Freebase, DBpedia, and Wikidata.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering

Linjordet,

Balog

2022

Preprint

View full text Add to dashboard Cite

Knowledge graph question answering (KGQA) facilitates information access by leveraging structured data without requiring formal query language expertise from the user. Instead, users can express their information needs by simply asking their questions in natural language (NL). Datasets used to train KGQA models that would provide such a service are expensive to construct, both in terms of expert and crowdsourced labor. Typically, crowdsourced labor is used to improve template-based pseudo-natural questions generated from formal queries. However, the resulting datasets often fall short of representing genuinely natural and fluent language. In the present work, we investigate ways to characterize and remedy these shortcomings. We create the IQN-KGQA test collection by sampling questions from existing KGQA datasets and evaluating them with regards to five different aspects of naturalness. Then, the questions are rewritten to improve their fluency. Finally, the performance of existing KGQA models is compared on the original and rewritten versions of the NL questions. We find that some KGQA systems fare worse when presented with more realistic formulations of NL questions. The IQN-KGQA test collection is a resource to help evaluate KGQA systems in a more realistic setting. The construction of this test collection also sheds light on the challenges of constructing large-scale KGQA datasets with genuinely NL questions.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Training machine learning models for KGQA requires large-scale datasets specific to the KGQA task. Most commonly, such datasets consist of instances that each comprises a formal query (also known as logic form) and a corresponding NL question [15].…”

Section: Introductionmentioning

confidence: 99%

Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering

Linjordet,

Balog

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In future work, we will study how to effectively leverage the commonsense knowledge from large-scale unstructured data to improve PTMs. We will also try to apply our approach to other knowledge-intensive tasks, e.g., knowledge graph completion and knowledge graph based question answering (Lan et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models

Jiang¹,

Zhou²,

Wen³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

Self Cite

View full text Add to dashboard Cite

Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models (PTMs) with a knowledge-aware graph neural network (GNN) encoder that models a commonsense knowledge graph (CSKG). Despite the effectiveness, these approaches are built on heavy architectures, and can't clearly explain how external knowledge resources improve the reasoning capacity of PTMs. Considering this issue, we conduct a deep empirical analysis, and find that it is indeed relation features from CSKGs (but not node features) that mainly contribute to the performance improvement of PTMs. Based on this finding, we design a simple MLP-based knowledge encoder that utilizes statistical relation paths as features. Extensive experiments conducted on five benchmarks demonstrate the effectiveness of our approach, which also largely reduces the parameters for encoding CSKGs. Our codes and data are publicly available at https://github.com/RUCAIBox/SAFE.

show abstract

“…single-hop QA [2,12,33,60,103,132], open-domain QA [184], medical QA [68,88] etc. The surveys that are most relevant to MHQA are the ones focused on QA over knowledge bases [32,43,82] and visual QA [88,135,164]. However, these can be considered as sub-domains of the more general formulation of MHQA field that this manuscript aims to survey.…”

Section: ♂ Available Context -B's Father Is C and Her Mother Is Amentioning

confidence: 99%

A Survey on Multi-hop Question Answering and Generation

Mavi¹,

Jangra²,

Jatowt³

2022

Preprint

View full text Add to dashboard Cite

The problem of Question Answering (QA) has attracted significant research interest for long. Its relevance to language understanding and knowledge retrieval tasks, along with the simple setting makes the task of QA crucial for strong AI systems. Recent success on simple QA tasks has shifted the focus to more complex settings. Among these, Multi-Hop QA (MHQA) is one of the most researched tasks over the recent years.The ability to answer multi-hop questions and perform multi step reasoning can significantly improve the utility of NLP systems. Consequently, the field has seen a sudden surge with high quality datasets, models and evaluation strategies. The notion of 'multiple hops' is somewhat abstract which results in a large variety of tasks that require multi-hop reasoning. This implies that different datasets and models differ significantly which makes the field challenging to generalize and survey. This work aims to provide a general and formal definition of MHQA task, and organize and summarize existing MHQA frameworks. We also outline the best methods to create MHQA datasets. The paper provides a systematic and thorough introduction as well as the structuring of the existing attempts to this highly interesting, yet quite challenging task.

show abstract

A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions

Cited by 94 publications

References 7 publications

Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering

Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering

Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models

A Survey on Multi-hop Question Answering and Generation

Contact Info

Product

Resources

About