Knowledge Base Question Answering: A Semantic Parsing Perspective

Recent advances in deep learning have greatly propelled the research on semantic parsing. Improvement has since been made in many downstream tasks, including natural language interface to web APIs, text-to-SQL generation, among others. However, despite the close connection shared with these tasks, research on question answering over knowledge bases (KBQA) has comparatively been progressing slowly. We identify and attribute this to two unique challenges of KBQA, schema-level complexity and fact-level complexity. In this survey, we situate KBQA in the broader literature of semantic parsing and give a comprehensive account of how existing KBQA approaches attempt to address the unique challenges. Regardless of the unique challenges, we argue that we can still take much inspiration from the literature of semantic parsing, which has been overlooked by existing research on KBQA. Based on our discussion, we can better understand the bottleneck of current KBQA research and shed light on promising directions for KBQA to keep up with the literature of semantic parsing, particularly in the era of pre-trained language models.

[1]  Haoming Jiang,et al.  SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models , 2022, NAACL-HLT.

[2]  Jivat Neet Kaur,et al.  Modern Baselines for SPARQL Semantic Parsing , 2022, SIGIR.

[3]  Yu Gu,et al.  ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering , 2022, COLING.

[4]  Andreas Both,et al.  Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisis , 2022, LREC.

[5]  Dragomir R. Radev,et al.  UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models , 2022, EMNLP.

[6]  Achille Fokoue,et al.  A Two-Stage Approach towards Generalization in Knowledge Base Question Answering , 2021, EMNLP.

[7]  Harm de Vries,et al.  The Power of Prompt Tuning for Low-Resource Semantic Parsing , 2021, ACL.

[8]  Michael White,et al.  Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction , 2021, FINDINGS.

[9]  Kazuma Hashimoto,et al.  RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering , 2021, Annual Meeting of the Association for Computational Linguistics.

[10]  Wayne Xin Zhao,et al.  Complex Knowledge Base Question Answering: A Survey , 2021, IEEE Transactions on Knowledge and Data Engineering.

[11]  Qian Liu,et al.  TAPEX: Table Pre-training via Learning a Neural SQL Executor , 2021, ICLR.

[12]  Liangming Pan,et al.  KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base , 2020, ACL.

[13]  Hongxia Jin,et al.  A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning , 2022, NAACL.

[14]  Ramón Fernández Astudillo,et al.  Learning to Transpile AMR into SPARQL , 2021, ArXiv.

[15]  Dzmitry Bahdanau,et al.  PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models , 2021, EMNLP.

[16]  Chin-Yew Lin,et al.  ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering , 2021, ACL.

[17]  Matthew Richardson,et al.  KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers , 2021, ACL.

[18]  Ji-Rong Wen,et al.  A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions , 2021, IJCAI.

[19]  Rajarshi Das,et al.  Case-based Reasoning for Natural Language Queries over Knowledge Bases , 2021, EMNLP.

[20]  Brian Lester,et al.  The Power of Scale for Parameter-Efficient Prompt Tuning , 2021, EMNLP.

[21]  Alexander G. Gray,et al.  Leveraging Abstract Meaning Representation for Knowledge Base Question Answering , 2020, FINDINGS.

[22]  Brian M. Sadler,et al.  Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases , 2020, WWW.

[23]  Ahmed Hassan Awadallah,et al.  Structure-Grounded Pretraining for Text-to-SQL , 2020, NAACL.

[24]  Jonathan Berant,et al.  SmBoP: Semi-autoregressive Bottom-up Semantic Parsing , 2020, SPNLP.

[25]  Dragomir R. Radev,et al.  GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing , 2020, ICLR.

[26]  Sebastian Rudolph,et al.  Neural Machine Translating from Natural Language to SPARQL , 2019, Future Gener. Comput. Syst..

[27]  Juan-Zi Li,et al.  Program Transfer and Ontology Awareness for Semantic Parsing in KBQA , 2021, ArXiv.

[28]  Yuzhong Qu,et al.  EDG-Based Question Decomposition for Complex Question Answering over Knowledge Bases , 2021, SEMWEB.

[29]  Jure Leskovec,et al.  LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs , 2021, ICML.

[30]  Asja Fischer,et al.  Introduction to neural network‐based question answering over knowledge graphs , 2021, WIREs Data Mining Knowl. Discov..

[31]  Kun Zhang,et al.  Hierarchical Query Graph Generation for Complex Question Answering over Knowledge Graph , 2020, CIKM.

[32]  Jian Sun,et al.  A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges , 2020, ArXiv.

[33]  Hanwang Zhang,et al.  KQA Pro: A Large Diagnostic Dataset for Complex Question Answering over Knowledge Base , 2020, ArXiv.

[34]  Yunshi Lan,et al.  Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases , 2020, ACL.

[35]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[36]  Hongxia Jin,et al.  A Complex KBQA System using Multiple Reasoning Paths , 2020, ArXiv.

[37]  Edgard Marx,et al.  Where is Linked Data in Question Answering over Linked Data? , 2020, ArXiv.

[38]  Thomas Muller,et al.  TaPas: Weakly Supervised Table Parsing via Pre-training , 2020, ACL.

[39]  Lingling Zhang,et al.  SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases , 2020, AAAI.

[40]  Xiaodong Liu,et al.  RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers , 2019, ACL.

[41]  Omer Levy,et al.  BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension , 2019, ACL.

[42]  Colin Raffel,et al.  Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..

[43]  H. V. Jagadish,et al.  Learning to Answer Complex Questions over Knowledge Bases with Query Composition , 2019, CIKM.

[44]  Shuohang Wang,et al.  Multi-hop Knowledge Base Question Answering with an Iterative Sequence Matching Model , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[45]  Jens Lehmann,et al.  LC-QuAD 2.0: A Large Dataset for Complex Question Answering over Wikidata and DBpedia , 2019, SEMWEB.

[46]  Wen-tau Yih,et al.  Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study , 2019, EMNLP.

[47]  Yuzhong Qu,et al.  Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering , 2019, EMNLP.

[48]  Shuohang Wang,et al.  Knowledge Base Question Answering with Topic Units , 2019, IJCAI.

[49]  Soumen Chakrabarti,et al.  Neural Program Induction for KBQA Without Gold Programs or Query Annotations , 2019, IJCAI.

[50]  Haoyu Zhang,et al.  Complex Question Decomposition for Semantic Parsing , 2019, ACL.

[51]  Lun-Wei Ku,et al.  UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering , 2019, NAACL.

[52]  Seunghyun Park,et al.  A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization , 2019, ArXiv.

[53]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[54]  Tao Yu,et al.  Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task , 2018, EMNLP.

[55]  Xifeng Yan,et al.  DialSQL: Dialogue Based Structured Query Generation , 2018, ACL.

[56]  Jens Lehmann,et al.  Formal Query Generation for Question Answering over Knowledge Bases , 2018, ESWC.

[57]  Mirella Lapata,et al.  Coarse-to-Fine Decoding for Neural Semantic Parsing , 2018, ACL.

[58]  Jonathan Berant,et al.  The Web as a Knowledge-Base for Answering Complex Questions , 2018, NAACL.

[59]  Mitesh M. Khapra,et al.  Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph , 2018, AAAI.

[60]  Muhammad Saleem,et al.  9th Challenge on Question Answering over Linked Data (QALD-9) (invited paper) , 2018, Semdeep/NLIWoD@ISWC.

[61]  Lei Zou,et al.  A State-transition Framework to Answer Complex Questions over Knowledge Base , 2018, EMNLP.

[62]  Vanessa López,et al.  Core techniques of question answering systems over knowledge bases: a survey , 2017, Knowledge and Information Systems.

[63]  Michael Gamon,et al.  Building Natural Language Interfaces to Web APIs , 2017, CIKM.

[64]  Jens Lehmann,et al.  LC-QuAD: A Corpus for Complex Question Answering over Knowledge Graphs , 2017, SEMWEB.

[65]  Jayant Krishnamurthy,et al.  Neural Semantic Parsing with Type Constraints for Semi-Structured Tables , 2017, EMNLP.

[66]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[67]  Gerhard Weikum,et al.  Automated Template Generation for Question Answering over Knowledge Graphs , 2017, WWW.

[68]  Chen Liang,et al.  Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision , 2016, ACL.

[69]  Brian M. Sadler,et al.  On Generating Characteristic-rich Question Sets for QA Evaluation , 2016, EMNLP.

[70]  Ming-Wei Chang,et al.  The Value of Semantic Parse Labeling for Knowledge Base Question Answering , 2016, ACL.

[71]  Percy Liang,et al.  Data Recombination for Neural Semantic Parsing , 2016, ACL.

[72]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[73]  Hannah Bast,et al.  More Accurate Question Answering on Freebase , 2015, CIKM.

[74]  Ming-Wei Chang,et al.  Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base , 2015, ACL.

[75]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

[76]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[77]  Markus Krötzsch,et al.  Wikidata , 2014, Commun. ACM.

[78]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[79]  Jonathan Berant,et al.  Semantic Parsing via Paraphrasing , 2014, ACL.

[80]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[81]  Alexander Yates,et al.  Large-scale Semantic Parsing via Schema Matching and Lexicon Extension , 2013, ACL.

[82]  Alexander Yates,et al.  Semantic Parsing Freebase: Towards Open-domain Semantic Parsing , 2013, *SEMEVAL.

[83]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[84]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.