Knowledge Graph Question Answering via SPARQL Silhouette Generation
Not on the map. Why?
Abstract (arXiv)
Knowledge Graph Question Answering (KGQA) has become a prominent area in natural language processing due to the emergence of large-scale Knowledge Graphs (KGs). Recently Neural Machine Translation based approaches are gaining momentum that translates natural language queries to structured query languages thereby solving the KGQA task. However, most of these methods struggle with out-of-vocabulary words where test entities and relations are not seen during training time. In this work, we propose a modular two-stage neural architecture to solve the KGQA task. The first stage generates a sketch of the target SPARQL called SPARQL silhouette for the input question. This comprises of (1) Noise simulator to facilitate out-of-vocabulary words and to reduce vocabulary size (2) seq2seq model for text to SPARQL silhouette generation. The second stage is a Neural Graph Search Module. SPARQL silhouette generated in the first stage is distilled in the second stage by substituting precise relation in the predicted structure. We simulate ideal and realistic scenarios by designing a noise simulator. Experimental results show that the quality of generated SPARQL silhouette in the first stage is outstanding for the ideal scenarios but for realistic scenarios (i.e. noisy linker), the quality of the resulting SPARQL silhouette drops drastically. However, our neural graph search module recovers it considerably. We show that our method can achieve reasonable performance improving the state-of-art by a margin of 3.72% F1 for the LC-QuAD-1 dataset. We believe, our proposed approach is novel and will lead to dynamic KGQA solutions that are suited for practical applications.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 59 references that are in the map. First posted on arXiv 6 Sep 2021.
Builds on
30 of 59 references.
References · 30
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2016Language Modeling with Gated Convolutional Networkscited by 688
- 2017Convolutional Sequence to Sequence Learningcited by 550
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
- 2015Large-scale Simple Question Answering with Memory Networkscited by 127
- 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 101
18 more
- 2019Scalable Zero-shot Entity Linking with Dense Entity Retrievalcited by 85
- 2018TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generationcited by 81
- 2020Efficient One-Pass End-to-End Entity Linking for Questionscited by 76
- 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
- 2017Improved Neural Relation Detection for Knowledge Base Question Answeringcited by 44
- 2016Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answeringcited by 35
- 2013Lambda Dependency-Based Compositional Semanticscited by 26
- 2019Message Passing for Complex Question Answering over Knowledge Graphscited by 24
- 2017An Encoder-Decoder Framework Translating Natural Language to Database Queriescited by 23
- 2019Neural Machine Translating from Natural Language to SPARQLcited by 23
- 2018SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approachcited by 18
- 2018Learning to Rank Query Graphs for Complex Question Answering over Knowledge Graphscited by 17
- 2018Towards a Question Answering System over the Semantic Webcited by 14
- 2016CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Basescited by 12
- 2016Simple Question Answering by Attentive Convolutional Neural Networkcited by 12
- 2020Pretrained Transformers for Simple Question Answering over Knowledge Graphscited by 12
- 2016Character-Level Question Answering with Attentioncited by 9
- 2018Weakly-supervised Neural Semantic Parsing with a Generative Rankercited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.