mlsanityData to 7 Oct 2026

Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base

arXiv 2207.03680 ↗First posted 8 Jul 2022cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Semantic parsing solves knowledge base (KB) question answering (KBQA) by composing a KB query, which generally involves node extraction (NE) and graph composition (GC) to detect and connect related nodes in a query. Despite the strong causal effects between NE and GC, previous works fail to directly model such causalities in their pipeline, hindering the learning of subtask correlations. Also, the sequence-generation process for GC in previous works induces ambiguity and exposure bias, which further harms accuracy. In this work, we formalize semantic parsing into two stages. In the first stage (graph structure generation), we propose a causal-enhanced table-filler to overcome the issues in sequence-modelling and to learn the internal causalities. In the second stage (relation extraction), an efficient beam-search algorithm is presented to scale complex queries on large-scale KBs. Experiments on LC-QuAD 1.0 indicate that our method surpasses previous state-of-the-arts by a large margin (17%) while remaining time and space efficiency. The code and models are available at https://github.com/AOZMH/Crake.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 15 of its 38 references that are in the map. First posted on arXiv 8 Jul 2022.

Builds on

15 of 38 references.

References · 15

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2015VQA: Visual Question Answeringcited by 2,489
  3. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  4. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  5. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  6. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  7. 2020Leveraging Abstract Meaning Representation for Knowledge Base Question Answeringcited by 53
  8. 2019KBQA: Learning Question Answering over QA Corpora and Knowledge Basescited by 44
  9. 2021UniRE: A Unified Label Space for Entity Relation Extractioncited by 38
  10. 2019Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Basecited by 33
  11. 2019Message Passing for Complex Question Answering over Knowledge Graphscited by 24
  12. 2021Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Basecited by 16
3 more
  1. 2021Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphscited by 16
  2. 2021A Two-Stage Approach towards Generalization in Knowledge Base Question Answeringcited by 15
  3. 2020Template-based Question Answering using Recursive Neural Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 1.

8 papers.

  1. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  2. 2023ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relationscited by 39
  3. 2024SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Taskcited by 19
  4. 2023Schema-adaptable Knowledge Graph Constructioncited by 4
  5. 2022gBuilder: A Scalable Knowledge Graph Construction System for Unstructured Corpuscited by 2
  6. 2023Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Linkscited by 2
  7. 2022VGStore: A Multimodal Extension to SPARQL for Querying RDF Scene Graphcited by 1
  8. 2023ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sourcescited by 0