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

arXiv: https://arxiv.org/abs/2207.03680 · HTML: https://mlsanity.com/paper/2207.03680/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 8 Jul 2022.

## Builds on (most cited first, 15 of 15)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Leveraging Abstract Meaning Representation for Knowledge Base Question Answering](https://mlsanity.com/paper/2012.01707/) (2020)
- [KBQA: Learning Question Answering over QA Corpora and Knowledge Bases](https://mlsanity.com/paper/1903.02419/) (2019)
- [UniRE: A Unified Label Space for Entity Relation Extraction](https://mlsanity.com/paper/2107.04292/) (2021)
- [Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base](https://mlsanity.com/paper/1910.05069/) (2019)
- [Message Passing for Complex Question Answering over Knowledge Graphs](https://mlsanity.com/paper/1908.06917/) (2019)
- [Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base](https://mlsanity.com/paper/2109.03614/) (2021)
- [Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs](https://mlsanity.com/paper/2111.00732/) (2021)
- [A Two-Stage Approach towards Generalization in Knowledge Base Question Answering](https://mlsanity.com/paper/2111.05825/) (2021)
- [Template-based Question Answering using Recursive Neural Networks](https://mlsanity.com/paper/2004.13843/) (2020)

## Built on by (most cited first, 8 of 8)

- [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://mlsanity.com/paper/2308.11761/) (2023)
- [ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations](https://mlsanity.com/paper/2304.14827/) (2023)
- [SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task](https://mlsanity.com/paper/2406.10710/) (2024)
- [Schema-adaptable Knowledge Graph Construction](https://mlsanity.com/paper/2305.08703/) (2023)
- [gBuilder: A Scalable Knowledge Graph Construction System for Unstructured Corpus](https://mlsanity.com/paper/2208.09705/) (2022)
- [Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links](https://mlsanity.com/paper/2309.05201/) (2023)
- [VGStore: A Multimodal Extension to SPARQL for Querying RDF Scene Graph](https://mlsanity.com/paper/2209.02981/) (2022)
- [ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources](https://mlsanity.com/paper/2308.04800/) (2023)

## 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.