# Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment

arXiv: https://arxiv.org/abs/2212.13036 · HTML: https://mlsanity.com/paper/2212.13036/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 26 Dec 2022.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph](https://mlsanity.com/paper/1801.10314/) (2018)
- [Learning to Rank Query Graphs for Complex Question Answering over Knowledge Graphs](https://mlsanity.com/paper/1811.01118/) (2018)
- [Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning](https://mlsanity.com/paper/2010.15877/) (2020)
- [Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base](https://mlsanity.com/paper/2109.03614/) (2021)
- [Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering](https://mlsanity.com/paper/1908.11053/) (2019)
- [Less is More: Data-Efficient Complex Question Answering over Knowledge Bases](https://mlsanity.com/paper/2010.15881/) (2020)
- [Iterative Utterance Segmentation for Neural Semantic Parsing](https://mlsanity.com/paper/2012.07019/) (2020)

## Built on by (most cited first, 1 of 1)

- [Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models](https://mlsanity.com/paper/2310.01290/) (2023)

## Abstract (arXiv)

Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions. However, there is a significant semantic and structural gap between natural language and action sequences, which makes this conversion difficult. In this paper, we introduce an alignment-enhanced complex question answering framework, called ALCQA, which mitigates this gap through question-to-action alignment and question-to-question alignment. We train a question rewriting model to align the question and each action, and utilize a pretrained language model to implicitly align the question and KG artifacts. Moreover, considering that similar questions correspond to similar action sequences, we retrieve top-k similar question-answer pairs at the inference stage through question-to-question alignment and propose a novel reward-guided action sequence selection strategy to select from candidate action sequences. We conduct experiments on CQA and WQSP datasets, and the results show that our approach outperforms state-of-the-art methods and obtains a 9.88% improvements in the F1 metric on CQA dataset. Our source code is available at https://github.com/TTTTTTTTy/ALCQA.