Coupling Distributed and Symbolic Execution for Natural Language Queries

By Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin. 2016

43 citations recorded by the source corpus.

Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor's intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback (2018, background): “More recently, several works have applied policy gradient techniques such as REINFORCE (Williams, 1992) to train neural semantic parsers (Liang et al. (2017); Mou et al. (2017); Peng et al. (2017); inter alia ).”
Chunk-Based Bi-Scale Decoder for Neural Machine Translation (2017, unknown): “Future work includes abandoning labeled chunk data, adopting reinforcement learning to explore the boundaries of phrase automatically (Mou et al., 2016).”
Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning (2021, background): “It also includes semantic parsing systems trained either without supervision (Liang et al., 2017; Mou et al., 2017; Muhlgay et al., 2019), or with synthetic language data (Marzoev et al., 2020; Xu et al., 2020b).”
HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering (2019, background): “Open-domain question answering (OpenQA) aims to seek answers for a broad range of questions from a large knowledge sources, e.g., structured knowledge bases (Berant et al. 2013; Mou et al. 2017) and unstructured documents from search engine (Ferrucci et al. 2010).”
FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase (2019, background): “…natural languages, such factoid QA tasks may serve as an excellent test-bed to study many natural language understanding problems, e.g., examine the recently emerging research efforts to combine neural models with the traditional symbolic processing methods (Liang et al., 2017; Mou et al., 2017).”
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning (2017, background): “Another direction incorporates the data in the table as an additional input (Pasupat & Liang, 2015; Mou et al., 2016).”