Data Recombination for Neural Semantic Parsing

By Robin Jia, Percy Liang. 2016

480 citations recorded by the source corpus.

Modeling crisp logical regularities is crucial in semantic parsing, making it difficult for neural models with no task-specific prior knowledge to achieve good results. In this paper, we introduce data recombination, a novel framework for injecting such prior knowledge into a model. From the training data, we induce a high-precision synchronous context-free grammar, which captures important conditional independence properties commonly found in semantic parsing. We then train a sequence-to-sequence recurrent network (RNN) model with a novel attention-based copying mechanism on datapoints sampled from this grammar, thereby teaching the model about these structural properties. Data recombination improves the accuracy of our RNN model on three semantic parsing datasets, leading to new state-of-the-art performance on the standard GeoQuery dataset for models with comparable supervision.

Subfields: Artificial Intelligence, Natural Language Processing, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

In Signal Processing

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, methodology): “A common approach is to increase the source side data, for instance by adding modifications or sampling from generative models (Hannun et al., 2014; Jia & Liang, 2016; Krizhevsky et al., 2017; Antoniou et al., 2017; Yasunaga et al., 2018; Yu et al., 2018a; Lee et al., 2019; Berthelot et al., 2019;…”
SPoC: Search-based Pseudocode to Code (2019, background): “Partial parses can be constructed by combining smaller partial parses in a bottom-up fashion [58, 28, 27], adding the next token to the sequence [10, 22, 51, 11, 25], or creating a new node in a tree structure [10, 26, 54, 39].”
Learning with Latent Language (2017, positive): “Data augmentation Due to their comparatively small size, a data augmentation scheme (Jia and Liang, 2016) is employed for the regular expression and navigation datasets.”
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback (2018, methodology): “Semantic parsers have been successfully trained using neural sequence-to-sequence models with a cross-entropy objective and question-parse pairs (Jia and Liang, 2016; Dong and Lapata, 2016)) or question-answer pairs (Neelakantan et al.”
Few-shot Mining of Naturally Occurring Inputs and Outputs (2022, methodology): “Data augmentation Data augmentation is a popular technique with a large body of work (Wang and Yang, 2015; Jia and Liang, 2016) et al., 2019), common-sense reasoning (Yang et al., 2020), and machine translation (Sennrich et al., 2016).”
Adversarial Examples for Evaluating Reading Comprehension Systems (2017, methodology): “We could also adversarially generate new examples by combining multiple existing ones, in the spirit of Data Recombination (Jia and Liang, 2016).”
The Web as a Knowledge-Base for Answering Complex Questions (2018, methodology): “We encode ˆ q with a one-layer GRU (Cho et al., 2014), and decode z with a one-layer GRU with attention as in Jia and Liang (2016).”
Challenges in Data-to-Document Generation (2017, positive): “involving augmenting encoder-decoder models to copy words directly from the source material on which they condition (Gu et al., 2016; Gülçehre et al., 2016; Merity et al., 2016; Jia and Liang, 2016; Yang et al., 2016).”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, methodology): “In addition, we include Seq2Seq+Copying by adding an attention-based copying operation similar to (Jia and Liang, 2016).”
Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (2016, methodology): “In semantic parsing, recent work handled this (Dong and Lapata, 2016; Jia and Liang, 2016) by training from manually annotated programs and avoiding program execution at training time.”
European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" (2016, neutral): “Research is underway in pursuit of rendering algorithms more amenable to ex post and ex ante inspection [11, 31, 20].”
Automatically Learning Data Augmentation Policies for Dialogue Tasks (2019, neutral): “…2017; Tran et al., 2017; Lemley et al., 2017) and NLP (F¨urstenau and Lapata, 2009; Sen-nrich et al., 2016; Wang and Yang, 2015; Zhang et al., 2015; Jia and Liang, 2016; Kim and Rush, 2016; Hu et al., 2017; Xu et al., 2017; Xia et al., 2017; Silfverberg et al., 2017; Kaﬂe et al., 2017; Hou et al.,…”
Key-Value Retrieval Networks for Task-Oriented Dialogue (2017, background): “Recent literature has shown that incorporating a copying mechanism into neural architectures improves performance on various sequence-to-sequence tasks (Jia and Liang, 2016; Gu et al., 2016; Ling et al., 2016; Gulcehre et al., 2016; Eric and Manning, 2017).”
Good-Enough Compositional Data Augmentation (2019, methodology): “In semantic parsing, it gives improvements comparable to the data augmentation approach of Jia and Liang (2016) on λ -calculus expressions, better performance than that approach on a different split of the data designed to test generalization more rigorously, and better performance on a different…”
Learning a Neural Semantic Parser from User Feedback (2017, methodology): “based on manually engineered semantic grammars (Jia and Liang, 2016)) and learning through direct interaction with users (e.”
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables (2017, methodology): “Recent work has shown that recurrent neural networks can be used for semantic parsing by encoding the question then predicting each token of the logical form in sequence (Jia and Liang, 2016; Dong and Lapata, 2016).”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, methodology): “Several ideas have been explored to enhance the performance of these models such as data augmentation (Kočiský et al., 2016; Jia and Liang, 2016), transfer learning (Fan et al.”
From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood (2017, background): “There has been recent interest in using recurrent neural networks for semantic parsing, both for modeling logical forms (Dong and Lapata, 2016; Jia and Liang, 2016; Liang et al., 2017) and for end-to-end execution (Yin et al.”