TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

By Pengcheng Yin, Graham Neubig. 2018

252 citations recorded by the source corpus.

We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs). TRANX uses a transition system based on the abstract syntax description language for the target MR, which gives it two major advantages: (1) it is highly accurate, using information from the syntax of the target MR to constrain the output space and model the information flow, and (2) it is highly generalizable, and can easily be applied to new types of MR by just writing a new abstract syntax description corresponding to the allowable structures in the MR. Experiments on four different semantic parsing and code generation tasks show that our system is generalizable, extensible, and effective, registering strong results compared to existing neural semantic parsers.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Information Extraction, Code Generation & Program Synthesis

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 Computer Vision and Pattern Recognition

In Natural Language Processing

In Information Extraction

In Code Generation & Program Synthesis

Citations in the corpus

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022, neutral): “, semantic parsing, use customized decoders to generate programs (Yin and Neubig, 2018; Ren et al., 2021).”
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, background): “, 2019) or sequences of parse actions (Chen et al., 2018; Cheng et al., 2019; Lin et al., 2019; Zhang et al., 2019; Yin and Neubig, 2018; Chen et al., 2018; Guo et al., 2019; Wang et al., 2020a; Li et al., 2021).”
Grammar-based Neural Text-to-SQL Generation (2019, methodology): “Grammar-based methods have been explored by Yin and Neubig (2018) for Wik-iSQL.”
Context Dependent Semantic Parsing: A Survey (2020, methodology): “TRANX (Yin and Neubig, 2018) defines the grammars in Abstract Syntax Description Language, while IRNET (Guo et al.”
Few-Shot Semantic Parsing for New Predicates (2021, methodology): “The supervised attention (Rabinovich et al., 2017; Yin and Neubig, 2018) is also applied to facilitate the learning of attention weights.”
A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization (2019, background): “The logical form (LX) and the execution accuracy (X) on dev set (consisting of 8,421 queries) and test set (consisting of 15,878 queries) of WikiSQL of several models are shown in Table 2.”
TreeGen: A Tree-Based Transformer Architecture for Code Generation (2019, methodology): “However, our model was directly adopted from the HS dataset, and achieved the highest accuracy, among all neural models ( Yin and Neubig 2018).”
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions (2021, result): “Our results show that both generative and retrieval models can predict SQL queries that match the user’s intention, but the scores are much lower than the original text-to-SQL task (Finegan-Dollak et al., 2018; Dong and Lapata, 2018a; Yin and Neubig, 2018; Cao et al., 2019; Rubin and Berant, 2021; H”
Semantic Parsing with Dual Learning (2019, unknown): “9 TRANX (Yin and Neubig, 2018) 86.”
Can we generate shellcodes via natural language? An empirical study (2021, methodology): “the Django dataset [67], a corpus widely used for code generation tasks [55,89,90, 91,37,21,30,85] and consisting of 18, 805 pairs of Python statements for the Django Web application framework alongside the corresponding English pseudo-code.”
ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering (2021, methodology): “The T RANX toolkit 4 (Yin and Neubig, 2018) employs a transition-based neural semantic parser to model the logical form generation procedure as a sequence of tree-constructing actions under grammar speciﬁcation.”
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (2019, background): “On the other hand, in view of the tree-structure nature of SQL (Yu et al., 2018b; Yin and Neubig, 2018), following the same”
An Empirical Study of the Non-Determinism of ChatGPT in Code Generation (2023, unknown): “Another primary concern highlighted in our analysis revolves around the operationalization of semantic, syntactic, and structural similarities into measurable metrics for assessing code similarity.”
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models (2021, background): “For a while now it has been possible to restrict auto-regressive decoding to only those token sequences that correctly parse to SQL abstract syntax trees (Yin and Neubig, 2018; Lin et al., 2019; Wang et al., 2020).”