GraphQ IR: Unifying Semantic Parsing of Graph Query Language with Intermediate Representation

05/24/2022
by   Lunyiu Nie, et al.
0

Subject to the semantic gap lying between natural and formal language, neural semantic parsing is typically bottlenecked by the paucity and imbalance of data. In this paper, we propose a unified intermediate representation (IR) for graph query languages, namely GraphQ IR. With the IR's natural-language-like representation that bridges the semantic gap and its formally defined syntax that maintains the graph structure, neural semantic parser can more effectively convert user queries into our GraphQ IR, which can be later automatically compiled into different downstream graph query languages. Extensive experiments show that our approach can consistently achieve state-of-the-art performance on benchmarks KQA Pro, Overnight and MetaQA. Evaluations under compositional generalization and few-shot learning settings also validate the promising generalization ability of GraphQ IR with at most 11

READ FULL TEXT
research
09/01/2018

Dependency-based Hybrid Trees for Semantic Parsing

We propose a novel dependency-based hybrid tree model for semantic parsi...
research
02/20/2023

Query Performance Prediction for Neural IR: Are We There Yet?

Evaluation in Information Retrieval relies on post-hoc empirical procedu...
research
10/22/2019

Transductive Parsing for Universal Decompositional Semantics

We introduce a transductive model for parsing into Universal Decompositi...
research
05/22/2019

Deeper Text Understanding for IR with Contextual Neural Language Modeling

Neural networks provide new possibilities to automatically learn complex...
research
09/09/2023

FAIR: Flow Type-Aware Pre-Training of Compiler Intermediate Representations

While the majority of existing pre-trained models from code learn source...
research
08/25/2023

An Intermediate Representation for Composable Typed Streaming Dataflow Designs

Tydi is an open specification for streaming dataflow designs in digital ...

Please sign up or login with your details

Forgot password? Click here to reset