A Sketch-Based System for Semantic Parsing

2019-09-02 · Zechang Li, Yuxuan Lai, Yuxi Xie, Yansong Feng, Dongyan Zhao

This paper presents our semantic parsing system for the evaluation task of open domain semantic parsing in NLPCC 2019. Many previous works formulate semantic parsing as a sequence-to-sequence(seq2seq) problem. Instead, we treat the task as a sketch-based problem in a coarse-to-fine(coarse2fine) fashion. The sketch is a high-level structure of the logical form exclusive of low-level details such as entities and predicates. In this way, we are able to optimize each part individually. Specifically, we decompose the process into three stages: the sketch classification determines the high-level structure while the entity labeling and the matching network fill in missing details. Moreover, we adopt the seq2seq method to evaluate logical form candidates from an overall perspective. The co-occurrence relationship between predicates and entities contribute to the reranking as well. Our submitted system achieves the exactly matching accuracy of 82.53% on full test set and 47.83% on hard test subset, which is the 3rd place in NLPCC 2019 Shared Task 2. After optimizations for parameters, network structure and sampling, the accuracy reaches 84.47% on full test set and 63.08% on hard test subset(Our code and data are available at https://github.com/zechagl/NLPCC2019-Semantic-Parsing).

📄 PDF Abstract BibTeX arXiv:1909.00574

Code (1)

zechagl/NLPCC2019-Semantic-Parsing 공식 구현 tf

Tasks

RerankingSemantic ParsingTask 2

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Deep Semantic Parsing of Freehand Sketches with Homogeneous Transformation, Soft-Weighted Loss, and Staged Learning

2019-10-14 · Ying Zheng, Hongxun Yao, Xiaoshuai Sun

In this paper, we propose a novel deep framework for part-level semantic parsing of freehand sketches, which makes three main contributions that are experimentally shown to have substantial practical merit. First, we pro…

Domain Adaptation Image Retrieval Retrieval Semantic Parsing+1

SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks

2017-09-05 · Ravi Kiran Sarvadevabhatla, Isht Dwivedi, Abhijat Biswas, Sahil Manocha 외

The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SketchParse, the first deep-network architecture for fully automati…

Image Retrieval Object Pose Prediction Retrieval+1

Fashion Editing with Adversarial Parsing Learning

2019-06-03 · CVPR 2020 6 · Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang 외

Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value. Existing works often treat it as a general inpa…

Decoder Generative Adversarial Network Human Parsing Image Manipulation

Coarse-to-Fine Decoding for Neural Semantic Parsing

2018-05-12 · ACL 2018 7 · Li Dong, Mirella Lapata

Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two …

Semantic Parsing

Sketch It Out: Exploring Label-Free Structural Cues for Multimodal Gait Recognition

2026-03-04 · Chao Zhang, Zhuang Zheng, Ruixin Li, Zhanyong Mei arxiv

Gait recognition is a non-intrusive biometric technique for security applications, yet existing studies are dominated by silhouette- and parsing-based representations. Silhouettes are sparse and miss internal structural …

Gait Recognition