scholarly journals A Grammar-Based Structural CNN Decoder for Code Generation

2019 ◽  
Vol 33 ◽  
pp. 7055-7062 ◽  
Author(s):  
Zeyu Sun ◽  
Qihao Zhu ◽  
Lili Mou ◽  
Yingfei Xiong ◽  
Ge Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Programming Language ◽  
Code Generation ◽  
State Of The Art ◽  
Semantic Parsing ◽  
Code Generator ◽  
Percentage Points ◽  
Grammar Rules ◽  
Previous State ◽  
Program Description

Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more tokens than a natural language sentence, and thus it may be inappropriate for RNN to capture such a long sequence. In this paper, we propose a grammar-based structural convolutional neural network (CNN) for code generation. Our model generates a program by predicting the grammar rules of the programming language; we design several CNN modules, including the tree-based convolution and pre-order convolution, whose information is further aggregated by dedicated attentive pooling layers. Experimental results on the HearthStone benchmark dataset show that our CNN code generator significantly outperforms the previous state-of-the-art method by 5 percentage points; additional experiments on several semantic parsing tasks demonstrate the robustness of our model. We also conduct in-depth ablation test to better understand each component of our model.

scholarly journals TreeGen: A Tree-Based Transformer Architecture for Code Generation

2020 ◽  
Vol 34 (05) ◽  
pp. 8984-8991
Author(s):  
Zeyu Sun ◽  
Qihao Zhu ◽  
Yingfei Xiong ◽  
Yican Sun ◽  
Lili Mou ◽  
...  
Keyword(s):  
Code Generation ◽  
State Of The Art ◽  
Structural Information ◽  
Semantic Parsing ◽  
Generation System ◽  
Neural Architecture ◽  
Percentage Points ◽  
Code Generators ◽  
Grammar Rules ◽  
Previous State

A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems. One is the long dependency problem, where a code element often depends on another far-away code element. A variable reference, for example, depends on its definition, which may appear quite a few lines before. The other problem is structure modeling, as programs contain rich structural information. In this paper, we propose a novel tree-based neural architecture, TreeGen, for code generation. TreeGen uses the attention mechanism of Transformers to alleviate the long-dependency problem, and introduces a novel AST reader (encoder) to incorporate grammar rules and AST structures into the network. We evaluated TreeGen on a Python benchmark, HearthStone, and two semantic parsing benchmarks, ATIS and GEO. TreeGen outperformed the previous state-of-the-art approach by 4.5 percentage points on HearthStone, and achieved the best accuracy among neural network-based approaches on ATIS (89.1%) and GEO (89.6%). We also conducted an ablation test to better understand each component of our model.

scholarly journals From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations

2018 ◽  
Vol 6 ◽  
pp. 343-356 ◽  
Author(s):  
Egoitz Laparra ◽  
Dongfang Xu ◽  
Steven Bethard
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Comparative Analysis ◽  
State Of The Art ◽  
Learning Approaches ◽  
Semantic Parsing ◽  
Time Intervals ◽  
Semantic Composition ◽  
Previous State ◽  
New Scoring

This paper presents the first model for time normalization trained on the SCATE corpus. In the SCATE schema, time expressions are annotated as a semantic composition of time entities. This novel schema favors machine learning approaches, as it can be viewed as a semantic parsing task. In this work, we propose a character level multi-output neural network that outperforms previous state-of-the-art built on the TimeML schema. To compare predictions of systems that follow both SCATE and TimeML, we present a new scoring metric for time intervals. We also apply this new metric to carry out a comparative analysis of the annotations of both schemes in the same corpus.

scholarly journals A Hybrid Network for Large-Scale Action Recognition from RGB and Depth Modalities

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3305 ◽  
Author(s):  
Huogen Wang ◽  
Zhanjie Song ◽  
Wanqing Li ◽  
Pichao Wang
Keyword(s):  
Neural Network ◽  
Action Recognition ◽  
Canonical Correlation ◽  
Large Scale ◽  
State Of The Art ◽  
Hybrid Network ◽  
Support Vector ◽  
Multiple Modalities ◽  
Large Margin ◽  
Percentage Points

The paper presents a novel hybrid network for large-scale action recognition from multiple modalities. The network is built upon the proposed weighted dynamic images. It effectively leverages the strengths of the emerging Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) based approaches to specifically address the challenges that occur in large-scale action recognition and are not fully dealt with by the state-of-the-art methods. Specifically, the proposed hybrid network consists of a CNN based component and an RNN based component. Features extracted by the two components are fused through canonical correlation analysis and then fed to a linear Support Vector Machine (SVM) for classification. The proposed network achieved state-of-the-art results on the ChaLearn LAP IsoGD, NTU RGB+D and Multi-modal & Multi-view & Interactive ( M 2 I ) datasets and outperformed existing methods by a large margin (over 10 percentage points in some cases).

scholarly journals Problems and Perspectives of Code Generation from UML Class Diagram

2011 ◽  
Vol 44 (1) ◽  
pp. 75-84 ◽  
Author(s):  
Janis Sejans ◽  
Oksana Nikiforova
Keyword(s):  
Programming Language ◽  
Code Generation ◽  
Unified Modeling Language ◽  
Experimental Models ◽  
Class Diagram ◽  
Code Generator ◽  
Unified Modeling ◽  
Model Driven ◽  
Technological Diversity ◽  
Uml Class Diagram

Problems and Perspectives of Code Generation from UML Class Diagram As a result of increasing technological diversity, more attention is being focused on model driven architecture (MDA), and its standard - Unified Modeling Language (UML). UML class diagrams require correct diagram notation mapping to target programming language syntax under the framework of MDA. Currently there are plenty of CASE tools which claim that they are able to generate the source code from UML models. Therefore by combining the knowledge of a programming language, syntax rules and UML class diagram notation semantic, an experimental model for stressing the code generator can be produced, thus allowing comparison of quality of the transformation result. This paper describes a creation of such experimental models.

scholarly journals ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network

2020 ◽  
Vol 34 (05) ◽  
pp. 8180-8187 ◽  
Author(s):  
Fei Li ◽  
Hong Yu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Evaluation Metrics ◽  
Research Attention ◽  
Clinical Text ◽  
Previous State ◽  
Mimic Iii ◽  
Icd Coding ◽  
Document Representations

Automated ICD coding, which assigns the International Classification of Disease codes to patient visits, has attracted much research attention since it can save time and labor for billing. The previous state-of-the-art model utilized one convolutional layer to build document representations for predicting ICD codes. However, the lengths and grammar of text fragments, which are closely related to ICD coding, vary a lot in different documents. Therefore, a flat and fixed-length convolutional architecture may not be capable of learning good document representations. In this paper, we proposed a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) for ICD coding. The innovations of our model are two-folds: it utilizes a multi-filter convolutional layer to capture various text patterns with different lengths and a residual convolutional layer to enlarge the receptive field. We evaluated the effectiveness of our model on the widely-used MIMIC dataset. On the full code set of MIMIC-III, our model outperformed the state-of-the-art model in 4 out of 6 evaluation metrics. On the top-50 code set of MIMIC-III and the full code set of MIMIC-II, our model outperformed all the existing and state-of-the-art models in all evaluation metrics. The code is available at https://github.com/foxlf823/Multi-Filter-Residual-Convolutional-Neural-Network.

scholarly journals An Enhanced Image Segmentation From 3D to 2D by Using Modified Neural Network

2021 ◽  
Vol 9 (12) ◽  
pp. 1712-1716
Author(s):  
P. Pushpalatha
Keyword(s):  
Neural Network ◽  
Optical Coherence Tomography Angiography ◽  
State Of The Art ◽  
Vascular Networks ◽  
Clinical Routine ◽  
Non Invasive ◽  
Previous State ◽  
Visualization Techniques ◽  
High Pass ◽  
Data Acquisition Process

Abstract: Optical coherence tomography angiography (OCTA) is an imaging which can applied in ophthalmology to provide detailed visualization of the perfusion of vascular networks in the eye. compared to previous state of the art dye-based imaging, such as fluorescein angiography. OCTA is non-invasive, time efficient, and it allows for the examination of retinal vascular in 3D. These advantage of the technique combined with the good usability in commercial devices led to a quick adoption of the new modality in the clinical routine. However, the interpretation of OCTA data is not without problems commonly observed image artifacts and the quite involved algorithmic details of OCTA signal construction can make the clinical assessment of OCTA exams challenging. In this paper we describe the technical background of OCTA and discuss the data acquisition process, common image visualization techniques, as well as 3D to 2D projection using high pass filtering, relu function and convolution neural network (CNN) for more accuracy and segmentation results.

scholarly journals DeepFacade: A Deep Learning Approach to Facade Parsing

2017 ◽  
Author(s):  
Hantang Liu ◽  
Jialiang Zhang ◽  
Jianke Zhu ◽  
Steven C. H. Hoi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Novel ◽  
Semantic Categories ◽  
The Neural Network ◽  
Building Facades ◽  
Previous State ◽  
Bounding Boxes

The parsing of building facades is a key component to the problem of 3D street scenes reconstruction, which is long desired in computer vision. In this paper, we propose a deep learning based method for segmenting a facade into semantic categories. Man-made structures often present the characteristic of symmetry. Based on this observation, we propose a symmetric regularizer for training the neural network. Our proposed method can make use of both the power of deep neural networks and the structure of man-made architectures. We also propose a method to refine the segmentation results using bounding boxes generated by the Region Proposal Network. We test our method by training a FCN-8s network with the novel loss function. Experimental results show that our method has outperformed previous state-of-the-art methods significantly on both the ECP dataset and the eTRIMS dataset. As far as we know, we are the first to employ end-to-end deep convolutional neural network on full image scale in the task of building facades parsing.

scholarly journals Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions

2013 ◽  
Vol 1 ◽  
pp. 49-62 ◽  
Author(s):  
Yoav Artzi ◽  
Luke Zettlemoyer
Keyword(s):  
Natural Language ◽  
Supervised Learning ◽  
State Of The Art ◽  
Semantic Parsing ◽  
Weak Supervision ◽  
Instruction Sets ◽  
Strong Signal ◽  
Previous State ◽  
Strong Performance ◽  
Weakly Supervised

The context in which language is used provides a strong signal for learning to recover its meaning. In this paper, we show it can be used within a grounded CCG semantic parsing approach that learns a joint model of meaning and context for interpreting and executing natural language instructions, using various types of weak supervision. The joint nature provides crucial benefits by allowing situated cues, such as the set of visible objects, to directly influence learning. It also enables algorithms that learn while executing instructions, for example by trying to replicate human actions. Experiments on a benchmark navigational dataset demonstrate strong performance under differing forms of supervision, including correctly executing 60% more instruction sets relative to the previous state of the art.

scholarly journals Back to the Future for Dialogue Research

2020 ◽  
Vol 34 (09) ◽  
pp. 13514-13519
Author(s):  
Philip R Cohen
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Research Strategy ◽  
The State ◽  
Semantic Parsing ◽  
Collaborative Dialogue ◽  
The Future ◽  
Dialogue Manager

This “blue sky” paper argues that future conversational systems that can engage in multiparty, collaborative dialogues will require a more fundamental approach than existing technology. This paper identifies significant limitations of the state of the art, and argues that our returning to the plan-based approach to dialogue will provide a stronger foundation. Finally, I suggest a research strategy that couples neural network-based semantic parsing with plan-based reasoning in order to build a collaborative dialogue manager.

scholarly journals The Lean 4 Theorem Prover and Programming Language

2021 ◽  
pp. 625-635
Author(s):  
Leonardo de Moura ◽  
Sebastian Ullrich
Keyword(s):  
Programming Language ◽  
Code Generation ◽  
Decision Procedures ◽  
Theorem Prover ◽  
Code Generator ◽  
Proof Automation ◽  
Significant Performance ◽  
Efficient Code ◽  
Tabled Resolution ◽  
New System

AbstractLean 4 is a reimplementation of the Lean interactive theorem prover (ITP) in Lean itself. It addresses many shortcomings of the previous versions and contains many new features. Lean 4 is fully extensible: users can modify and extend the parser, elaborator, tactics, decision procedures, pretty printer, and code generator. The new system has a hygienic macro system custom-built for ITPs. It contains a new typeclass resolution procedure based on tabled resolution, addressing significant performance problems reported by the growing user base. Lean 4 is also an efficient functional programming language based on a novel programming paradigm called functional but in-place. Efficient code generation is crucial for Lean users because many write custom proof automation procedures in Lean itself.

Sign in / Sign up

Export Citation Format

Share Document