Filters








7,220 Hits in 4.1 sec

Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable Sentiment Dependency Learning [article]

Heng Yang, Biqing Zeng, Mayi Xu, Tianxing Wang
2021 arXiv   pre-print
However, syntax information (e.g., syntactic dependency trees) usually occupies expensive computational resources in terms of the operation of the adjacent matrix.  ...  Aspect-based Sentiment Classification (ABSC) is a challenging sub-task of traditional sentiment analysis.  ...  Intelligence of China, project number: 2019KZDZX1033.  ... 
arXiv:2110.08604v1 fatcat:ztzf3o72xbb2jaeu2hdepptb2u

Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting [article]

Chen Lin, Zhichao Ouyang, Junqing Zhuang, Jianqiang Chen, Hui Li, Rongxin Wu
2021 arXiv   pre-print
BASTS splits the code of a method based on the blocks in the dominator tree of the Control Flow Graph, and generates a split AST for each code split.  ...  In this paper, we present the Block-wise Abstract Syntax Tree Splitting method (BASTS for short), which fully utilizes the rich tree-form syntax structure in ASTs, for improving code summarization.  ...  few works simplify the tree structure of ASTs, e.g., transform an AST to a binary tree [20] .  ... 
arXiv:2103.07845v2 fatcat:tki2nfw7xfdvvipajj4bcjxguq

Context-Aware Parse Trees [article]

Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Paul Petersen, Jesmin Jahan Tithi, Tim Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich
2020 arXiv   pre-print
The simplified parse tree (SPT) presented in Aroma, a state-of-the-art code recommendation system, is a tree-structured representation used to infer code semantics by capturing program structure rather  ...  This is a departure from the classical abstract syntax tree, which is principally driven by programming language syntax.  ...  To our knowledge, Aroma's simplified parse tree (SPT) represents a state-of-the-art structural representation for code similarity [23] .  ... 
arXiv:2003.11118v1 fatcat:5l2nzt5gkzfgdj3rladwnbef3u

RPT: Effective and Efficient Retrieval of Program Translations from Big Code [article]

Binger Chen, Ziawasch Abedjan
2021 arXiv   pre-print
One way to automate this process is to make use of the big data of programs, i.e., Big Code. In particular, one can search for program translations in Big Code.  ...  Furthermore, we present our index structure and hierarchical filtering mechanism for efficient code retrieval from a Big Code database.  ...  In future work, will augment the retrieval system with program generation to overcome the limitations of the database.  ... 
arXiv:2103.12797v1 fatcat:de2lurjhwjcxdpisszfwumoizu

An Attention-Based Syntax-Tree and Tree-LSTM Model for Sentence Summarization

Wenfeng Liu
2017 International Journal of Performability Engineering  
Thereinto, block-alignment is used to align the input and output syntax blocks, while inter-alignment is used for alignment of words within that of block pairs.  ...  In this work, we propose an attention-based Tree-LSTM model for sentence summarization, which utilizes an attention-based syntactic structure as auxiliary information.  ...  Acknowledgements This work was supported by National Natural Science Foundation of China (number: 61373148, 61502151) and National Social Science Foundation (number: 12BXW040).  ... 
doi:10.23940/ijpe.17.05.p20.775782 fatcat:z4cxdppbhjecbk7nakviesh7q4

Syntax-Infused Variational Autoencoder for Text Generation

Xinyuan Zhang, Yi Yang, Siyang Yuan, Dinghan Shen, Lawrence Carin
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences.  ...  Finally, we show that the proposed models can be used for unsupervised paraphrasing given different syntactic tree templates.  ...  We thank Kazi Shefaet Rahman, Ozan Irsoy, Igor Malioutov and other people in the Bloomberg NLP platform team for their feedback on the initial idea of the work.  ... 
doi:10.18653/v1/p19-1199 dblp:conf/acl/ZhangYYSC19 fatcat:le3674of3nhdlmmiiqubtqvso4

Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

Ondřej Dušek, Filip Jurcicek
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts  ...  The joint setup offers better performance, surpassing state-of-the-art with regards to n-gram-based scores while providing more relevant outputs.  ...  We thank our colleagues and the anonymous reviewers for helpful comments.  ... 
doi:10.18653/v1/p16-2008 dblp:conf/acl/DusekJ16 fatcat:ysnboxsdondyjeby3tzfzg5aau

Syntax Vector Learning using correspondence for Natural Language Understanding

Hyein Seo, Sangkeun Jung, Taewook Hwang, Hyunji Kim, Yoon-Hyung Roh
2021 IEEE Access  
Most of the syntactic structures take the form of a tree. Many previous studies have focused on an encoding tree structure [6] . In this study, we simplified the syntax encoding pipeline using BERT.  ...  The process of encoding is the same as that for the dependency parsing-or phrase structure parsing-type syntax reader. C.  ... 
doi:10.1109/access.2021.3087271 fatcat:pt6lftkj2jbn5o3lddnrzdcqji

SamQL: a structured query language and filtering tool for the SAM/BAM file format

Christopher T Lee, Manolis Maragkakis
2021 BMC Bioinformatics  
SamQL is a complete query language that we envision as a step to a structured database engine for genomics.  ...  Here we introduce SamQL, an SQL-like query language for the SAM format with intuitive syntax that supports complex and efficient queries on top of SAM/BAM files and that can replace commonly used Bash  ...  The whole tree is progressively replaced by a single FILTER function that is used for record filtering Table 2 2 Comparison of the error messages of the different tools for a syntax error involving a  ... 
doi:10.1186/s12859-021-04390-3 pmid:34600480 fatcat:w7j5deeqcfcbxm2kbntts7ifp4

Process Discovery for Structured Program Synthesis [article]

Dell Zhang, Alexander Kuhnle, Julian Richardson, Murat Sensoy
2020 arXiv   pre-print
To our knowledge, this is the first process discovery algorithm that is made for the purpose of program synthesis.  ...  discovery metrics but also in terms of the effectiveness in finding out the true underlying structured program from a small number of its execution traces.  ...  .): S 1 S −→ (S 1 &S 2 ) concurrence para: S 1 S 2 a b f e d c | & * (a) abstract syntax tree a while (.): if (.): b else: c d para: e f (b) source code To a large degree, the (structured program) syntax  ... 
arXiv:2008.05804v1 fatcat:i2neriv3lrg3lowwgm2vvsry6i

Semantic Preserving Bijective Mappings of Mathematical Formulae Between Document Preparation Systems and Computer Algebra Systems [chapter]

Howard S. Cohl, Moritz Schubotz, Abdou Youssef, André Greiner-Petter, Jürgen Gerhard, Bonita V. Saunders, Marjorie A. McClain, Joon Bang, Kevin Chen
2017 Lecture Notes in Computer Science  
We have also developed tools for translating the entire Wolfram Encoding Continued Fraction Knowledge and University of Antwerp Continued Fractions for Special Functions datasets, for use in the NIST Digital  ...  ) is achieved by using a semantic macro set.  ...  We would also like to thank Eric Weisstein for supplying the Wolfram eCF dataset, Annie Cuyt, Franky Backeljauw, and Stefan Becuwe for supplying the University of Antwerp CFSF Maple dataset, and Adri Olde  ... 
doi:10.1007/978-3-319-62075-6_9 fatcat:4s4h6dzp5bafhjqop5gdmlfvqm

Adding Missing Words to Regular Expressions [chapter]

Thomas Rebele, Katerina Tzompanaki, Fabian M. Suchanek
2018 Lecture Notes in Computer Science  
We investigate how missing words can be added automatically to a regular expression by creating disjunctions at the appropriate positions.  ...  for 20: c1, ..., c k ← children of n between m(i) and m(j) 21: Replace c1, ..., c k by a disjunction c1...c k |wi+1, ..., wj−1 22: end for The next step is to repair the regex.  ...  make children of n to the right optional 16: end for 17: for node n on the path from m(j) to n in the syntax tree of r do 18: if n is concatenation then make children of n to the left optional 19: end  ... 
doi:10.1007/978-3-319-93037-4_6 fatcat:qotbzjxccbeydaqlmuqnhbq6mq

Understanding Web query interfaces

Zhen Zhang, Bin He, Kevin Chen-Chuan Chang
2004 Proceedings of the 2004 ACM SIGMOD international conference on Management of data - SIGMOD '04  
At the heart of our form extractor, we thus develop a 2P grammar and a best-effort parser, which together realize a parsing mechanism for a hypothetical syntax.  ...  Toward this insight, we hypothesize the existence of a hidden syntax that guides the creation of query interfaces, albeit from different sources.  ...  Constraint C is a boolean expression defined on M . Constructor F is a function defined on M , returning an instance of H. Figure 9 : 9 Two parse trees for query interface Q1.  ... 
doi:10.1145/1007568.1007583 dblp:conf/sigmod/ZhangHC04 fatcat:belhisbzofdwdkgbvfwkdboeoe

WASTK: A Weighted Abstract Syntax Tree Kernel Method for Source Code Plagiarism Detection

Deqiang Fu, Yanyan Xu, Haoran Yu, Boyang Yang
2017 Scientific Programming  
WASTK firstly transfers the source code of a program to an abstract syntax tree and then gets the similarity by calculating the tree kernel of two abstract syntax trees.  ...  In this paper, we introduce a source code plagiarism detection method, named WASTK (Weighted Abstract Syntax Tree Kernel), for computer science education.  ...  Besides, a simplified abstract syntax tree results in less time needed by running ASTK and WASTK, which helps to solve Problem 3.  ... 
doi:10.1155/2017/7809047 fatcat:za7s5oo2o5bkppua5w7zjyxw7i

Syntax Role for Neural Semantic Role Labeling

Zuchao Li, Hai Zhao, Shexia He, Jiaxun Cai
2021 Computational Linguistics  
We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruningbased and  ...  Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.  ...  To simplify implementation, we construct a new syntactic tree based on the gold standard parse tree.  ... 
doi:10.1162/coli_a_00408 fatcat:pt6ntrdsovgjra7rjhrpq5mf5i
« Previous Showing results 1 — 15 out of 7,220 results