Filters








4,145 Hits in 6.2 sec

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model [article]

Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Liwei Chen, Vadim Sheinin
2018 arXiv   pre-print
We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form.  ...  Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph  ...  Graph-to-sequence Model for Semantic Parsing After building the syntactic graph for the input text, we employ a novel graph-to-sequence model (Xu et al., 2018) , which includes a graph encoder and a sequence  ... 
arXiv:1808.07624v1 fatcat:uenxcq3dfjeftesvhvr2hmwupy

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Liwei Chen, Vadim Sheinin
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
In this paper, we first propose to use the syntactic graph to represent three types of syntactic information, i.e., word order, dependency and constituency features; then employ a graph-tosequence model  ...  Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency or constituent  ...  Graph-to-sequence Model for Semantic Parsing After building the syntactic graph for the input text, we employ a novel graph-to-sequence model (Xu et al., 2018) , which includes a graph encoder and a sequence  ... 
doi:10.18653/v1/d18-1110 dblp:conf/emnlp/XuWWYCS18 fatcat:ztx75adlwvdwrfzib6p67yclru

A Survey of Syntactic-Semantic Parsing Based on Constituent and Dependency Structures [article]

Meishan Zhang
2020 arXiv   pre-print
This article briefly reviews the representative models of constituent parsing and dependency parsing, and also dependency graph parsing with rich semantics.  ...  Constituent parsing is majorly targeted to syntactic analysis, and dependency parsing can handle both syntactic and semantic analysis.  ...  For semantic parsing, the dependency-based grammar is not enough for rich semantics, even being relaxed with graph constraints.  ... 
arXiv:2006.11056v1 fatcat:pd22rciuxzdc5kvghaapjjyg3u

Joint Universal Syntactic and Semantic Parsing

Elias Stengel-Eskin, Kenton Murray, Sheng Zhang, Aaron Steven White, Benjamin Van Durme
2021 Transactions of the Association for Computational Linguistics  
We explore multiple model architectures that allow us to exploit the rich syntactic and semantic annotations contained in the Universal Decompositional Semantics (UDS) dataset, jointly parsing Universal  ...  While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other.  ...  We would like to thank the action editors, Carlos Gómez-Rodríguez and Miguel Ballesteros, and the  ... 
doi:10.1162/tacl_a_00396 fatcat:7wxn7djko5gydmqzu4velaueem

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation [article]

Yu Chen, Lingfei Wu, Mohammed J. Zaki
2020 arXiv   pre-print
To address these limitations, in this paper, we propose a reinforcement learning (RL) based graph-to-sequence (Graph2Seq) model for QG.  ...  and RL losses to ensure the generation of syntactically and semantically valid text.  ...  We think it is because a Graph2Seq model is able to exploit the rich text structure information better than a Seq2Seq model.  ... 
arXiv:1908.04942v4 fatcat:xsfuywd7ovgoziueizxeilabwu

Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis [article]

Yixuan Zhou, Changhe Song, Jingbei Li, Zhiyong Wu, Yanyao Bian, Dan Su, Helen Meng
2022 arXiv   pre-print
Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS).  ...  To better utilize the dependency structure, relational gated graph network (RGGN) is introduced to make semantic information flow and aggregate through the dependency structure.  ...  In this regard, how to exploit the rich linguistic information 2 in raw text (including syntax, semantics, pragmatics, etc.) corresponding to the variation of speech is crucial to handle the one-to-many  ... 
arXiv:2104.06835v3 fatcat:47qegsc2kfaozcdjynxzxvtmua

Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model

James Henderson, Paola Merlo, Ivan Titov, Gabriele Musillo
2013 Computational Linguistics  
This joint model achieves competitive performance on both syntactic and semantic dependency parsing for several languages.  ...  dMetrics Current investigations in data-driven models of parsing have shifted from purely syntactic analysis to richer semantic representations, showing that the successful recovery of the meaning of text  ...  Acknowledgments The authors would particularly like to thank Andrea Gesmundo for his help with the CoNLL-2009 shared task.  ... 
doi:10.1162/coli_a_00158 fatcat:mtvi7qkngjgrhjyyztr4zf5itq

End-to-End Chinese Parsing Exploiting Lexicons [article]

Yuan Zhang, Zhiyang Teng, Yue Zhang
2020 arXiv   pre-print
In particular, our parsing model relies on word-char graph attention networks, which can enrich the character inputs with external word knowledge.  ...  In this paper, we propose an end-to-end Chinese parsing model based on character inputs which jointly learns to output word segmentation, part-of-speech tags and dependency structures.  ...  First, we investigate the effectiveness of word information for the task by considering a novel graph attention network with semantic and structural channels.  ... 
arXiv:2012.04395v1 fatcat:ps3lyosizve2rjrjhv7vff5k3i

CMU: Arc-Factored, Discriminative Semantic Dependency Parsing

Sam Thomson, Brendan O'Connor, Jeffrey Flanigan, David Bamman, Jesse Dodge, Swabha Swayamdipta, Nathan Schneider, Chris Dyer, Noah A. Smith
2014 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)  
We present an arc-factored statistical model for semantic dependency parsing, as defined by the SemEval 2014 Shared Task 8 on Broad-Coverage Semantic Dependency Parsing.  ...  Acknowledgements We are grateful to Manaal Faruqui for his help in word vector experiments, and to reviewers for helpful comments. The research reported in this paper was sponsored by the U.S.  ...  Conclusion and Future Work We found that feature-rich discriminative models perform well at the task of mapping from sentences to semantic dependency parses.  ... 
doi:10.3115/v1/s14-2027 dblp:conf/semeval/ThomsonOFBDSSDS14 fatcat:tacnbyk6tbg2bhttgbefwercaq

Exploiting XPG for Visual Languages Definition, Analysis and Development

G. Costagliola, V. Deufemia, F. Ferrucci, C. Gravino
2003 Electronical Notes in Theoretical Computer Science  
Indeed, it allows us to exploit the well-established theoretical background and techniques developed for string languages in the setting of visual languages.  ...  Moreover, syntax-direct translations can be used to verify properties of visual sentences during a semantic analysis phase.  ...  In particular, the analysis could be effectively performed by representing the information of a collaboration diagram with a It is worth noting that it is possible to define algorithms that exploit the  ... 
doi:10.1016/s1571-0661(05)82631-3 fatcat:fuixek47bbafroptmuwe7quu3a

Semantics-based Graph Approach to Complex Question-Answering

Tomasz Jurczyk, Jinho D. Choi
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop  
There are four kinds of entity relations added to our knowledge graph: syntactic dependencies, semantic role labels, named entities, and coreference links, which can be effectively applied to answer complex  ...  This paper suggests an architectural approach of representing knowledge graph for complex question-answering.  ...  Thanks to years of research on statistical parsing, several tools are already available that provide rich syntactic and semantic structures from texts.  ... 
doi:10.3115/v1/n15-2019 dblp:conf/naacl/JurczykC15 fatcat:wuhuat6wmzbytagrkflars6pya

A Diagram Is Worth A Dozen Images [article]

Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi
2016 arXiv   pre-print
We introduce Diagram Parse Graphs (DPG) as our representation to model the structure of diagrams.  ...  Diagrams are common tools for representing complex concepts, relationships and events, often when it would be difficult to portray the same information with natural images.  ...  We also evaluate our introduced model Dsdp-Net for syntactic parsing of diagrams that forms DPGs and compare it to several baseline approaches.  ... 
arXiv:1603.07396v1 fatcat:zi3nnaos6bcinktmmrxcndqf3q

Peking: Profiling Syntactic Tree Parsing Techniques for Semantic Graph Parsing

Yantao Du, Fan Zhang, Weiwei Sun, Xiaojun Wan
2014 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)  
Using the SemEval-2014 Task 8 data, we profile the syntactic tree parsing techniques for semantic graph parsing.  ...  In particular, we implement different transitionbased and graph-based models, as well as a parser ensembler, and evaluate their effectiveness for semantic dependency parsing.  ...  Transition-Based Models Transition-based models are usually used for dependency tree parsing. For this task, we exploit it for dependency graph parsing.  ... 
doi:10.3115/v1/s14-2080 dblp:conf/semeval/DuZSW14 fatcat:hiwtjhlxjjfxbcwks7dxjiy3wq

Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem [article]

Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu, Sheng Zhong
2020 arXiv   pre-print
In particular, we investigated our model for solving two problems, neural semantic parsing and math word problem.  ...  However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of  ...  For inputs, we consider parsing tree augmented sequences to get structural information.  ... 
arXiv:2004.13781v2 fatcat:vilrnho4c5g43iettvw5ie6blq

Improving Semantic Dependency Parsing with Higher-Order Information Encoded by Graph Neural Networks

Bin Li, Yunlong Fan, Yikemaiti Sataer, Zhiqiang Gao, Yaocheng Gui
2022 Applied Sciences  
Higher-order information brings significant accuracy gains in semantic dependency parsing. However, modeling higher-order information is non-trivial.  ...  Graph neural networks (GNNs) have been demonstrated to be an effective tool for encoding higher-order information in many graph learning tasks.  ...  Acknowledgments: Our code extends this github repository https://github.com/yzhangcs/parser (accessed on 15 October 2021), thanks to it very much.  ... 
doi:10.3390/app12084089 fatcat:nuvfqmsjn5dira4xl2rqsyfxxm
« Previous Showing results 1 — 15 out of 4,145 results