Filters








1,404 Hits in 5.4 sec

Neural Joint Model for Transition-based Chinese Syntactic Analysis

Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing.  ...  Our models are the first neural approaches for fully joint Chinese analysis that is known to prevent the error propagation problem of pipeline models.  ...  In neural joint models, Zheng et al. (2013) propose a neural network-based Chinese word segmentation model based on tag inferences. They extend their models for joint segmentation and POS tagging.  ... 
doi:10.18653/v1/p17-1111 dblp:conf/acl/KuritaKK17 fatcat:vnyljg7pozalzjjwr7phvqicge

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

Meishan Zhang
2020 arXiv   pre-print
Constituent parsing is majorly targeted to syntactic analysis, and dependency parsing can handle both syntactic and semantic analysis.  ...  Syntactic and semantic parsing has been investigated for decades, which is one primary topic in the natural language processing community. This article aims for a brief survey on this topic.  ...  Swayamdipta et al. (2016) [120] present a transition-based stack-LSTM model for joint syntactic and semantic dependencies, where their transition system is largely followed (Henderson et al., 2013)  ... 
arXiv:2006.11056v1 fatcat:pd22rciuxzdc5kvghaapjjyg3u

Neural Network-based Chinese Joint Syntactic Analysis

Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi
2019 Journal of Natural Language Processing  
In this study, we propose a neural network-based joint word-segmentation, POS tagging and dependency parsing model in addition to a joint word-segmentation and POS tagging model.  ...  When these parsing models are applied to Chinese sentences, they are used in a pipeline model with word segmentation and POS tagging models.  ...  "Globally Normalized Transition-Based Neural Networks." In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2442-2452.  ... 
doi:10.5715/jnlp.26.231 fatcat:uhdulwaubnhspmipjzhm3erocq

Joint POS Tagging and Dependency Parsing with Transition-based Neural Networks [article]

Liner Yang, Meishan Zhang, Yang Liu, Nan Yu, Maosong Sun, Guohong Fu
2017 arXiv   pre-print
In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks.  ...  Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts.  ...  In this paper, we propose an approach to joint POS tagging and dependency parsing with neural networks by extending from a transition-based dependency parsing model.  ... 
arXiv:1704.07616v1 fatcat:lanhuh3e5jeyholup5mowvpcxy

Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs [article]

Swabha Swayamdipta and Miguel Ballesteros and Chris Dyer and Noah A. Smith
2018 arXiv   pre-print
We present a transition-based parser that jointly produces syntactic and semantic dependencies. It learns a representation of the entire algorithm state, using stack long short-term memories.  ...  On the CoNLL 2008--9 English shared tasks, we obtain the best published parsing performance among models that jointly learn syntax and semantics.  ...  Acknowledgments The authors thank Sam Thomson, Lingpeng Kong, Mark Yatskar, Eunsol Choi, George Mulcaire, and Luheng He, as well as the anonymous reviewers, for many useful comments.  ... 
arXiv:1606.08954v2 fatcat:h6zom7mmfvblleeawekik6o2iu

Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs

Swabha Swayamdipta, Miguel Ballesteros, Chris Dyer, Noah A. Smith
2016 Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning  
We present a transition-based parser that jointly produces syntactic and semantic dependencies. It learns a representation of the entire algorithm state, using stack long short-term memories.  ...  On the CoNLL 2008-9 English shared tasks, we obtain the best published parsing performance among models that jointly learn syntax and semantics.  ...  Acknowledgments The authors thank Sam Thomson, Lingpeng Kong, Mark Yatskar, Eunsol Choi, George Mulcaire, and Luheng He, as well as the anonymous reviewers, for many useful comments.  ... 
doi:10.18653/v1/k16-1019 dblp:conf/conll/SwayamdiptaBDS16 fatcat:cii3counvfaj3grs3ohq2um76e

Recurrent Neural Network Grammars

Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
and Chinese.  ...  We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure.  ...  Acknowledgments We thank Brendan O'Connor, Swabha Swayamdipta, and Brian Roark for feedback on drafts of this paper, and Jan Buys, Phil Blunsom, and Yue Zhang for help with data preparation.  ... 
doi:10.18653/v1/n16-1024 dblp:conf/naacl/DyerKBS16 fatcat:v6c3wr3ssfa7hc47wyigk3wur4

Recurrent Neural Network Grammars [article]

Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith
2016 arXiv   pre-print
and Chinese.  ...  We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure.  ...  Acknowledgments We thank Brendan O'Connor, Swabha Swayamdipta, and Brian Roark for feedback on drafts of this paper, and Jan Buys, Phil Blunsom, and Yue Zhang for help with data preparation.  ... 
arXiv:1602.07776v4 fatcat:6lhz5ectzbhhfovqgepcc44opu

Semantic Role Labeling as Syntactic Dependency Parsing [article]

Tianze Shi, Igor Malioutov, Ozan İrsoy
2020 arXiv   pre-print
Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for over 98% of the SRL annotations for both English and Chinese data.  ...  We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing.  ...  Tsai for discussion and comments.  ... 
arXiv:2010.11170v1 fatcat:qolkf4y7xze2pis6pzrxanbhlq

Pre- and In-Parsing Models for Neural Empty Category Detection

Yufei Chen, Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Motivated by the positive impact of empty categories on syntactic parsing, we study neural models for pre-and in-parsing detection of empty categories, which has not previously been investigated.  ...  Our neural ECD models outperform the prior state-of-the-art by significant margins.  ...  We thank the anonymous reviewers for their helpful comments. Weiwei Sun is the corresponding author.  ... 
doi:10.18653/v1/p18-1250 dblp:conf/acl/SunWCZ18 fatcat:riydix7nevbovdbo5sczlhotbe

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

Yuan Zhang, Zhiyang Teng, Yue Zhang
2020 arXiv   pre-print
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.  ...  Experiments on three Chinese parsing benchmark datasets show the effectiveness of our models, achieving the state-of-the-art results on end-to-end Chinese parsing.  ...  Kurita et al. (2017) first investigate transition-based models for joint Chinese lexical and syntactic analysis with neural models.  ... 
arXiv:2012.04395v1 fatcat:ps3lyosizve2rjrjhv7vff5k3i

EmergEventMine: End-to-End Chinese Emergency Event Extraction Using a Deep Adversarial Network

Jianzhuo Yan, Lihong Chen, Yongchuan Yu, Hongxia Xu, Qingcai Gao, Kunpeng Cao, Jianhui Chen
2022 ISPRS International Journal of Geo-Information  
the event extraction with four subtasks as a two-stage task based on the goals of subtasks, and then develops a lightweight heterogeneous joint model based on deep neural networks for realizing end-to-end  ...  Moreover, adversarial training is introduced into the joint model to alleviate the overfitting of the model on the small-scale labelled corpora.  ...  Compared with existing professional event extraction joint models, this model is a lightweight model, which does not depend on external syntactic analysis tools and has a simpler network structure for  ... 
doi:10.3390/ijgi11060345 doaj:6e7db2e6baa54d548dbac6eff32a2abf fatcat:axatcoloxvd63h3cbja2fnyonm

Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing? [article]

Houquan Zhou, Yu Zhang, Zhenghua Li, Min Zhang
2020 arXiv   pre-print
In contrast, recent studies suggest that POS tagging becomes much less important or even useless for neural parsing, especially when using character-based word representations.  ...  But quite a few works focus on joint tagging and parsing models to avoid error propagation.  ...  In the pre-DL era, researchers propose joint tagging and parsing models under both graph-based and transition-based parsing architectures [9, 18] .  ... 
arXiv:2003.03204v2 fatcat:bykuma6mcvfuhajavzdkluev4e

Segmenting Chinese Microtext: Joint Informal-Word Detection and Segmentation with Neural Networks

Meishan Zhang, Guohong Fu, Nan Yu
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
word detection can be helpful for microtext processing.In this work, we investigate it under the neural setting, by proposing a joint segmentation model that integrates the detection of informal words  ...  simultaneously.In addition, we generate training corpus for the joint model by using existing corpus automatically.Experimental results show that the proposed model is highly effective for segmentation  ...  Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2017/591 dblp:conf/ijcai/ZhangFY17 fatcat:ylgslg5q6fbhvnnktutkd7hkum

A transition-based neural framework for Chinese information extraction

Wenzhi Huang, Junchi Zhang, Donghong Ji, Jie Zhang
2020 PLoS ONE  
To address these two challenges, we propose a novel transition-based model that jointly performs entity recognition, relation extraction and event detection as a single task.  ...  Results on standard ACE benchmarks show the benefits of the proposed joint model and lattice network, which gives the best result in the literature.  ...  Acknowledgments We would like to thank the anonymous reviewers for their many valuable comments and suggestions.  ... 
doi:10.1371/journal.pone.0235796 pmid:32667950 fatcat:4wbiyaiyprerfayavgvrlgmdya
« Previous Showing results 1 — 15 out of 1,404 results