A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
A Transition-based Model for Joint Segmentation, POS-tagging and Normalization
2015
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Preserved Fulltext
We propose a transition-based model for joint word segmentation, POS tagging and text normalization. ...
Experimental results show that our joint model can help improve the performance of word segmentation on microblogs, giving an error reduction in segmentation accuracy of 12.02%, compared to the traditional ...
Acknowledgments We thank all reviewers for the insightful comments. ...
doi:10.18653/v1/d15-1211
dblp:conf/emnlp/QianZZRJ15
fatcat:hezuh25mdferpdw3hrbgggb6da
Neural Network-based Chinese Joint Syntactic Analysis
2019
Journal of Natural Language Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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. ...
In such cases, parsing models do not work well because of word segmentation and POS tagging errors. This can be solved by joint models of word segmentation, POS tagging and dependency parsing. ...
,Weiss, D., Coppola, G., and Petrov, S. (2015). "Improved Transition-Based Parsingand Tagging with Neural Networks." ...
doi:10.5715/jnlp.26.231
fatcat:uhdulwaubnhspmipjzhm3erocq
A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing
2020
Transactions of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a graph-based model to integrate Chinese word segmentation and dependency parsing. ...
Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing. ...
Acknowledgments We would like to thank the action editor and the anonymous reviewers for their insightful comments. ...
doi:10.1162/tacl_a_00301
fatcat:x5h42hmpfjftnp2ghzqstixbz4
Uyghur morphological analysis using joint conditional random fields: Based on small scaled corpus
2019
Discrete and Continuous Dynamical Systems. Series S
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
As a fundamental research in the field of natural language processing, the Uyghur morphological analysis is used mainly to determine the part of speech (POS) and segmental morphemes (stem and affix) of ...
In order to increase the morphological analysis efficiency, this paper puts forward a hybrid approach to create a statistical model for Uyghur morphological tagging through a small-scale corpus. ...
The transition model for morphological tagging puts forward in [14] based on the stem and affix dictionaries, which are used to obtain all possible segmentation candidates of each Uyghur word in a training ...
doi:10.3934/dcdss.2019055
fatcat:3p4cc6dukzfhlj4uqupo3q7w5i
Syntactic Processing Using the Generalized Perceptron and Beam Search
2011
Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We apply the framework to word segmentation, joint segmentation and POStagging, dependency parsing, and phrase-structure parsing. ...
We argue that the conceptual and computational simplicity of the framework, together with its language-independent nature, make it a competitive choice for a range of syntactic processing tasks and one ...
Acknowledgments This work was largely carried out while Yue Zhang was a DPhil student at the Oxford University Computing Laboratory, where he was supported by an ORS Scholarship and the Clarendon Fund. ...
doi:10.1162/coli_a_00037
fatcat:2n7lttgt4jgahcue6nxc7xg7iq
A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose a graph-based model to integrate Chinese word segmentation and dependency parsing. ...
Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing. ...
Acknowledgements We would like to thank the action editor and the anonymous reviewers for their insightful comments. ...
arXiv:1904.04697v2
fatcat:d53adfzpg5huzlvz26dflvy3km
Randomized Greedy Inference for Joint Segmentation, POS Tagging and Dependency Parsing
2015
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
In this paper, we introduce a new approach for joint segmentation, POS tagging and dependency parsing. ...
Specifically, we employ a randomized greedy algorithm that jointly predicts segmentations, POS tags and dependency trees. ...
We also thank the MIT NLP group and the ACL reviewers for their comments. ...
doi:10.3115/v1/n15-1005
dblp:conf/naacl/ZhangLBD15
fatcat:oioxj4sel5g47pacmdiijlum7e
Improving accuracy of Part-of-Speech (POS) tagging using hidden markov model and morphological analysis for Myanmar Language
2020
International Journal of Electrical and Computer Engineering (IJECE)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper presented the comparison of separate word segmentation and POS tagging with joint word segmentation and POS tagging. ...
For Myanmar Language, there are also separate word segmentors and POS taggers based on statistical approaches such as Neural Network (NN) and Hidden Markov Models (HMMs). ...
In our experiments, we compare the separate word segmentation and POS tagging using HMM , joint word segmentation and POS tagging using HMM and joint word segmentataion and POS tagging using HMM with morphological ...
doi:10.11591/ijece.v10i2.pp2023-2030
fatcat:gctwsuxfcvbntamylvf2jy4hee
End-to-End Chinese Parsing Exploiting Lexicons
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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. ...
Chinese parsing has traditionally been solved by three pipeline systems including word-segmentation, part-of-speech tagging and dependency parsing modules. ...
Hatori et al. (2012) pioneer research on the joint model of word segmentation, POS tagging, and dependency parsing for Chinese using transition-based methods. ...
arXiv:2012.04395v1
fatcat:ps3lyosizve2rjrjhv7vff5k3i
A Hierarchical LSTM Model for Joint Tasks
[chapter]
2016
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Lots of task-specific joint models are proposed. This paper proposes a Hierarchical Long Short-Term Memory (HLSTM) model and some its variants for modeling two tasks jointly. ...
Previous work has shown that joint modeling of two Natural Language Processing (NLP) tasks are effective for achieving better performances for both tasks. ...
This paper is partially supported by National Natural Science Foundation of China (No 61273365), discipline building plan in 111 base (No.B08004) and Engineering Research Center of Information Networks ...
doi:10.1007/978-3-319-47674-2_27
fatcat:wd4krhmnmrhlpff6zntyvtp73e
Painless Unsupervised Learning with Features
2010
North American Chapter of the Association for Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We apply this technique to part-of-speech induction, grammar induction, word alignment, and word segmentation, incorporating a few linguistically-motivated features into the standard generative model for ...
These feature-enhanced models each outperform their basic counterparts by a substantial margin, and even compete with and surpass more complex state-of-the-art models. ...
Acknowledgements We thank Percy Liang for making his word segmentation code available to us, and the anonymous reviewers for their comments. ...
dblp:conf/naacl/Berg-KirkpatrickBDK10
fatcat:kcuymthvmffd7lwuah6l5losbe
Joint Training and Decoding Using Virtual Nodes for Cascaded Segmentation and Tagging Tasks
2010
Conference on Empirical Methods in Natural Language Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Many sequence labeling tasks in NLP require solving a cascade of segmentation and tagging subtasks, such as Chinese POS tagging, named entity recognition, and so on. ...
In this paper, we present a novel method which integrates graph structures of two subtasks into one using virtual nodes, and performs joint training and decoding in the factorized state space. ...
Acknowledgements The author wishes to thank the anonymous reviewers for their helpful comments. ...
dblp:conf/emnlp/QianZZHW10
fatcat:lxnheqwnlrgrdaoqtoaqmk62u4
Joint PoS Tagging and Stemming for Agglutinative Languages
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present an unsupervised Bayesian model using Hidden Markov Models (HMMs) for joint PoS tagging and stemming for agglutinative languages. ...
Our results show that joint POS tagging and stemming improves PoS tagging scores. We present results for Turkish and Finnish as agglutinative languages and English as a morphologically poor language. ...
Acknowledgments This research is supported by the Scientific and Technological Research Council of Turkey (TUBITAK) with the project number EEEAG-E . ...
arXiv:1705.08942v1
fatcat:hauvrqaoobfgbly32rkw6ukuza
Jointly or Separately: Which is Better for Parsing Heterogeneous Dependencies?
2014
International Conference on Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we study how these correlations influence final dependency parsing performances, by proposing a joint model which can make full use of the correlations between heterogeneous dependencies ...
improved performances for both schemes over the individual models. ...
Acknowledgments We thank Yue Zhang and the anonymous reviewers for their constructive comments, and gratefully acknowledge the support of the National Basic Research Program (973 Program) of China via ...
dblp:conf/coling/ZhangCSL14
fatcat:u34k2encfzfuhof4uz4gotsreu
Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features
2014
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We propose three improvements to address the drawbacks of state-of-the-art transition-based constituent parsers. ...
First, to resolve the error propagation problem of the traditional pipeline approach, we incorporate POS tagging into the syntactic parsing process. ...
All opinions expressed here are those of the authors and do not necessarily reflect the views of DARPA. ...
doi:10.3115/v1/p14-1069
dblp:conf/acl/WangX14
fatcat:5baqxggkojg4bazfhbrtswj73m
« Previous
Showing results 1 — 15 out of 4,634 results