A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Efficient Stacked Dependency Parsing by Forest Reranking
2013
Transactions of the Association for Computational Linguistics
Preserved Fulltext
This paper proposes a discriminative forest reranking algorithm for dependency parsing that can be seen as a form of efficient stacked parsing. ...
Testing on the English Penn Treebank data, forest reranking gave a state-of-the-art unlabeled dependency accuracy of 93.12. ...
This paper proposes an efficient stacked parsing method through discriminative reranking with higher-order graph-based features, which works on the forests output by the first-stage dynamic programming ...
doi:10.1162/tacl_a_00216
fatcat:nmtftcqitzgvbkfuisuazcsviy
Efficient Stacked Dependency Parsing by Forest Reranking
2013
Transactions of the Association for Computational Linguistics
unpublished
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.
This paper proposes a discriminative forest reranking algorithm for dependency parsing that can be seen as a form of efficient stacked parsing. ...
Testing on the English Penn Treebank data, forest reranking gave a state-of-the-art unlabeled dependency accuracy of 93.12. ...
This work was partly 148 supported by Grant-in-Aid for Japan Society for the Promotion of Science (JSPS) Research Fellowship for Young Scientists. ...
fatcat:7iyq4bnifncebpctx2rb72fmqe
A Search-Based Dynamic Reranking Model for Dependency Parsing
2016
Proceedings of the 54th 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 2020; you can also visit the original URL.
The file type is application/pdf.
We propose a novel reranking method to extend a deterministic neural dependency parser. ...
Different to conventional k-best reranking, the proposed model integrates search and learning by utilizing a dynamic action revising process, using the reranking model to guide modification for the base ...
This work was supported by the Natural Science Foundation of China (61472183, 6130158, 61472191), the 863 program via 2015AA015406 and Singapore Ministratry of Education Tier 2 Grant T2MOE201301. ...
doi:10.18653/v1/p16-1132
dblp:conf/acl/ZhouZHZDC16
fatcat:64mlokcsxfhyjhgbkytcha334q
Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
[article]
2016
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.
To remedy this, we introduce a new shift-reduce system whose stack contains merely sentence spans, represented by a bare minimum of LSTM features. ...
Parsing accuracy using efficient greedy transition systems has improved dramatically in recent years thanks to neural networks. ...
This project was supported in part by NSF IIS-1656051, DARPA FA8750-13-2-0041 (DEFT), and a Google Faculty Research Award. ...
arXiv:1612.06475v1
fatcat:vnlv3hencvdhpj6h5ey43g4whe
Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
2016
Proceedings of the 2016 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 2020; you can also visit the original URL.
The file type is application/pdf.
To remedy this, we introduce a new shiftreduce system whose stack contains merely sentence spans, represented by a bare minimum of LSTM features. ...
Parsing accuracy using efficient greedy transition systems has improved dramatically in recent years thanks to neural networks. ...
This project was supported in part by NSF IIS-1656051, DARPA FA8750-13-2-0041 (DEFT), and a Google Faculty Research Award. ...
doi:10.18653/v1/d16-1001
dblp:conf/emnlp/CrossH16
fatcat:zc2w5kuxgvbobp7mt5po3fmzxu
The Inside-Outside Recursive Neural Network model for Dependency Parsing
2014
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
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.
counting, and tends to choose more accurate parses in k-best lists. ...
In addition, reranking with this model achieves state-of-the-art unlabelled attachment scores and unlabelled exact match scores. ...
Reranking k-best lists was introduced by Collins and Koo (2005) and Charniak and Johnson (2005) . Their rerankers are discriminative and for constituent parsing. ...
doi:10.3115/v1/d14-1081
dblp:conf/emnlp/LeZ14
fatcat:yepxgwbv5bhdpm3ankzc7khll4
Shift-reduce Spinal TAG Parsing with Dynamic Programming
2016
Transactions of the Japanese society for artificial intelligence
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.
Unfortunately, the model has the serious drawback of low parsing efficiency since its Eisner-CKY style parsing algorithm needs O(n 4 ) computation time for input length n. ...
The spinal tree adjoining grammar (TAG) parsing model of [Carreras 08] achieves the current state-of-the-art constituent parsing accuracy on the commonly used English Penn Treebank evaluation setting. ...
Charniak & Johnson (2005) [Charniak 05] and Huang (2008) [Huang 08 ] showed that k-best and forest reranking with rich non-local features improves constituent parsing accuracies significantly. ...
doi:10.1527/tjsai.j-f83
fatcat:75z43q3ucffbxcrqizm3wm6xuq
CYK Parsing over Distributed Representations
2020
Algorithms
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.
By showing that CYK can be entirely performed on distributed representations, we open the way to the definition of recurrent layer neural networks that can process general context-free languages. ...
to drive the search in the parsing space, resulting in hybrid architectures using both symbolic and distributed representations. ...
On the other hand, general parsing methods have been developed for ambiguous CFGs that construct compact representations, called parse forests, of all possible parse trees assigned by the underlying grammar ...
doi:10.3390/a13100262
fatcat:wcovlq4ayjg3nfo4j6fud7eer4
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 also show how the comparability of candidates considered by the beam is an important factor in the performance. ...
Stephen Clark was supported by EPSRC grant EP/E035698/1. ...
doi:10.1162/coli_a_00037
fatcat:2n7lttgt4jgahcue6nxc7xg7iq
Dependency Parsing with Transformed Feature
2017
Information
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.
Dependency parsing is an important subtask of natural language processing. ...
Moreover, this problem can be alleviated by reducing the number of the nearest transformed features of a feature. ...
Like some reranking frameworks such as the forest reranking algorithm [20] without needing the K-best output, we employ a fusion decoding to integrate original and transformed features. ...
doi:10.3390/info8010013
fatcat:jn6z7are7rh77khfvjz65oolte
Expected F-Measure Training for Shift-Reduce Parsing with Recurrent Neural Networks
2016
Proceedings of the 2016 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 2016; you can also visit the original URL.
The file type is application/pdf.
We apply the model to CCG parsing, where it improves over a strong greedy RNN baseline, by 1.47% F1, yielding state-of-the-art results for shiftreduce CCG parsing. ...
We present expected F-measure training for shift-reduce parsing with RNNs, which enables the learning of a global parsing model optimized for sentence-level F1. ...
Clark is supported by ERC Starting Grant DisCoTex (306920) and EPSRC grant EP/I037512/1. ...
doi:10.18653/v1/n16-1025
dblp:conf/naacl/XuAC16
fatcat:i5uqhjbihnhnzh5z37riix7va4
Recurrent Neural Network Grammars
[article]
2016
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
We explain efficient inference procedures that allow application to both parsing and language modeling. ...
Experiments show that they provide better parsing in English than any single previously published supervised generative model and better language modeling than state-of-the-art sequential RNNs in English ...
This work was sponsored in part by the Defense ...
arXiv:1602.07776v4
fatcat:6lhz5ectzbhhfovqgepcc44opu
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features
2014
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 2014; you can also visit the original URL.
The file type is application/pdf.
We also present encouraging preliminary results on the use of unsupervised dependency parsing for syntax-based machine translation. ...
In this article, we present a tree-to-tree machine translation system inspired by quasi-synchronous grammar. ...
This research was supported in part by the National Science Foundation through grant IIS-0844507, the U.S. Army Research Laboratory and the U.S. ...
doi:10.1162/coli_a_00175
fatcat:e3hfi5iovvdrrhqbi76h3yrvwq
Recurrent Neural Network Grammars
2016
Proceedings of the 2016 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 2018; you can also visit the original URL.
The file type is application/pdf.
We explain efficient inference procedures that allow application to both parsing and language modeling. ...
Experiments show that they provide better parsing in English than any single previously published supervised generative model and better language modeling than state-of-the-art sequential RNNs in English ...
This work was sponsored in part by the Defense ...
doi:10.18653/v1/n16-1024
dblp:conf/naacl/DyerKBS16
fatcat:v6c3wr3ssfa7hc47wyigk3wur4
Valency-Augmented Dependency Parsing
2018
Proceedings of the 2018 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 2020; you can also visit the original URL.
The file type is application/pdf.
We present a complete, automated, and efficient approach for utilizing valency analysis in making dependency parsing decisions. ...
Finally, we explore the potential of extending valency patterns beyond their traditional domain by confirming their helpfulness in improving PP attachment decisions. 1 ...
TS and LL were supported in part by a Google Focused Research Grant to Cornell University. LL was also supported in part by NSF grant SES-1741441. ...
doi:10.18653/v1/d18-1159
dblp:conf/emnlp/ShiL18
fatcat:p33x22qewzdqrkryzwlarlyebm
« Previous
Showing results 1 — 15 out of 72 results