Filters








46 Hits in 5.6 sec

A Transition-Based Algorithm for Unrestricted AMR Parsing

David Vilares, Carlos Gómez-Rodríguez
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)  
Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy leftto-right non-projective transition-based parser.  ...  The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself.  ...  We gratefully acknowledge NVIDIA Corporation for the donation of a GTX Titan X GPU.  ... 
doi:10.18653/v1/n18-2023 dblp:conf/naacl/VilaresG18 fatcat:umafm7yhbfcshofm7zuxrfzd4y

A Transition-based Algorithm for Unrestricted AMR Parsing [article]

David Vilares, Carlos Gómez-Rodríguez
2018 arXiv   pre-print
Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser.  ...  The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself.  ...  We gratefully acknowledge NVIDIA Corporation for the donation of a GTX Titan X GPU.  ... 
arXiv:1805.09007v1 fatcat:4f5bsezvlje35owd4lluu5zlgi

An Incremental Parser For Abstract Meaning Representation

Marco Damonte, Shay B. Cohen, Giorgio Satta
2017 Zenodo  
We describe a transition-based parser for AMR that parses sentences left-to-right, in linear time.  ...  Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense  ...  This research was supported by a grant from Bloomberg and by the H2020 project SUMMA, under grant agreement 688139.  ... 
doi:10.5281/zenodo.827292 fatcat:x4q3qiib4vekhnqizr2tu2idnm

An Incremental Parser for Abstract Meaning Representation [article]

Marco Damonte, Shay B. Cohen, Giorgio Satta
2017 arXiv   pre-print
We describe a transition-based parser for AMR that parses sentences left-to-right, in linear time.  ...  Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense  ...  This research was supported by a grant from Bloomberg and by the H2020 project SUMMA, under grant agreement 688139.  ... 
arXiv:1608.06111v5 fatcat:5dc4366yfza6xnuhbawhtuibau

An Incremental Parser for Abstract Meaning Representation

Marco Damonte, Shay B. Cohen, Giorgio Satta
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers  
We describe a transition-based parser for AMR that parses sentences leftto-right, in linear time.  ...  Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense  ...  This research was supported by a grant from Bloomberg and by the H2020 project SUMMA, under grant agreement 688139.  ... 
doi:10.18653/v1/e17-1051 dblp:conf/eacl/SattaCD17 fatcat:kxg3tqnngzad3ogluumujldmri

AMR Parsing with Action-Pointer Transformer [article]

Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Radu Florian
2021 arXiv   pre-print
In this work, we propose a transition-based system that combines hard-attention over sentences with a target-side action pointer mechanism to decouple source tokens from node representations and address  ...  Meaning Representation parsing is a sentence-to-graph prediction task where target nodes are not explicitly aligned to sentence tokens.  ...  Figure 2 shows a partially parsed example of a source sentence, a transition action sequence and the AMR graph for the proposed transitions.  ... 
arXiv:2104.14674v3 fatcat:udst5brlxzbhnc3iyqrbh6j5ri

Multitask Parsing Across Semantic Representations

Daniel Hershcovich, Omri Abend, Ari Rappoport
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks.  ...  In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks.  ...  The first author was supported by a fellowship from the Edmond and Lily Safra Center for Brain Sciences. We thank Roi Reichart, Rotem Dror and the anonymous reviewers for their helpful comments.  ... 
doi:10.18653/v1/p18-1035 dblp:conf/acl/AbendRH18 fatcat:7a3pds2wqfb2pmtwglk2pm2rci

Multitask Parsing Across Semantic Representations [article]

Daniel Hershcovich, Omri Abend, Ari Rappoport
2018 arXiv   pre-print
We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks.  ...  In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks.  ...  The first author was supported by a fellowship from the Edmond and Lily Safra Center for Brain Sciences. We thank Roi Reichart, Rotem Dror and the anonymous reviewers for their helpful comments.  ... 
arXiv:1805.00287v1 fatcat:sl5kdl5qaferzjdcgoitcoubna

Transition-based Semantic Dependency Parsing with Pointer Networks [article]

Daniel Fernández-González, Carlos Gómez-Rodríguez
2020 arXiv   pre-print
Transition-based parsers implemented with Pointer Networks have become the new state of the art in dependency parsing, excelling in producing labelled syntactic trees and outperforming graph-based models  ...  In order to further test the capabilities of these powerful neural networks on a harder NLP problem, we propose a transition system that, thanks to Pointer Networks, can straightforwardly produce labelled  ...  (2019) proposed a transition-based parser that, while it can be applied for SDP, was specifically designed for AMR and UCCA parsing (where graph nodes do not correspond with words and must be generated  ... 
arXiv:2005.13344v2 fatcat:ym73vvlclvcj3egz2amvfy722y

Discontinuous Grammar as a Foreign Language [article]

Daniel Fernández-González, Carlos Gómez-Rodríguez
2021 arXiv   pre-print
To close the gap, we here extend the framework of sequence-to-sequence models for constituent parsing, not only by providing a more powerful neural architecture for improving their performance, but also  ...  While they show a competitive performance, these text-to-parse transducers are still lagging behind classic techniques in terms of accuracy, coverage and speed.  ...  Neural Architecture Based on the approach proposed by (Fernandez Astudillo et al., 2020) for dependency and AMR parsing, we present a Transformer sequence-to-sequence architecture for unrestricted constituent  ... 
arXiv:2110.10431v1 fatcat:rezfppajm5fxxc75jl4yxn4ymm

Contextual Hyperedge Replacement Grammars for Abstract Meaning Representations

Frank Drewes, Anna Jonsson
2017 International Workshop on Tree Adjoining Grammars and Related Formalisms  
We show how contextual hyperedge replacement grammars can be used to generate abstract meaning representations (AMRs), and argue that they are more suitable for this purpose than hyperedge replacement  ...  Contextual hyperedge replacement turns out to have two advantages over plain hyperedge replacement: it can completely cover the language of all AMRs over a given domain of concepts, and at the same time  ...  In fact, as the rank of hyperedges and the number of rules are central parameters in the complexity of membership algorithms for both unrestricted HRGs and CHRGs, it may even pay off to turn to CHRGs since  ... 
dblp:conf/tag/DrewesJ17 fatcat:rz5gw7x64zavjcixj7alepf4we

Uniform Parsing for Hyperedge Replacement Grammars

Henrik Björklund, Frank Drewes, Petter Ericson, Florian Starke
2020 Journal of computer and system sciences (Print)  
In this paper we propose a low-degree polynomialtime algorithm that solves the uniform parsing problem for a restricted type of hyperedgereplacement grammars which we expect to be of interest for practical  ...  Little is known about restrictions under which truly uniform polynomial parsing is possible.  ...  Acknowledgment We are very grateful to the reviewers whose comments have -as we believe -led to a significant improvement of the readability of this paper.  ... 
doi:10.1016/j.jcss.2020.10.002 fatcat:tex62zjn4bffxdyaiypacgibu4

Graph Neural Networks for Natural Language Processing: A Survey [article]

Lingfei Wu, Yu Chen, Kai Shen, Xiaojie Guo, Hanning Gao, Shucheng Li, Jian Pei, Bo Long
2021 arXiv   pre-print
We propose a new taxonomy of GNNs for NLP, whichsystematically organizes existing research of GNNs for NLP along three axes: graph construction,graph representation learning, and graph based encoder-decoder  ...  As a result, thereis a surge of interests in developing new deep learning techniques on graphs for a large numberof NLP tasks.  ...  In-order transition-based constituent parsing. Transactions of the Association for Computational Linguistics, 5:413–424, 2017. doi: 10.1162/tacl a 00070.  ... 
arXiv:2106.06090v1 fatcat:zvkhinpcvzbmje4kjpwjs355qu

Complex Knowledge Base Question Answering: A Survey [article]

Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen
2022 arXiv   pre-print
Next, we present two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods.  ...  Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success.  ...  [55] introduced AMR to help understand questions, the benefits are two-fold: (1) AMR is effective in disambiguating the natural language utterances. (2) AMR parsing module is highly abstract and helps  ... 
arXiv:2108.06688v4 fatcat:xsudc6hwp5bmxhasgwf5jjswt4

History-Aware Question Answering in a Blocks World Dialogue System [article]

Benjamin Kane, Georgiy Platonov, Lenhart K. Schubert
2020 arXiv   pre-print
It is essential for dialogue-based spatial reasoning systems to maintain memory of historical states of the world.  ...  queries, and a constraint solver that derives answers based on 3-D spatial modelling.  ...  An example of a transduction tree being used for parsing a historical question into ULF is shown and described in Figure 3 .  ... 
arXiv:2005.12501v1 fatcat:s4gwgpk37ncjzjm3hp42qdfep4
« Previous Showing results 1 — 15 out of 46 results