Filters








479 Hits in 3.0 sec

Automatic Accuracy Prediction for AMR Parsing [article]

Juri Opitz, Anette Frank
2019 arXiv   pre-print
We propose AMR accuracy prediction as the task of predicting several metrics of correctness for an automatically generated AMR parse - in absence of the corresponding gold parse.  ...  Finally, we predict system ranks for submissions from two AMR shared tasks on the basis of their predicted parse accuracy averages.  ...  We are grateful to the NVIDIA corporation for donating the GPU used in this research.  ... 
arXiv:1904.08301v1 fatcat:fjpzo3nz3feungcysatlbn2qfy

Automatic Accuracy Prediction for

Juri Opitz, Anette Frank
2019 Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*  
We propose AMR accuracy prediction as the task of predicting several metrics of correctness for an automatically generated AMR parse -in absence of the corresponding gold parse.  ...  Finally, we predict system ranks for submissions from two AMR shared tasks on the basis of their predicted parse accuracy averages.  ...  We are grateful to the NVIDIA corporation for donating the GPU used in this research.  ... 
doi:10.18653/v1/s19-1024 dblp:conf/starsem/OpitzF19 fatcat:lqkkmot4gvfcfku5fn6y6v3ajq

ICL-HD at SemEval-2016 Task 8: Meaning Representation Parsing - Augmenting AMR Parsing with a Preposition Semantic Role Labeling Neural Network

Lauritz Brandt, David Grimm, Mengfei Zhou, Yannick Versley
2016 Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)  
Despite the usefulness of preposition semantic role labeling information for AMR parsing, it does not have an impact to the parsing F-score of CAMR, but reduces the parsing recall by 1%.  ...  We describe our submission system to the SemEval-2016 Task 8 on Abstract Meaning Representation (AMR) Parsing.  ...  Acknowledgments We would like to thank Sameer Pradhan for providing us with SRL parses of all task data.  ... 
doi:10.18653/v1/s16-1179 dblp:conf/semeval/BrandtGZV16 fatcat:ttbn75lvxfg2rhrf2gcyyv2ajy

Robust Subgraph Generation Improves Abstract Meaning Representation Parsing

Keenon Werling, Gabor Angeli, Christopher D. Manning
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
We improve on the previous state-of-the-art result for AMR parsing, boosting end-to-end performance by 3 F 1 on both the LDC2013E117 and LDC2014T12 datasets.  ...  Node generation, typically done using a simple dictionary lookup, is currently an important limiting factor in AMR parsing.  ...  Acknowledgments We thank the anonymous reviewers for their thoughtful feedback.  ... 
doi:10.3115/v1/p15-1095 dblp:conf/acl/WerlingAM15 fatcat:wv24gabecrdx7lbasrmdyzuvea

Robust Subgraph Generation Improves Abstract Meaning Representation Parsing [article]

Keenon Werling, Gabor Angeli, Christopher Manning
2015 arXiv   pre-print
We improve on the previous state-of-the-art result for AMR parsing, boosting end-to-end performance by 3 F_1 on both the LDC2013E117 and LDC2014T12 datasets.  ...  Node generation, typically done using a simple dictionary lookup, is currently an important limiting factor in AMR parsing.  ...  Acknowledgments We thank the anonymous reviewers for their thoughtful feedback.  ... 
arXiv:1506.03139v1 fatcat:jlzxkg2noneqtcko7w7lqzbm5e

Parsing Indonesian Sentence into Abstract Meaning Representation using Machine Learning Approach [article]

Adylan Roaffa Ilmy, Masayu Leylia Khodra
2021 arXiv   pre-print
Pair prediction uses dependency parsing component to get the edges between the words for the AMR.  ...  However, research on AMR parsing for Indonesian sentence is fairly limited. In this paper, we develop a system that aims to parse an Indonesian sentence using a machine learning approach.  ...  [5] for the model repository that is useful for this study as reference.  ... 
arXiv:2103.03730v1 fatcat:d6qfgto43ffnjg2xzvovgs5doe

Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention

Jan Buys, Phil Blunsom
2017 Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)  
We present an end-to-end neural encoderdecoder AMR parser that extends an attention-based model by predicting the alignment between graph nodes and sentence tokens explicitly with a pointer mechanism.  ...  The approach does not rely on syntactic parses or extensive external resources. Our parser obtained 59% Smatch on the SemEval test set.  ...  We thank the anonymous reviewers for their feedback.  ... 
doi:10.18653/v1/s17-2157 dblp:conf/semeval/BuysB17 fatcat:cnffndwipfdsdcvgeszg5d6oku

Online Back-Parsing for AMR-to-Text Generation [article]

Xuefeng Bai, Linfeng Song, Yue Zhang
2020 arXiv   pre-print
We propose a decoder that back predicts projected AMR graphs on the target sentence during text generation. As the result, our outputs can better preserve the input meaning than standard decoders.  ...  AMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph.  ...  We would like to thank the anonymous reviewers for their insightful comments and Yulong Chen for his fruitful inspiration.  ... 
arXiv:2010.04520v1 fatcat:3gjb7rndizcgpj5vzutj4nisca

Robust Incremental Neural Semantic Graph Parsing [article]

Jan Buys, Phil Blunsom
2017 arXiv   pre-print
Further, the 86.69% Smatch score of our MRS parser is higher than the upper-bound on AMR parsing, making MRS an attractive choice as a semantic representation.  ...  The model architecture uses stack-based embedding features, predicting graphs jointly with unlexicalized predicates and their token alignments.  ...  We thank Stephan Oepen for feedback and help with data preperation, and members of the Oxford NLP group for valuable discussions.  ... 
arXiv:1704.07092v2 fatcat:zbwybywpwngd7mtwjtwyqpbaay

RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy

Guntis Barzdins, Didzis Gosko
2016 Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)  
For AMR parsing task the character-level neural translation attains surprising 7% gain over the carefully optimized word-level neural translation.  ...  The second extension combines a per-sentence smatch with an ensemble method for selecting the best AMR graph among the set of AMR graphs for the same sentence.  ...  AMR parsing), but for e.g.  ... 
doi:10.18653/v1/s16-1176 dblp:conf/semeval/BarzdinsG16 fatcat:vrs4bnjnavc3hhmgcl3iv3h47q

Robust Incremental Neural Semantic Graph Parsing

Jan Buys, Phil Blunsom
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Further, the 86.69% Smatch score of our MRS parser is higher than the upper-bound on AMR parsing, making MRS an attractive choice as a semantic representation.  ...  The model architecture uses stack-based embedding features, predicting graphs jointly with unlexicalized predicates and their token alignments.  ...  We thank Stephan Oepen for feedback and help with data preperation, and members of the Oxford NLP group for valuable discussions.  ... 
doi:10.18653/v1/p17-1112 dblp:conf/acl/BuysB17 fatcat:nawjgia2cnhh3gesf6gzlsrxu4

Multilingual AMR Parsing with Noisy Knowledge Distillation [article]

Deng Cai and Xin Li and Jackie Chun-Sing Ho and Lidong Bing and Wai Lam
2021 arXiv   pre-print
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher.  ...  We constrain our exploration in a strict multilingual setting: there is but one model to parse all different languages including English.  ...  We find that automatic translation can serve as an effective noise generator for multilingual AMR parsing.  ... 
arXiv:2109.15196v2 fatcat:yqmgru4w4fb3hhnxhzi4y6n7my

RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy [article]

Guntis Barzdins, Didzis Gosko
2016 arXiv   pre-print
For AMR parsing task the character-level neural translation attains surprising 7% gain over the carefully optimized word-level neural translation.  ...  The second extension combines a per-sentence smatch with an en-semble method for selecting the best AMR graph among the set of AMR graphs for the same sentence.  ...  AMR parsing), but for e.g.  ... 
arXiv:1604.01278v1 fatcat:mjrialhlanctjjo6kf72qx2uhi

Compositional Semantic Parsing across Graphbanks

Matthias Lindemann, Jonas Groschwitz, Alexander Koller
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Incorporating BERT embeddings and multi-task learning improves the accuracy further, setting new states of the art on DM, PAS, PSD, AMR 2015 and EDS.  ...  We present a compositional neural semantic parser which achieves, for the first time, competitive accuracies across a diverse range of graphbanks.  ...  Acknowledgements We thank Stephan Oepen, Weiwei Sun and Meaghan Fowlie for helpful discussions and the reviewers for their insightful comments. This work was supported by DFG grant KO 2916/2-2.  ... 
doi:10.18653/v1/p19-1450 dblp:conf/acl/LindemannGK19 fatcat:4sy5bcjumvd4rcnsw7ryf2x3xa

Toward Abstractive Summarization Using Semantic Representations [article]

Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh, Noah A. Smith
2018 arXiv   pre-print
The framework is data-driven, trainable, and not specifically designed for a particular domain. Experiments on gold-standard AMR annotations and system parses show promising results.  ...  We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR).  ...  Acknowledgments The authors thank three anonymous reviewers for their insightful input. We are grateful to Nathan Schneider, Kevin Gimpel, Sasha Rush, and the ARK group for valuable discussions.  ... 
arXiv:1805.10399v1 fatcat:g245cr3sd5e6hpkqghmxxypthe
« Previous Showing results 1 — 15 out of 479 results