Filters








354 Hits in 2.7 sec

Multilingual AMR-to-Text Generation [article]

Angela Fan, Claire Gardent
2020 arXiv   pre-print
We leverage advances in cross-lingual embeddings, pretraining, and multilingual models to create multilingual AMR-to-text models that generate in twenty one different languages.  ...  We analyse the ability of our multilingual models to accurately capture morphology and word order using human evaluation, and find that native speakers judge our generations to be fluent.  ...  We gratefully acknowledge the support of the French National Research Agency (Gardent; award ANR-20-CHIA-0003, XNLG "Multilingual, Multi-Source Text Generation").  ... 
arXiv:2011.05443v1 fatcat:qigjt3cqabevnojukorr5itpsi

Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation [article]

Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, Iryna Gurevych
2021 arXiv   pre-print
Recent work on multilingual AMR-to-text generation has exclusively focused on data augmentation strategies that utilize silver AMR.  ...  We find that combining both complementary sources of information further improves multilingual AMR-to-text generation.  ...  Acknowledgments We would like to thank Gözde Gül Sahin, Ji-Ung Lee, Kevin Stowe, Kexin Wang and Nandan Thakur for their feedback on this work. Leonardo F. R.  ... 
arXiv:2109.03808v1 fatcat:7plehgxhuvhftnch5yoqufeuoa

Multilingual AMR-to-Text Generation

Angela Fan, Claire Gardent
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
We leverage advances in cross-lingual embeddings, pretraining, and multilingual models to create multilingual AMR-to-text models that generate in twenty one different languages.  ...  We analyse the ability of our multilingual models to accurately capture morphology and word order using human evaluation, and find that native speakers judge our generations to be fluent. 1 AMR datasets  ...  We gratefully acknowledge the support of the French National Research Agency (Gardent; award ANR-20-CHIA-0003, XNLG "Multilingual, Multi-Source Text Generation").  ... 
doi:10.18653/v1/2020.emnlp-main.231 fatcat:vbhrdsf42neebbj4imqep4rtsy

Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation

Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, Iryna Gurevych
2021 Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing   unpublished
Recent work on multilingual AMR-to-text generation has exclusively focused on data augmentation strategies that utilize silver AMR.  ...  We find that combining both complementary sources of information further improves multilingual AMR-to-text generation.  ...  Acknowledgments We would like to thank Gözde Gül Sahin, Ji-Ung Lee, Kevin Stowe, Kexin Wang and Nandan Thakur for their feedback on this work. Leonardo F. R.  ... 
doi:10.18653/v1/2021.emnlp-main.57 fatcat:fsy5ibu6anajrbpk7yrcsho5oy

RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation

Normunds Gruzitis, Didzis Gosko, Guntis Barzdins
2017 Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)  
We strengthen the interlingual aspect of AMR by applying the multilingual Grammatical Framework (GF) for AMR-to-text generation.  ...  By addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua.  ...  AMR-to-text generation Our approach to text generation from AMR graphs stems from a recent feasibility study (Gruzitis and Barzdins, 2016) on the grammar-based generation of storyline highlights -a list  ... 
doi:10.18653/v1/s17-2159 dblp:conf/semeval/GruzitisGB17 fatcat:6pbmqueomjbyzel7ihmnocirtu

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.  ...  KD has been proved useful in a range of sequence generation tasks such as machine translation (Freitag et al., 2017; Tan et al., 2019) , non-autoregressive text generation (Gu et al., 2017; , and text  ... 
arXiv:2109.15196v2 fatcat:yqmgru4w4fb3hhnxhzi4y6n7my

Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing [article]

Yitao Cai, Zhe Lin, Xiaojun Wan
2021 arXiv   pre-print
In this work, we introduce bilingual input, namely the translated texts as well as non-English texts, in order to enable the model to predict more accurate concepts.  ...  However, they find that concepts in their predicted AMR graphs are less specific. We argue that the misprediction of concepts is due to the high relevance between English tokens and AMR concepts.  ...  ., gold AMR graphs -silver translations) to generate our data for training and validation.  ... 
arXiv:2106.04814v1 fatcat:jppfrhdupnhdfmrlrgqvrile2m

A demo of FORGe: the Pompeu Fabra Open Rule-based Generator

Simon Mille, Leo Wanner
2017 Proceedings of the 10th International Conference on Natural Language Generation  
This demo paper presents the multilingual deep sentence generator developed by the TALN group at Universitat Pompeu Fabra, implemented as a series of rule-based graphtransducers.  ...  Overview of the system In this section, we briefly describe the input to the system and the successive transductions . 1 See this paper for an evaluation of the system in the context of the SemEval AMR-to-text  ...  It is currently being adapted to languages such as Spanish, German French, and Polish, in the context of ontology-to-text generation as part of a dialogue system.  ... 
doi:10.18653/v1/w17-3539 dblp:conf/inlg/MilleW17 fatcat:uytooabzprgnbafy5kff4xs5h4

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures [article]

Jannis Vamvas, Rico Sennrich
2022 arXiv   pre-print
When used for reference-based evaluation of data-to-text generation in 2 tasks and 17 languages, translation-based measures show a relatively high correlation to human judgments.  ...  Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation.  ...  We would like to thank Farhad Nooralahzadeh for helpful feedback, and Angela Fan for making human judgment data available.  ... 
arXiv:2204.13692v1 fatcat:kxj5u56gcjfzlfycqfof7d3ib4

Sentence Object Notation: Multilingual sentence notation based on Wordnet [article]

Abdelkrime Aries, Djamel Eddine Zegour, Walid Khaled Hidouci
2018 arXiv   pre-print
Its benefit is to be used as a medium between different parts of applications like: text summarization, language translation, etc.  ...  This simplifies developing simple automatic generators and creating test banks manually.  ...  Acknowledgement Special thanks to Hisham Omar for his valuable feedback concerning Japanese examples.  ... 
arXiv:1801.00984v2 fatcat:p7num6fo4va7znjekacjzq6kba

Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees

Simon Mille, Bernd Bohnet, Leo Wanner, Anja Belz
2017 Proceedings of the 10th International Conference on Natural Language Generation  
We propose a shared task on multilingual Surface Realization, i.e., on mapping unordered and uninflected universal dependency trees to correctly ordered and inflected sentences in a number of languages  ...  a shared task effort in view of the arrival of Universal Dependencies annotated treebanks for a large number of languages on the one hand, and the increasing dominance of Deep Learning, which proved to  ...  We hope to attract a number of submissions within these application contexts (not only from the generation, but also, for instance, from the parsing community) and deepen the interest in text generation  ... 
doi:10.18653/v1/w17-3517 dblp:conf/inlg/MilleBWB17 fatcat:4yn7wyrhgndrze2pnbutmzdony

POTATO: exPlainable infOrmation exTrAcTion framewOrk [article]

Ádám Kovács, Kinga Gémes, Eszter Iklódi, Gábor Recski
2022 arXiv   pre-print
POTATO handles any type of directed graph and supports parsing text into Abstract Meaning Representations (AMR), Universal Dependencies (UD), and 4lang semantic graphs.  ...  A streamlit-based user interface allows users to build rule systems from graph patterns, provides real-time evaluation based on ground truth data, and suggests rules by ranking graph features using interpretable  ...  system (Damonte and Cohen, 2018) implemented by the amr-eager-multilingual 8 library.  ... 
arXiv:2201.13230v1 fatcat:u33p5omxrnf5niyapu4cfxma4q

Hybrid Natural Language Generation from Lexical Conceptual Structures

Nizar Habash, Bonnie Dorr, David Traum
2003 Machine Translation  
The generation system can also be extended to other languages and this is demonstrated and evaluated for Spanish.  ...  The contributions of this work include: (1) development of a large-scale Hybrid Natural Language Generation system with language-independent components; (2) enhancements to an interlingual representation  ...  The editor would like to thank Paul Bennett for help with the Chinese examples.  ... 
doi:10.1023/b:coat.0000020960.27186.18 fatcat:xzoohd5ytrfmlbhmwur5dpvise

L2F/INESC-ID at SemEval-2017 Tasks 1 and 2: Lexical and semantic features in word and textual similarity

Pedro Fialho, Hugo Patinho Rodrigues, Luísa Coheur, Paulo Quaresma
2017 Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)  
This paper describes our approach to the SemEval-2017 "Semantic Textual Similarity" and "Multilingual Word Similarity" tasks.  ...  These move from lexical to semantic features. In particular, we try to take advantage of the recent Abstract Meaning Representation and SMATCH measure.  ...  The AMR for each sentence in a pair is generated with JAMR 3 , and then supplied to SMATCH, which returns a numeric value between 0 and 1 denoting their similarity.  ... 
doi:10.18653/v1/s17-2032 dblp:conf/semeval/FialhoRCQ17 fatcat:cwr3njfk55dgbeelbgupsv7t74

Generating Text from Anonymised Structures

Emilie Colin, Claire Gardent
2019 Proceedings of the 12th International Conference on Natural Language Generation  
In this paper, we introduce a new parallel dataset of deep meaning representations and French sentences and we present a novel method for MR-to-text generation which seeks to generalise by abstracting  ...  Most current work on natural language generation focuses on generating text that matches a reference using BLEU as evaluation criteria.  ...  Introduction Surface realisation (SR), the ability to generate text from meaning representations (MR), is a key component of data-to-text generation.  ... 
doi:10.18653/v1/w19-8614 dblp:conf/inlg/ColinG19 fatcat:7cx7feflz5g4fc55rooi3npm6a
« Previous Showing results 1 — 15 out of 354 results