Natural Language Generation: Recently Learned Lessons, Directions for Semantic Representation-based Approaches, and the Case of Brazilian Portuguese Language

This paper presents a more recent literature review on Natural Language Generation. In particular, we highlight the efforts for Brazilian Portuguese in order to show the available resources and the existent approaches for this language. We also focus on the approaches for generation from semantic representations (emphasizing the Abstract Meaning Representation formalism) as well as their advantages and limitations, including possible future directions.

[1]  Verena Rieser,et al.  The E2E Dataset: New Challenges For End-to-End Generation , 2017, SIGDIAL Conference.

[2]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[3]  Iryna Gurevych,et al.  BinLin: A Simple Method of Dependency Tree Linearization , 2018 .

[4]  Ivandré Paraboni,et al.  Highly-Inflected Language Generation Using Factored Language Models , 2011, CICLing.

[5]  Sandra M. Aluísio,et al.  Um repositório de verbos para a anotação de papéis semânticos disponível na web (A Verb Repository for Semantic Role Labeling Available in the Web) [in Portuguese] , 2013, STIL.

[6]  Mariana L. Neves,et al.  RDF2PT: Generating Brazilian Portuguese Texts from RDF Data , 2018, LREC.

[7]  Yue Zhang,et al.  AMR-to-text generation as a Traveling Salesman Problem , 2016, EMNLP.

[8]  Henry Elder,et al.  Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models , 2018, ArXiv.

[9]  Emiel Krahmer,et al.  Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation , 2017, INLG.

[10]  Ivandré Paraboni,et al.  Text Generation for Brazilian Portuguese: the Surface Realization Task , 2010, NAACL.

[11]  Anja Belz,et al.  The First Surface Realisation Shared Task: Overview and Evaluation Results , 2011, ENLG.

[12]  Guntis Barzdins,et al.  RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation , 2017, SemEval@ACL.

[13]  Kevin Knight,et al.  Generating English from Abstract Meaning Representations , 2016, INLG.

[14]  Ivandré Paraboni,et al.  Improved Text Generation Using N-gram Statistics , 2010, IBERAMIA.

[15]  Emiel Krahmer,et al.  Graph-Based Generation of Referring Expressions , 2003, CL.

[16]  Iryna Gurevych,et al.  E2E NLG Challenge: Neural Models vs. Templates , 2018, INLG.

[17]  Ivandré Paraboni,et al.  Statistical Surface Realisation of Portuguese Referring Expressions , 2008, GoTAL.

[18]  Andreas Vlachos,et al.  Sheffield at SemEval-2017 Task 9: Transition-based language generation from AMR , 2017, SemEval@ACL.

[19]  Thiago A. S. Pardo,et al.  Towards AMR-BR: A SemBank for Brazilian Portuguese Language , 2018, LREC.

[20]  Sandra M. Aluísio,et al.  Automatic Generation of a Lexical Resource to support Semantic Role Labeling in Portuguese , 2015, *SEMEVAL.

[21]  Gholamreza Haffari,et al.  Graph-to-Sequence Learning using Gated Graph Neural Networks , 2018, ACL.

[22]  Leo Wanner,et al.  The First Multilingual Surface Realisation Shared Task (SR’18): Overview and Evaluation Results , 2018 .

[23]  Ivandré Paraboni,et al.  From Semantic Properties to Surface Text: the Generation of Domain Object Descriptions , 2010, Inteligencia Artif..

[24]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[25]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[26]  Albert Gatt,et al.  SimpleNLG: A Realisation Engine for Practical Applications , 2009, ENLG.

[27]  Nathan Hartmann,et al.  Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks , 2017, STIL.

[28]  Thiago Alexandre Salgueiro Pardo,et al.  NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models , 2018 .

[29]  Ivandré Paraboni,et al.  Portuguese text generation using factored language models , 2012, Journal of the Brazilian Computer Society.

[30]  Shashi Narayan,et al.  Creating Training Corpora for NLG Micro-Planners , 2017, ACL.

[31]  Yejin Choi,et al.  Neural AMR: Sequence-to-Sequence Models for Parsing and Generation , 2017, ACL.

[32]  Jaime G. Carbonell,et al.  Generation from Abstract Meaning Representation using Tree Transducers , 2016, NAACL.

[33]  Xiao Li,et al.  Statistical NLG for Generating the Content and Form of Referring Expressions , 2018, INLG.

[34]  Guillaume Lample,et al.  Phrase-Based & Neural Unsupervised Machine Translation , 2018, EMNLP.

[35]  Joaquim Sousa Pinto,et al.  Natural Language Generation in the context of Multimodal Interaction in Portuguese , 2012 .

[36]  Johan Bos,et al.  Squib: Expressive Power of Abstract Meaning Representations , 2016, CL.

[37]  Yue Zhang,et al.  A Graph-to-Sequence Model for AMR-to-Text Generation , 2018, ACL.

[38]  Guillaume Lample,et al.  Unsupervised Machine Translation Using Monolingual Corpora Only , 2017, ICLR.

[39]  Markus Freitag,et al.  Unsupervised Natural Language Generation with Denoising Autoencoders , 2018, EMNLP.

[40]  Antonio Teixeira,et al.  Towards a hybrid NLG system for Data2Text in Portuguese , 2015, 2015 10th Iberian Conference on Information Systems and Technologies (CISTI).

[41]  Ivandré Paraboni,et al.  Um Sistema de Realização Superficial para Geração de Textos em Português , 2013, RITA.

[42]  Jonathan May,et al.  SemEval-2017 Task 9: Abstract Meaning Representation Parsing and Generation , 2017, *SEMEVAL.

[43]  Yue Zhang,et al.  AMR-to-text Generation with Synchronous Node Replacement Grammar , 2017, ACL.

[44]  Roberto Carlini,et al.  FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers , 2017, SemEval@ACL.

[45]  Rodrigo de Oliveira,et al.  Adapting SimpleNLG for Brazilian Portuguese realisation , 2014, INLG.

[46]  Robert Weißgraeber,et al.  AX Semantics’ Submission to the Surface Realization Shared Task 2018 , 2018 .