Review of neural approaches for conditional text generation
Keywords:natural language processing, neural networks, machine learning, conditional text generation, paraphrase generation, grammatical error correction, text simplification
The article is devoted to the review of conditional test generation, one of the most promising fields of natural language processing and artificial intelligence. Specifically, we explore monolingual local sequence transduction tasks: paraphrase generation, grammatical and spelling errors correction, text simplification. To give a better understanding of the considered tasks, we show examples of good rewrites. Then we take a deep look at such key aspects as publicly available datasets with the splits (training, validation, and testing), quality metrics for proper evaluation, and modern solutions based primarily on modern neural networks. For each task, we analyze its main characteristics and how they influence the state-of-the-art models. Eventually, we investigate the most significant shared features for the whole group of tasks in general and for approaches that provide solutions for them.
Pages of the article in the issue: 102 - 107
Language of the article: Ukrainian
BROWN, T.B. et al. (2020) Language Models are Few-Shot Learners. In NeurIPS 2020
KAGGLE. (2017) Quora Duplicate Questions [Online] – Available from: https://www.kaggle.com/aymenmouelhi/quora-duplicate-questions [Accessed: 19th June 2012].
WIETING, J. and GIMPEL, K. (2017) PARANMT-50M: Pushing the Limits of Paraphrastic Embeddings with Millions of Machine Translations. In ACL 2017
LAN, W. et al. (2017) A Continuously Growing Dataset of Sentential Paraphrases. In EMNLP 2017
LIN, T. et al. (2014) Microsoft COCO: Common Objects in Context. In ECCV 2014
PAPINENI, K. et al. (2002) Bleu: a Method for Automatic Evaluation of Machine Translation. In ACL 2002
LIN, C. (2004) ROUGE: A Package for Automatic Evaluation for Summary. In ACL 2004
FU, Y. and FENG, Y. (2019) Paraphrase Generation with Latent Bag of Words. In NeurIPS 2019
DAHLMEIER, D. et al. (2013) Building a Large Annotated Corpus of Learner English: The NUS Corpus of Learner English. In BEA 2013
TAJIRI, T. et al. (2012) Tense and Aspect Error Correction for ESL Learners Using Global Context. In ACL 2012
YANNAKOUDAKIS, H. et al. (2011) A New Dataset and Method for Automatically Grading ESOL Texts. In ACL 2011
BRYANT, C. et al. (2019) The BEA-2019 Shared Task on Grammatical Error Correction. In ACL 2019
DAHLMEIER, D. and NH, T. H. (2012) Better Evaluation for Grammatical Error Correction. In NAACL 2012
BRYANT, C. et al. (2017) Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction. In ACL 2017
OMELIANCHUK, K. et al. (2019) GECToR – Grammatical Error Correction: Tag, Not Rewrite. In BEA 2019
YANG, Z. et al. (2019) XLNet: Generalized Autoregressive Pretraining for Language Understanding. In NeurIPS 2019
ZHANG, X. and LAPATA, M. (2017) Sentence Simplification with Deep Reinforcement Learning. In EMNLP 2017
XU, W. et al. (2015) Problems in Current Text Simplification Research: New Data Can Help. In TACL 2015
XU, W. et al. (2016) Optimizing Statistical Machine Translation for Text Simplification. In TACL 2016 20. KINCAID, J. P. et al. (1975) Derivation Of New Readability Formulas. Institute for Simulation and Training, 56
MARTIN, L. et al. (2020) Multilingual Unsupervised Sentence Simplification
LEWIS, M. et al. (2019) BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL 2020
VASWANI, A. (2017) Attention is all you need. In NIPS 2017
How to Cite
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).