Generating Factual Text via Entailment Recognition Task
Source abstract
Abstract
Generating diverse and factual text is challenging and is receiving increasing attention. By sampling from the latent space, variational autoencoder-based models have recently enhanced the diversity of generated text. However... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Advanced Text Analysis Techniques · Semantic Web and Ontologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (38)
Show source-provided references
1. Building applied natural language generation systems10.1017/S1351324997001502 ↗
2. Z. W. Ji, N. Lee, and R. Frieske, “Survey of hallucination in natural language generation,” arXiv preprint arXiv:2202.03629, 2022.
3. H. Li, W. J. Yu, and W. T. Ma, “A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions,” arXiv preprint arXiv:2311.05232, 2023.
4. D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” arXiv preprint arXiv:1409.0473, 2014.
5. CatVRNN: Generating category text via multi-task learning10.1016/j.knosys.2022.108491 ↗
6. J. Ji, Q. Wang, K. Toutanova, and Y. Gong, “A nested attention neural hybrid model for grammatical error correction,” arXiv preprint arXiv:1707.02026, 2017.10.18653/v1/P17-1070 ↗
7. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders
8. SeqGAN: Sequence generative adversarial nets with policy gradient
9. Generating sentences from a continuous space
10. FAR-ASS: Fact-aware reinforced abstractive sentence summarization10.1016/j.ipm.2020.102478 ↗
11. Z. Cao, F. Wei, and W. Li, “Faithful to the original: Fact aware neural abstractive summarization,” arXiv preprint arXiv:1711.04434, 2017.10.1609/aaai.v32i1.11912 ↗
12. Ensure the correctness of the summary: Incorporate entailment knowledge into abstractive sentence summarization
13. Ranking generated summaries by correctness: An interesting but challenging application for natural language inference
14. Sohn · Advances in Neural Information Processing Systems · 2015 · 28 · 3483
15. Generative adversarial networks10.1145/3422622 ↗
16. Sentence embeddings in nli with iterative refinement encoders10.1017/S1351324919000202 ↗
17. Bengio · Advances in Neural Information Processing Systems · 2015 · 28 · 1771
18. Long text generation via adversarial training with leaked information
19. SentiGAN: Generating sentimental text via mixture adversarial networks
20. CatGAN: Category-aware generative adversarial networks with hierarchical evolutionary learning for category text generation
21. Toward controlled generation of text
22. Long and diverse text generation with planning-based hierarchical variational model
23. Transformer-based conditioned variational autoencoder for story completion
24. Control, generate, augment: A scalable framework for multi-attribute text generation
25. Assessing the factual accuracy of generated text
26. Multi-reward reinforced summarization with saliency and entailment
27. N. Mundler, J. X. He, and S. Jenko, “Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation,” arXiv preprint arXiv:2305.15852, 2024.
28. D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, 2022.
29. ControlVAE: Controllable variational autoencoder
30. A large annotated corpus for learning natural language inference
31. A broad-coverage challenge corpus for sentence understanding through inference
32. GLUE: A multi-task benchmark and analysis platform for natural language understanding
33. CommonGen: A constrained text generation challenge for generative commonsense reasoning
34. Adversarially regularized autoencoders
35. Lin · Text Summarization Branches Out · 2004 · 74
36. BLEU: A method for automatic evaluation of machine translation
37. Generating diverse translations with sentence codes
38. Y. H. Liu, M. Ott, and N. Goyal, “RoBERTa: A Robustly optimized BERT pretraining approach,” arXiv preprint arXiv:1907.11692, 2019.