mlsanityData to 7 Oct 2026

Controlling Text Edition by Changing Answers of Specific Questions

arXiv 2105.11018 ↗First posted 23 May 2021cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce the new task of controllable text edition, in which we take as input a long text, a question, and a target answer, and the output is a minimally modified text, so that it fits the target answer. This task is very important in many situations, such as changing some conditions, consequences, or properties in a legal document, or changing some key information of an event in a news text. This is very challenging, as it is hard to obtain a parallel corpus for training, and we need to first find all text positions that should be changed and then decide how to change them. We constructed the new dataset WikiBioCTE for this task based on the existing dataset WikiBio (originally created for table-to-text generation). We use WikiBioCTE for training, and manually labeled a test set for testing. We also propose novel evaluation metrics and a novel method for solving the new task. Experimental results on the test set show that our proposed method is a good fit for this novel NLP task.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 23 May 2021.

Builds on

33 of 49 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  4. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  5. 2015Teaching Machines to Read and Comprehendcited by 1,039
  6. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  7. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 851
  8. 2018Disentangling by Factorisingcited by 614
  9. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  10. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  11. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  12. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
21 more
  1. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  2. 2020Enabling Language Models to Fill in the Blankscited by 121
  3. 2018Invariant Representations without Adversarial Trainingcited by 111
  4. 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 93
  5. 2018MaskGAN: Better Text Generation via Filling in the______cited by 89
  6. 2017Generating Sentences by Editing Prototypescited by 88
  7. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  8. 2017Table-to-text Generation by Structure-aware Seq2seq Learningcited by 54
  9. 2018Response Generation by Context-aware Prototype Editingcited by 40
  10. 2020A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasetscited by 40
  11. 2019Unsupervised Paraphrasing by Simulated Annealingcited by 37
  12. 2018Neural Machine Translation Decoding with Terminology Constraintscited by 36
  13. 2018Learning to Represent Editscited by 34
  14. 2019Text Infillingcited by 32
  15. 2018WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discoursecited by 26
  16. 2020Learning from the Best: Rationalizing Prediction by Adversarial Information Calibrationcited by 25
  17. 2017Order-Planning Neural Text Generation From Structured Datacited by 20
  18. 2018Adversarial Decomposition of Text Representationcited by 18
  19. 2020Copy that! Editing Sequences by Copying Spanscited by 13
  20. 2019Independent Subspace Analysis for Unsupervised Learning of Disentangled Representationscited by 8
  21. 2020Multi-type Disentanglement without Adversarial Trainingcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 4.

6 papers.

  1. 2021Tailor: Generating and Perturbing Text with Semantic Controlscited by 67
  2. 2022The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applicationscited by 32
  3. 2024ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddingscited by 31
  4. 2024A Survey on Natural Language Counterfactual Generationcited by 21
  5. 2024Harnessing the Plug-and-Play Controller by Promptingcited by 4
  6. 2024RORA: Robust Free-Text Rationale Evaluationcited by 4