mlsanityData to 14 Oct 2026

Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension

arXiv 1808.08744 ↗First posted 27 Aug 2018cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

We propose a machine reading comprehension model based on the compare-aggregate framework with two-staged attention that achieves state-of-the-art results on the MovieQA question answering dataset. To investigate the limitations of our model as well as the behavioral difference between convolutional and recurrent neural networks, we generate adversarial examples to confuse the model and compare to human performance. Furthermore, we assess the generalizability of our model by analyzing its differences to human inference,

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 1; 2023: 7; 2024: 3.

19 papers.

Sort:

By area:

  1. 2023In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPTcited by 37
  2. 2021Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglotscited by 23
  3. 2021Certified Robustness to Programmable Transformations in LSTMscited by 18
  4. 2023Synthesizing Human Gaze Feedback for Improved NLP Performancecited by 16
  5. 2021On Robustness of Neural Semantic Parserscited by 14
  6. 2022Residue-Based Natural Language Adversarial Attack Detectioncited by 8
  7. 2021Improving the robustness and accuracy of biomedical language models through adversarial trainingcited by 7
  8. 2021Semantic-Preserving Adversarial Text Attackscited by 5
  9. 2021Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directionscited by 4
  10. 2023The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Modelscited by 4
  11. 2021Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classificationcited by 3
  12. 2021Adversarial Machine Learning in Text Analysis and Generationcited by 2
7 more
  1. 2023Translate your gibberish: black-box adversarial attack on machine translation systemscited by 2
  2. 2023A Multilingual Evaluation of NER Robustness to Adversarial Inputscited by 2
  3. 2024TransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation via Solo PPG Signal Capturingcited by 2
  4. 2023Sentiment Perception Adversarial Attacks on Neural Machine Translation Systemscited by 1
  5. 2024Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attackscited by 1
  6. 2023From text to multimodal: a survey of adversarial example generation in question answering systemscited by 0
  7. 2024Towards Robust Extractive Question Answering Models: Rethinking the Training Methodologycited by 0