Abstract
Textbook question answering is challenging as it aims to automatically answer various questions on textbook lessons with long text and complex diagrams, requiring reasoning across modalities. In this work, we propose MRHF, a novel framework that incorporates dense passage re-ranking and the mixture-of-experts architecture for TQA. MRHF proposes a novel query augmentation method for diagram questions and then adopts multi-stage dense passage re-ranking with large pretrained retrievers for retrieving paragraph-level contexts. Then it employs a unified question solver to process different types of text questions. Considering the rich blobs and relation knowledge contained in diagrams, we propose to perform multimodal feature fusion over the retrieved context and the heterogeneous diagram features. Furthermore, we introduce the mixture-of-experts architecture to solve the diagram questions to learn from both the rich text context and the complex diagrams and mitigate the possible negative effects between features of the two modalities. We test the framework on the CK12-TQA benchmark dataset, and the results show that MRHF outperforms the state-of-the-art results in all types of questions. The ablation and case study also demonstrates the effectiveness of each component of the framework.
P. Zhu, Z. Wang—Equal Contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Fedus, W., Dean, J., Zoph, B.: A review of sparse expert models in deep learning. arXiv preprint arXiv:2209.01667 (2022)
Gómez-Pérez, J.M., Ortega, R.: ISAAQ-mastering textbook questions with pre-trained transformers and bottom-up and top-down attention. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5469–5479 (2020)
He, J., Fu, X., Long, Z., Wang, S., Liang, C., Lin, H.: Textbook question answering with multi-type question learning and contextualized diagram representation. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12894, pp. 86–98. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86380-7_8
He, K., Chen, X., Xie, S., Li, Y., Dollár, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000–16009 (2022)
Honnibal, M., Montani, I.: spaCy 2: natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing (2017). to appear
Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79–87 (1991)
Jiang, Y., et al.: Improving machine reading comprehension with single-choice decision and transfer learning. arXiv preprint arXiv:2011.03292 (2020)
Jocher, G., et al.: ultralytics/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration. Zenodo, January 2021. https://doi.org/10.5281/zenodo.4418161
Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6(2), 181–214 (1994)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)
Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235–251. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_15
Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? Textbook question answering for multimodal machine comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4999–5007 (2017)
Kim, D., Kim, S., Kwak, N.: Textbook question answering with multi-modal context graph understanding and self-supervised open-set comprehension. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3568–3584 (2019)
Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: RACE: large-scale reading comprehension dataset from examinations. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 785–794 (2017)
Li, J., Su, H., Zhu, J., Wang, S., Zhang, B.: Textbook question answering under instructor guidance with memory networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3655–3663 (2018)
Li, J., Su, H., Zhu, J., Zhang, B.: Essay-anchor attentive multi-modal bilinear pooling for textbook question answering. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2018)
Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Ma, J., Chai, Q., Liu, J., Yin, Q., Wang, P., Zheng, Q.: XTQA: span-level explanations for textbook question answering (2023)
Ma, J., Liu, J., Wang, Y., Li, J., Liu, T.: Relation-aware fine-grained reasoning network for textbook question answering. IEEE Transactions on Neural Networks and Learning Systems (2021)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-Networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, November 2019
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-Networks. arXiv preprint arXiv:1908.10084 (2019)
Riquelme, C., et al.: Scaling vision with sparse mixture of experts. Adv. Neural Inf. Process. Syst. 34, 8583–8595 (2021)
Robertson, S.E., Walker, S.: Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval. In: Croft, B.W., van Rijsbergen, C.J. (eds.) SIGIR ’94, pp. 232–241. Springer, London (1994). https://doi.org/10.1007/978-1-4471-2099-5_24
Rose, S., Engel, D., Cramer, N., Cowley, W.: Automatic keyword extraction from individual documents. Text Min. Appl. Theory 1(1–20), 10–1002 (2010)
Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: MPNet: masked and permuted pre-training for language understanding. Adv. Neural Inf. Process. Syst. 33, 16857–16867 (2020)
Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: MINILM: deep self-attention distillation for task-agnostic compression of pre-trained transformers. Adv. Neural Inf. Process. Syst. 33, 5776–5788 (2020)
Xu, F., et al.: MoCA: incorporating domain pretraining and cross attention for textbook question answering. Pattern Recognit. 140, 109588 (2023)
Zhao, Y., Ni, X., Ding, Y., Ke, Q.: Paragraph-level neural question generation with maxout pointer and gated self-attention networks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3901–3910 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, P., Wang, Z., Okumura, M., Yang, J. (2024). MRHF: Multi-stage Retrieval and Hierarchical Fusion for Textbook Question Answering. In: Rudinac, S., et al. MultiMedia Modeling. MMM 2024. Lecture Notes in Computer Science, vol 14555. Springer, Cham. https://doi.org/10.1007/978-3-031-53308-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-53308-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53307-5
Online ISBN: 978-3-031-53308-2
eBook Packages: Computer ScienceComputer Science (R0)