Interpretable Image Caption Generation Based on Dependency Syntax

Liu Maofu; Bi Jianqi; Zhou Bingying; Hu Huijun

doi:10.7544/issn1000-1239.202220432

Journal of Computer Research and Development > 2023 > 60(9): 2115-2126. > DOI: 10.7544/issn1000-1239.202220432

Liu Maofu, Bi Jianqi, Zhou Bingying, Hu Huijun. Interpretable Image Caption Generation Based on Dependency Syntax[J]. Journal of Computer Research and Development, 2023, 60(9): 2115-2126. DOI: 10.7544/issn1000-1239.202220432

Citation:

PDF (1687 KB)

Interpretable Image Caption Generation Based on Dependency Syntax

School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065

Funds: This work was supported by the Major Projects of the National Social Science Foundation of China (11&ZD189), the Planning Projects of Guizhou Provincial Science and Technology ([2020]3003), and the Graduate Innovation Fund of Wuhan University of Science and Technology (2022210).

More Information

Author Bio:
Liu Maofu: born in 1977. PhD, professor. Senior member of CCF. His main research interests include natural language processing and intelligent media computing

Bi Jianqi: born in 1998. MSc. His main research interest includes intelligent media computing

Zhou Bingying: born in 2000. Master candidate. Her main research interest includes intelligent media computing

Hu Huijun: born in 1976. PhD, associate professor. Her main research interests include natural language processing and intelligent media computing
Received Date: May 31, 2022
Revised Date: September 26, 2022
Available Online: April 13, 2023

Graphical Abstract

Abstract

Abstract

Although existing image captioning models can detect and represent target objects and visual relationships, they have not focused on the interpretability of image captioning model from the perspective of syntactic relations. To this end, we present an interpretable image caption generation based on dependency syntax triplets modeling (IDSTM) , which leverages the multi-task learning to jointly generate the dependency syntax triplet sequence and image caption. IDSTM firstly obtains the potential dependency syntactic features from the input image through the dependency syntax encoder, and then incorporates these features with the dependency syntactic triplets and textual word embedding vectors into single LSTM (long short-term memory) to generate the dependency syntactic triplet sequence as the prior knowledge. Secondly, the dependency syntactic features are input into captioning encoder to extract the visual object textual features. Finally, hard and soft limitations are adopted to employ the dependency syntactic and relation features into double LSTM for the interpretable image caption generation. With the generation of the task of dependency syntax triplet sequence, IDSTM improves the interpretability of the image captioning model without a significant decrease on the accuracy of the generated captions. In addition, we propose novel metrics B1-DS (BLEU-1-DS), B4-DS (BLEU-4-DS) and M-DS (METEOR-DS) to testify the quality of dependency syntax triplets and to show extensive experimental results on MSCOCO dataset for evaluating the effectiveness and interpretability of IDSTM.
- image caption generation,
- dependency syntax,
- interpretability,
- multi-task learning

FullText(HTML)

References (38)

References

[1]	Karpathy A, Li Feifei. Deep visual-semantic alignments for generating image descriptions[C]//Proc of the 2015 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 3128−3137
[2]	Park C C, Kim B, Kim G. Towards personalized image captioning via multimodal memory networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 41(4): 999−1012
[3]	Vinyals O, Toshev A, Bengio S, et al. Show and tell: A neural image caption generator[C]//Proc of the 2015 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 3156−3164
[4]	李志欣,魏海洋,张灿龙,等. 图像描述生成研究进展[J]. 计算机研究与发展,2021,58(9):1951−1974 Li Zhixin, Wei Haiyang, Zhang Canlong, et al. Research progress on image captioning[J]. Journal of Computer Research and Development, 2021, 58(9): 1951−1974 (in Chinese)
[5]	Ren Shaoqing, He Kaiming, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137−1149 doi: 10.1109/TPAMI.2016.2577031
[6]	李志欣,魏海洋,黄飞成,等. 结合视觉特征和场景语义的图像描述生成[J]. 计算机学报,2020,43(9):1624−1640 Li Zhixin, Wei Haiyang, Huang Feicheng, et al. Combine visual features and scene semantics for image captioning[J]. Chinese Journal of Computers, 2020, 43(9): 1624−1640 (in Chinese)
[7]	Wang Dalin, Beck D, Cohn T. On the role of scene graphs in image captioning[C]// Proc of the Beyond Vision and Language: Integrating Real-world Knowledge (LANTERN). Stroudsburg, PA: ACL, 2019: 29−34
[8]	Shi Zhan, Zhou Xu, Qiu Xipeng, et al. Improving image captioning with better use of caption[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 7454−7464
[9]	Li Xiangyang, Jiang Shuqiang. Know more say less: Image captioning based on scene graphs[J]. IEEE Transactions on Multimedia, 2019, 21(8): 2117−2130 doi: 10.1109/TMM.2019.2896516
[10]	Luo Yunpeng, Ji Jiayi, Sun Xiaoshuai, et al. Dual-level collaborative transformer for image captioning[C]//Proc of the 35th AAAI Conf on Artificial Intelligence. Menlo Park, CA: AAAI, 2021: 2286−2293
[11]	Ji Jiayi, Luo Yunpeng, Sun Xiaoshuai, et al. Improving image captioning by leveraging intra-and inter-layer global representation in transformer network[C]//Proc of the 35th AAAI Conf on Artificial Intelligence. Menlo Park, CA: AAAI, 2021: 1655−1663
[12]	Xu K, Ba J, Kiros R, et al. Show, attend and tell: Neural image caption generation with visual attention[C]//Proc of the 32nd Int Conf on Machine Learning. New York: ACM, 2015: 2048−2057
[13]	Deshpande A, Aneja J, Wang Liwei, et al. Fast, diverse and accurate image captioning guided by part-of-speech[C]//Proc of the 2019 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 10695−10704
[14]	Hou Jingyi, Wu Xinxiao, Zhao Wentian, et al. Joint syntax representation learning and visual cue translation for video captioning[C]//Proc of the 2019 IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 8918−8927
[15]	Wang Yufei, Lin Zhe, Shen Xiaohui, et al. Skeleton key: Image captioning by skeleton-attribute decomposition[C]//Proc of the 2017 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 7272−7281
[16]	Anderson P, He Xiaodong, Buehler C, et al. Bottom-Up and top-down attention for image captioning and visual question answering[C]//Proc of the 2018 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 6077−6086
[17]	Pan Yingwei, Yao Ting, Li Yehao, et al. X-Linear attention networks for image captioning[C]//Proc of the 2020 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 10971−10980
[18]	Lu Jiasen, Xiong Caiming, Parikh D, et al. Knowing when to look: Adaptive attention via a visual sentinel for image captioning[C]//Proc of the 2017 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 375−383
[19]	He Chen, Hu Haifeng. Image captioning with visual-semantic double attention[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2019, 15(1): 1−16
[20]	Ben Huixia, Pan Yingwei, Li Yehao, et al. Unpaired image captioning with semantic-constrained self-learning[J]. IEEE Transactions on Multimedia, 2021, 24(1): 904−916
[21]	Rennie S J, Marcheret E, Mroueh Y, et al. Self-critical sequence training for image captioning[C]//Proc of the 2017 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 7008−7024
[22]	Yang Liang, Hu Haifeng, Xing Songlong, et al. Constrained LSTM and residual attention for image captioning[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2020, 16(3): 1−18
[23]	Wang Cheng, Yang Haojin, Meinel C. Image captioning with deep bidirectional LSTMs and multi-task learning[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2018, 14(2s): 1−20
[24]	成科扬,王宁,师文喜,等. 深度学习可解释性研究进展[J]. 计算机研究与发展,2020,57(6):1208−1217 Cheng Keyang, Wang Ning, Shi Wenxi, et al. Research advances in the interpretability of deep learning[J]. Journal of Computer Research and Development, 2020, 57(6): 1208−1217 (in Chinese)
[25]	Lu Xu, Liu Li, Nie Liqiang, et al. Semantic-driven interpretable deep multi-modal hashing for large-scale multimedia retrieval[J]. IEEE Transactions on Multimedia, 2020, 23(1): 4541−4554
[26]	Tang Zheng, Hahn-Powell G, Surdeanu M. Exploring interpretability in event extraction: Multitask learning of a neural event classifier and an explanation decoder[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop. Stroudsburg, PA: ACL, 2020: 169−175
[27]	Gonen H, Jawahar G, Seddah D, et al. Simple, interpretable and stable method for detecting words with usage change across corpora[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 538−555
[28]	Falenska A, Kuhn J. The (non-)utility of structural features in BiLSTM-based dependency parsers[C]//Proc of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2019: 117−128
[29]	Wang Xing, Tu Zhaopeng, Wang Longyue, et al. Self-attention with structural position representations[C]//Proc of the 2019 Conf on Empirical Methods in Natural Language Processing and the 9th Int Joint Conf on Natural Language Processing (EMNLP-IJCNLP). Stroudsburg, PA: ACL, 2019: 1403−1409
[30]	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 31st Int Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2017: 6000−6010
[31]	Bugliarello E, Okazaki N. Enhancing machine translation with dependency-aware self-attention[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 1618−1627
[32]	Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: Common objects in context[C]//Proc of the 13th European Conf on Computer Vision. Berlin: Springer, 2014: 740−755
[33]	Papineni K, Roukos S, Ward T, et al. BLEU: A method for automatic evaluation of machine translation[C]//Proc of the 40th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2002: 311−318
[34]	Banerjee S, Lavie A. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments[C]//Proc of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization. Stroudsburg, PA: ACL, 2005: 65−72
[35]	Lin C Y. ROUGE: A package for automatic evaluation of summaries[C]//Proc of the ACL Workshop on Text Summarization Branches Out. Stroudsburg, PA: ACL, 2004: 74−81
[36]	Vedantam R, Zitnick C, Parikh D. CIDEr: Consensus-based image description evaluation[C]//Proc of the 2015 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 4566−4575
[37]	Manning C, Surdeanu M, Bauer J, et al. The Stanford CoreNLP natural language processing toolkit[C]//Proc of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Stroudsburg, PA: ACL, 2014: 55−60
[38]	Yao Ting, Pan Yingwei, Li Yehao, et al. Boosting image captioning with attributes[C]//Proc of the 2017 IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 4894−4902

[1]	Zhai Ennan, Cao Jiamin, Qian Kun, Guan Yu. Towards Network Infrastructure Research for the Era of Large Language Models: Challenges, Practices, and Prospects[J]. Journal of Computer Research and Development, 2024, 61(11): 2664-2677. DOI: 10.7544/issn1000-1239.202440576
[2]	Qin Zhen, Zhuang Tianming, Zhu Guosong, Zhou Erqiang, Ding Yi, Geng Ji. Survey of Security Attack and Defense Strategies for Artificial Intelligence Model[J]. Journal of Computer Research and Development, 2024, 61(10): 2627-2648. DOI: 10.7544/issn1000-1239.202440449
[3]	Zhang Mi, Pan Xudong, Yang Min. JADE-DB：A Universal Testing Benchmark for Large Language Model Safety Based on Targeted Mutation[J]. Journal of Computer Research and Development, 2024, 61(5): 1113-1127. DOI: 10.7544/issn1000-1239.202330959
[4]	Zheng Mingyu, Lin Zheng, Liu Zhengxiao, Fu Peng, Wang Weiping. Survey of Textual Backdoor Attack and Defense[J]. Journal of Computer Research and Development, 2024, 61(1): 221-242. DOI: 10.7544/issn1000-1239.202220340
[5]	Zhang Xiaodong, Zhang Chaokun, Zhao Jijun. State-of-the-Art Survey on Edge Intelligence[J]. Journal of Computer Research and Development, 2023, 60(12): 2749-2769. DOI: 10.7544/issn1000-1239.202220192
[6]	Liu Qixu, Liu Jiaxi, Jin Ze, Liu Xinyu, Xiao Juxin, Chen Yanhui, Zhu Hongwen, Tan Yaokang. Survey of Artificial Intelligence Based IoT Malware Detection[J]. Journal of Computer Research and Development, 2023, 60(10): 2234-2254. DOI: 10.7544/issn1000-1239.202330450
[8]	Sang Jitao, Yu Jian. ChatGPT: A Glimpse into AI’s Future[J]. Journal of Computer Research and Development, 2023, 60(6): 1191-1201. DOI: 10.7544/issn1000-1239.202330304
[9]	Chen Yufei, Shen Chao, Wang Qian, Li Qi, Wang Cong, Ji Shouling, Li Kang, Guan Xiaohong. Security and Privacy Risks in Artificial Intelligence Systems[J]. Journal of Computer Research and Development, 2019, 56(10): 2135-2150. DOI: 10.7544/issn1000-1239.2019.20190415
[10]	Rao Dongning, Jiang Zhihua, Jiang Yunfei, Wu Kangheng. Learning Non-Deterministic Action Models for Web Services from WSBPEL Programs[J]. Journal of Computer Research and Development, 2010, 47(3): 445-454.