CM-BERT: Cross-Modal BERT for Text-Audio Sentiment Analysis
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Multimodal sentiment analysis is an emerging research field that aims to enable machines to recognize, interpret, and express emotion. Through the cross-modal interaction, we can get more comprehensive emotional characteristics of the speaker. Bidirectional Encoder Representations from Transformers (BERT) is an efficient pre-trained language representation model. Fine-tuning it has obtained new state-of-the-art results on eleven natural language processing tasks like question answering and natural language inference. However, most previous works fine-tune BERT only base on text data, how to learn a better representation by introducing the multimodal information is still worth exploring. In this paper, we propose the Cross-Modal BERT (CM-BERT), which relies on the interaction of text and audio modality to fine-tune the pre-trained BERT model. As the core unit of the CM-BERT, masked multimodal attention is designed to dynamically adjust the weight of words by combining the information of text and audio modality. We evaluate our method on the public multimodal sentiment analysis datasets CMU-MOSI and CMU-MOSEI. The experiment results show that it has significantly improved the performance on all the metrics over previous baselines and text-only finetuning of BERT. Besides, we visualize the masked multimodal attention and proves that it can reasonably adjust the weight of words by introducing audio modality information.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
Tensor Fusion Network for Multimodal Sentiment Analysis
Zadeh, A., Chen, M., Poria, S., Cambria, E., & Morency, L.-P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1115 · Cited by 2,102 · cited 1×
“To get better multimodal information representation, Zadeh et al. [32] proposed a tensor fusion network which use the product of multimodal features to represent the multimodal fusion information.”
BackgroundA review of affective computing: From unimodal analysis to multimodal fusion
Poria, S., Cambria, E., Bajpai, R., & Hussain, A. (2017) · Information Fusion · doi:10.1016/j.inffus.2017.02.003 · Cited by 1,644 · cited 1×
“To date, there are mainly two types of fusion strategies: feature fusion and decision fusion [9, 21].”
BackgroundHow to Fine-Tune BERT for Text Classification?
Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-32381-3_16 · Cited by 1,534
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
Bagher Zadeh, A., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1208 · Cited by 1,433 · cited 2×
“To prove the effectiveness of our method, we evaluate it on the public multimodal sentiment analysis datasets CMU-MOSI [35] and CMU-MOSEI [36].”
MethodEfficient Low-rank Multimodal Fusion With Modality-Specific Factors
Liu, Z., Shen, Y., Lakshminarasimhan, V. B., Liang, P. P., Bagher Zadeh, A., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1209 · Cited by 1,170 · cited 2×
“LMF [17] Low-rank Multimodal Fusion (LMF) is a method that leveraging low-rank weight tensors to make multimodal fusion efficient without compromising on performance.”
MethodContext-Dependent Sentiment Analysis in User-Generated Videos
Poria, S., Cambria, E., Hazarika, D., Majumder, N., Zadeh, A., & Morency, L.-P. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1081 · Cited by 939
Multimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal Messages
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.94 · Cited by 852 · cited 7×
“We evaluate the CM-BERT model on the CMU-MOSI dataset, Tabel 1 shows the experiment results.”
MethodInfluentialPham, H., Liang, P. P., Manzini, T., Morency, L.-P., & Póczos, B. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016892 · Cited by 512
Multimodal Language Processing in Human Communication
Holler, J., & Levinson, S. C. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2019.05.006 · Cited by 441 · cited 1×
“To make up for the disadvantage of the single modality, multimodal sentiment analysis as an increasingly extensive field of affective computing has attracted widespread attention [12].”
BackgroundMultimodal sentiment analysis with word-level fusion and reinforcement learning
Chen, M., Wang, S., Liang, P. P., Baltrušaitis, T., Zadeh, A., & Morency, L.-P. (2017) · Proceedings of the 19th ACM International Conference on Multimodal Interaction · doi:10.1145/3136755.3136801 · Cited by 334 · cited 1×
“The interaction between text and audio modality can provide more comprehensive information and capture more emotional characteristics [3].”
BackgroundMultimodal Language Analysis with Recurrent Multistage Fusion
Liang, P. P., Liu, Z., Bagher Zadeh, A., & Morency, L.-P. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1014 · Cited by 230
Cited by
Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis
Mai, S., Zeng, Y., Zheng, S., & Hu, H. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3172360 · Cited by 277
Mai, S., Zeng, Y., & Hu, H. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3171679 · Cited by 182
“Cross-Modal BERT (CM-BERT) [37] relies on the interaction of text and audio modality to fine-tune the pretrained BERT model, where a masked multimodal attention is designed to dynamically adjust the weight of words by combining the combination of text and audio modality.”
BackgroundLiu, R., Zuo, H., Lian, Z., Schuller, B. W., & Li, H. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3378570 · Cited by 96
Bimodal fusion network with multi-head attention for multimodal sentiment analysis
Zhang, R., Xue, C., Qi, Q., Lin, L., Zhang, J., & Zhang, L. (2023) · Applied Sciences · doi:10.3390/app13031915 · Cited by 11
Metadata
- Authors
- Yang, K., Xu, H., & Gao, K.
- Venue
- Proceedings of the 28th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2020-10-12
- Pages
- 521-528
- OpenAlex
- W3093400813
- Cited by
- 129
- References
- 14
- FWCI
- 6.25
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.