Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWeakly-supervised Multi-task Learning for Multimodal Affect Recognition
449
0
0.0
(
0
)
Added by
Wenliang Dai
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Multimodal affect recognition constitutes an important aspect for enhancing interpersonal relationships in human-computer interaction. However, relevant data is hard to come by and notably costly to annotate, which poses a challenging barrier to build robust multimodal affect recognition systems. Models trained on these relatively small datasets tend to overfit and the improvement gained by using complex state-of-the-art models is marginal compared to simple baselines. Meanwhile, there are many different multimodal affect recognition datasets, though each may be small. In this paper, we propose to leverage these datasets using weakly-supervised multi-task learning to improve the generalization performance on each of them. Specifically, we explore three multimodal affect recognition tasks: 1) emotion recognition; 2) sentiment analysis; and 3) sarcasm recognition. Our experimental results show that multi-tasking can benefit all these tasks, achieving an improvement up to 2.9% accuracy and 3.3% F1-score. Furthermore, our method also helps to improve the stability of model performance. In addition, our analysis suggests that weak supervision can provide a comparable contribution to strong supervision if the tasks are highly correlated.
rate research
Read More
Representation Learning is a significant and challenging task in multimodal learning. Effective modality representations should contain two parts of characteristics: the consistency and the difference. Due to the unified multimodal annotation, existing methods are restricted in capturing differentiated information. However, additional uni-modal annotations are high time- and labor-cost. In this paper, we design a label generation module based on the self-supervised learning strategy to acquire independent unimodal supervisions. Then, joint training the multi-modal and uni-modal tasks to learn the consistency and difference, respectively. Moreover, during the training stage, we design a weight-adjustment strategy to balance the learning progress among different subtasks. That is to guide the subtasks to focus on samples with a larger difference between modality supervisions. Last, we conduct extensive experiments on three public multimodal baseline datasets. The experimental results validate the reliability and stability of auto-generated unimodal supervisions. On MOSI and MOSEI datasets, our method surpasses the current state-of-the-art methods. On the SIMS dataset, our method achieves comparable performance than human-annotated unimodal labels. The full codes are available at https://github.com/thuiar/Self-MM.
In recent years, we have witnessed a surge of interests in learning a suitable distance metric from weakly supervised data. Most existing methods aim to pull all the similar samples closer while push the dissimilar ones as far as possible. However, when some classes of the dataset exhibit multimodal distribution, these goals conflict and thus can hardly be concurrently satisfied. Additionally, to ensure a valid metric, many methods require a repeated eigenvalue decomposition process, which is expensive and numerically unstable. Therefore, how to learn an appropriate distance metric from weakly supervised data remains an open but challenging problem. To address this issue, in this paper, we propose a novel weakly supervised metric learning algorithm, named MultimoDal Aware weakly supervised Metric Learning (MDaML). MDaML partitions the data space into several clusters and allocates the local cluster centers and weight for each sample. Then, combining it with the weighted triplet loss can further enhance the local separability, which encourages the local dissimilar samples to keep a large distance from the local similar samples. Meanwhile, MDaML casts the metric learning problem into an unconstrained optimization on the SPD manifold, which can be efficiently solved by Riemannian Conjugate Gradient Descent (RCGD). Extensive experiments conducted on 13 datasets validate the superiority of the proposed MDaML.
Named Entity Recognition (NER) from social media posts is a challenging task. User generated content that forms the nature of social media, is noisy and contains grammatical and linguistic errors. This noisy content makes it much harder for tasks such as named entity recognition. We propose two novel deep learning approaches utilizing multimodal deep learning and Transformers. Both of our approaches use image features from short social media posts to provide better results on the NER task. On the first approach, we extract image features using InceptionV3 and use fusion to combine textual and image features. This presents more reliable name entity recognition when the images related to the entities are provided by the user. On the second approach, we use image features combined with text and feed it into a BERT like Transformer. The experimental results, namely, the precision, recall and F1 score metrics show the superiority of our work compared to other state-of-the-art NER solutions.
Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation. Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.
General embeddings like word2vec, GloVe and ELMo have shown a lot of success in natural language tasks. The embeddings are typically extracted from models that are built on general tasks such as skip-gram models and natural language generation. In this paper, we extend the work from natural language understanding to multi-modal architectures that use audio, visual and textual information for machine learning tasks. The embeddings in our network are extracted using the encoder of a transformer model trained using multi-task training. We use person identification and automatic speech recognition as the tasks in our embedding generation framework. We tune and evaluate the embeddings on the downstream task of emotion recognition and demonstrate that on the CMU-MOSEI dataset, the embeddings can be used to improve over previous state of the art results.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
