Multimodal Transformers achieve superior performance in multimodal learning tasks. However, the quadratic complexity of the self-attention mechanism in Transformers limits their deployment in low-resource devices and makes their inference and training computationally expensive. We propose multimodal Sparse Phased Transformer (SPT) to alleviate the problem of self-attention complexity and memory footprint. SPT uses a sampling function to generate a sparse attention matrix and compress a long sequence to a shorter sequence of hidden states. SPT concurrently captures interactions between the hidden states of different modalities at every layer. To further improve the efficiency of our method, we use Layer-wise parameter sharing and Factorized Co-Attention that share parameters between Cross Attention Blocks, with minimal impact on task performance. We evaluate our model with three sentiment analysis datasets and achieve comparable or superior performance compared with the existing methods, with a 90% reduction in the number of parameters. We conclude that (SPT) along with parameter sharing can capture multimodal interactions with reduced model size and improved sample efficiency.
Analysis of client and therapist behavior in counseling sessions can provide helpful insights for assessing the quality of the session and consequently, the client’s behavioral outcome. In this paper, we study the automatic classification of standardized behavior codes (annotations) used for assessment of psychotherapy sessions in Motivational Interviewing (MI). We develop models and examine the classification of client behaviors throughout MI sessions, comparing the performance by models trained on large pretrained embeddings (RoBERTa) versus interpretable and expert-selected features (LIWC). Our best performing model using the pretrained RoBERTa embeddings beats the baseline model, achieving an F1 score of 0.66 in the subject-independent 3-class classification. Through statistical analysis on the classification results, we identify prominent LIWC features that may not have been captured by the model using pretrained embeddings. Although classification using LIWC features underperforms RoBERTa, our findings motivate the future direction of incorporating auxiliary tasks in the classification of MI codes.
Dialogue Act (DA) classification is the task of classifying utterances with respect to the function they serve in a dialogue. Existing approaches to DA classification model utterances without incorporating the turn changes among speakers throughout the dialogue, therefore treating it no different than non-interactive written text. In this paper, we propose to integrate the turn changes in conversations among speakers when modeling DAs. Specifically, we learn conversation-invariant speaker turn embeddings to represent the speaker turns in a conversation; the learned speaker turn embeddings are then merged with the utterance embeddings for the downstream task of DA classification. With this simple yet effective mechanism, our model is able to capture the semantics from the dialogue content while accounting for different speaker turns in a conversation. Validation on three benchmark public datasets demonstrates superior performance of our model.
Offensive and abusive language is a pressing problem on social media platforms. In this work, we propose a method for transforming offensive comments, statements containing profanity or offensive language, into non-offensive ones. We design a Retrieve, Generate and Edit unsupervised style transfer pipeline to redact the offensive comments in a word-restricted manner while maintaining a high level of fluency and preserving the content of the original text. We extensively evaluate our method’s performance and compare it to previous style transfer models using both automatic metrics and human evaluations. Experimental results show that our method outperforms other models on human evaluations and is the only approach that consistently performs well on all automatic evaluation metrics.