Gabriel Murray

Raymond Li, Ruixin Yang, Wen Xiao et al. · gatech

While transformer-based models have achieved state-of-the-art results in a variety of classification and generation tasks, their black-box nature makes them challenging for interpretability. In this work, we present a novel visual analytical framework to support the analysis of transformer-based generative networks. In contrast to previous work, which has mainly focused on encoder-based models, our framework is one of the first dedicated to supporting the analysis of transformer-based encoder-decoder models and decoder-only models for generative and classification tasks. Hence, we offer an intuitive overview that allows the user to explore different facets of the model through interactive visualization. To demonstrate the feasibility and usefulness of our framework, we present three detailed case studies based on real-world NLP research problems.

Raymond Li, Gabriel Murray, Giuseppe Carenini

In this work, we propose a method that combines two popular research areas by injecting linguistic structures into pre-trained language models in the parameter-efficient fine-tuning (PEFT) setting. In our approach, parallel adapter modules encoding different linguistic structures are combined using a novel Mixture-of-Linguistic-Experts architecture, where Gumbel-Softmax gates are used to determine the importance of these modules at each layer of the model. To reduce the number of parameters, we first train the model for a fixed small number of steps before pruning the experts based on their importance scores. Our experiment results with three different pre-trained models show that our approach can outperform state-of-the-art PEFT methods with a comparable number of parameters. In addition, we provide additional analysis to examine the experts selected by each model at each layer to provide insights for future studies.

Raymond Li, Amirhossein Abaskohi, Chuyuan Li et al.

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to construct semantically-grounded soft label targets using Language Models (LMs) by projecting the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary to obtain contextually enriched supervision signals. By training the topic models to reconstruct the soft labels using the LM hidden states, our method produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Experiments on three datasets show that our method achieves substantial improvements in topic coherence, purity over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications.

Raymond Li, Felipe González-Pizarro, Linzi Xing et al.

The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between topic words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining a high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.

Raymond Li, Wen Xiao, Linzi Xing et al.

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers propose new attention augmentation methods to make transformers more accurate, efficient and interpretable. In this paper, we combine these two lines of research in a human-in-the-loop pipeline to first discover important task-specific attention patterns. Then those patterns are injected, not only to smaller models, but also to the original model. The benefits of our pipeline and discovered patterns are demonstrated in two case studies with extractive summarization and topic segmentation. After discovering interpretable patterns in BERT-based models fine-tuned for the two downstream tasks, experiments indicate that when we inject the patterns into attention heads, the models show considerable improvements in accuracy and efficiency.

Uliyana Kubasova, Gabriel Murray, McKenzie Braley

This work analyzes the efficacy of verbal and nonverbal features of group conversation for the task of automatic prediction of group task performance. We describe a new publicly available survival task dataset that was collected and annotated to facilitate this prediction task. In these experiments, the new dataset is merged with an existing survival task dataset, allowing us to compare feature sets on a much larger amount of data than has been used in recent related work. This work is also distinct from related research on social signal processing (SSP) in that we compare verbal and nonverbal features, whereas SSP is almost exclusively concerned with nonverbal aspects of social interaction. A key finding is that nonverbal features from the speech signal are extremely effective for this task, even on their own. However, the most effective individual features are verbal features, and we highlight the most important ones.

Gabriel Murray

We present a position paper advocating the notion that Stoic philosophy and ethics can inform the development of ethical A.I. systems. This is in sharp contrast to most work on building ethical A.I., which has focused on Utilitarian or Deontological ethical theories. We relate ethical A.I. to several core Stoic notions, including the dichotomy of control, the four cardinal virtues, the ideal Sage, Stoic practices, and Stoic perspectives on emotion or affect. More generally, we put forward an ethical view of A.I. that focuses more on internal states of the artificial agent rather than on external actions of the agent. We provide examples relating to near-term A.I. systems as well as hypothetical superintelligent agents.