Current research in machine learning and artificial intelligence is largely centered on modeling and performance evaluation, less so on data collection. However, recent research demonstrated that limitations and biases in data may negatively impact trustworthiness and reliability. These aspects are particularly impactful on sensitive domains such as mental health and neurological disorders, where speech data are used to develop AI applications aimed at improving the health of patients and supporting healthcare providers. In this paper, we chart the landscape of available speech datasets for this domain, to highlight possible pitfalls and opportunities for improvement and promote fairness and diversity. We present a comprehensive list of desiderata for building speech datasets for mental health and neurological disorders and distill it into a checklist focused on ethical concerns to foster more responsible research.
In this paper, we present TWOLAR: a two-stage pipeline for passage reranking based on the distillation of knowledge from Large Language Models (LLM). TWOLAR introduces a new scoring strategy and a distillation process consisting in the creation of a novel and diverse training dataset. The dataset consists of 20K queries, each associated with a set of documents retrieved via four distinct retrieval methods to ensure diversity, and then reranked by exploiting the zero-shot reranking capabilities of an LLM. Our ablation studies demonstrate the contribution of each new component we introduced. Our experimental results show that TWOLAR significantly enhances the document reranking ability of the underlying model, matching and in some cases even outperforming state-of-the-art models with three orders of magnitude more parameters on the TREC-DL test sets and the zero-shot evaluation benchmark BEIR. To facilitate future work we release our data set, finetuned models, and code.
Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.
Transformers changed modern NLP in many ways. However, they can hardly exploit domain knowledge, and like other blackbox models, they lack interpretability. Unfortunately, structured knowledge injection, in the long run, risks to suffer from a knowledge acquisition bottleneck. We thus propose a memory enhancement of transformer models that makes use of unstructured domain knowledge expressed in plain natural language. An experimental evaluation conducted on two challenging NLP tasks demonstrates that our approach yields better performance and model interpretability than baseline transformer-based architectures.
We propose a novel architecture for Graph Neural Networks that is inspired by the idea behind Tree Kernels of measuring similarity between trees by taking into account their common substructures, named fragments. By imposing a series of regularization constraints to the learning problem, we exploit a pooling mechanism that incorporates such notion of fragments within the node soft assignment function that produces the embeddings. We present an extensive experimental evaluation on a collection of sentence classification tasks conducted on several argument mining corpora, showing that the proposed approach performs well with respect to state-of-the-art techniques.
Dialogue systems are widely used in AI to support timely and interactive communication with users. We propose a general-purpose dialogue system architecture that leverages computational argumentation and state-of-the-art language technologies. We illustrate and evaluate the system using a COVID-19 vaccine information case study.
We explore the use of residual networks and neural attention for argument mining and in particular link prediction. The method we propose makes no assumptions on document or argument structure. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble. We evaluate it on a challenging data set consisting of user-generated comments, as well as on two other datasets consisting of scientific publications. On the user-generated content dataset, our model outperforms state-of-the-art methods that rely on domain knowledge. On the scientific literature datasets it achieves results comparable to those yielded by BERT-based approaches but with a much smaller model size.
Recent work has demonstrated how data-driven AI methods can leverage consumer protection by supporting the automated analysis of legal documents. However, a shortcoming of data-driven approaches is poor explainability. We posit that in this domain useful explanations of classifier outcomes can be provided by resorting to legal rationales. We thus consider several configurations of memory-augmented neural networks where rationales are given a special role in the modeling of context knowledge. Our results show that rationales not only contribute to improve the classification accuracy, but are also able to offer meaningful, natural language explanations of otherwise opaque classifier outcomes.
As ML applications are becoming ever more pervasive, fully-trained systems are made increasingly available to a wide public, allowing end-users to submit queries with their own data, and to efficiently retrieve results. With increasingly sophisticated such services, a new challenge is how to scale up to evergrowing user bases. In this paper, we present a distributed architecture that could be exploited to parallelize a typical ML system pipeline. We propose a case study consisting of a text mining service and discuss how the method can be generalized to many similar applications. We demonstrate the significance of the computational gain boosted by the distributed architecture by way of an extensive experimental evaluation.
Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap towards performing advanced reasoning tasks. We illustrate how neural-symbolic and statistical relational learning could play a crucial role in the integration of symbolic and sub-symbolic methods to achieve this goal.