Recent large-scale Spoken Language Understanding datasets focus predominantly on English and do not account for language-specific phenomena such as particular phonemes or words in different lects. We introduce ITALIC, the first large-scale speech dataset designed for intent classification in Italian. The dataset comprises 16,521 crowdsourced audio samples recorded by 70 speakers from various Italian regions and annotated with intent labels and additional metadata. We explore the versatility of ITALIC by evaluating current state-of-the-art speech and text models. Results on intent classification suggest that increasing scale and running language adaptation yield better speech models, monolingual text models outscore multilingual ones, and that speech recognition on ITALIC is more challenging than on existing Italian benchmarks. We release both the dataset and the annotation scheme to streamline the development of new Italian SLU models and language-specific datasets.

Language is constantly changing and evolving, leaving language models to become quickly outdated. Consequently, we should continuously update our models with new data to expose them to new events and facts. However, that requires additional computing, which means new carbon emissions. Do any measurable benefits justify this cost? This paper looks for empirical evidence to support continuous training. We reproduce existing benchmarks and extend them to include additional time periods, models, and tasks. Our results show that the downstream task performance of temporally adapted English models for social media data do not improve over time. Pretrained models without temporal adaptation are actually significantly more effective and efficient. However, we also note a lack of suitable temporal benchmarks. Our findings invite a critical reflection on when and how to temporally adapt language models, accounting for sustainability.

The model is trained on over 700k The extraordinary growth of online retail - as < image, text > pairs from the inventory of of 2020, 4 trillion dollars per year (Cramer-Flood, Farfetch, one of the largest fashion luxury retailer 2020) - had a profound impact on the fashion industry, in the world, and is applied to use cases with 1 out of 4 transactions now happening online known to be crucial in a vast global market; (McKinsey, 2019). The combination of large amounts of data and variety of use cases supported 2. we evaluate FashionCLIP in a variety of by growing investments has made e-commerce fertile tasks, showing that fine-tuning helps capture for the application of cutting-edge machine domain-specific concepts and generalize them learning models, with NLP involved in recommendations in zero-shot scenarios; we supplement quantitative (de Souza Pereira Moreira et al., 2019; Guo tests with qualitative analyses, and et al., 2020; Goncalves et al., 2021), information offer preliminary insights of how concepts retrieval (IR) (Ai and Narayanan.R, 2021), product grounded in a visual space unlock linguistic

As Transformers are increasingly relied upon to solve complex NLP problems, there is an increased need for their decisions to be humanly interpretable. While several explainable AI (XAI) techniques for interpreting the outputs of transformer-based models have been proposed, there is still a lack of easy access to using and comparing them. We introduce ferret, a Python library to simplify the use and comparisons of XAI methods on transformer-based classifiers. With ferret, users can visualize and compare transformers-based models output explanations using state-of-the-art XAI methods on any free-text or existing XAI corpora. Moreover, users can also evaluate ad-hoc XAI metrics to select the most faithful and plausible explanations. To align with the recently consolidated process of sharing and using transformers-based models from Hugging Face, ferret interfaces directly with its Python library. In this paper, we showcase ferret to benchmark XAI methods used on transformers for sentiment analysis and hate speech detection. We show how specific methods provide consistently better explanations and are preferable in the context of transformer models.