Abstract Understanding the implications underlying a text is critical to assessing its impact, in particular the social dynamics that may result from a reading of the text. This requires endowing artificial intelligence (AI) systems with[…]

Read More

Abstract While GPT models have shown impressive performance on summarization and open-ended text generation, it’s important to assess their abilities on more constrained text generation tasks that require significant and diverse rewritings. In this talk,[…]

Read More

Abstract Advanced neural language models have grown ever larger and more complex, pushing forward the limits of language understanding and generation, while diminishing interpretability. The black-box nature of deep neural networks blocks humans from understanding[…]

Read More

Read More

Abstract Biases in datasets, or unintentionally introduced spurious cues, are a common source of misspecification in machine learning. Performant models trained on such data can gender stereotype or be brittle under distribution shift.  In this[…]

Read More

Abstract While large language models have advanced the state-of-the-art in natural language processing, these models are trained on large-scale datasets, which may include harmful information. Studies have shown that as a result, the models exhibit[…]

Read More

Abstract Transformers are essential to pretraining. As we approach 5 years of BERT, the connection between attention as architecture and transfer learning remains key to this central thread in NLP. Other architectures such as CNNs and RNNs[…]

Read More