The advent of large language models (LLMs) and their adoption by the legal community has
given rise to the question: what types of legal reasoning can LLMs perform? To enable …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Machine learning models that achieve high overall accuracy often make systematic errors
on important subsets (or slices) of data. Identifying underperforming slices is particularly …

Despite impressive performance on standard benchmarks, deep neural networks are often
brittle when deployed in real-world systems. Consequently, recent research has focused on …

Existing KBQA approaches, despite achieving strong performance on iid test data, often
struggle in generalizing to questions involving unseen KB schema items. Prior ranking …

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained
entity types and entity descriptions to perform linking. The model performs mention …

Abstract We present Retriever-Transducer-Checker (ReTraCk), a neural semantic parsing
framework for large scale knowledge base question answering (KBQA). ReTraCk is …

We introduce Saga, a next-generation knowledge construction and serving platform for
powering knowledge-based applications at industrial scale. Saga follows a hybrid batch …

Natural language texts, such as tweets and news, contain a vast amount of geospatial
information, which can be extracted by first recognizing toponyms in texts (toponym …

Retrieval is a core component for open-domain NLP tasks. In open-domain tasks, multiple
entities can share a name, making disambiguation an inherent yet under-explored problem …