Sean MacAvaney

We propose a joint approach that incorporates BERT's classification vector into existing neural models and show that it outperforms state-of-the-art ad-hoc ranking baselines. Expand

We propose a weak supervision approach based on pairs of text to train neural ranking models and a filtering technique to adapt the dataset to a given domain. Expand

We introduce the SMHD (Self-reported Mental Health Diagnoses) dataset, a large dataset of social media posts from users with one or multiple mental health conditions along with matched control users. Expand

We present a search system called SLEDGE, which utilizes SciBERT to effectively re-rank articles. Expand

We present a system for this task that uses supervised learning for the extraction of temporal expression and event spans with corresponding attributes and narrative container relations. Expand

We identify and examine challenges faced by online automatic approaches for hate speech detection in text. Expand

We propose an effective approach to reduce the query-time latency of deep transformer networks (up to a 42x speedup on web document ranking) making these networks more practical to use in a real-time ranking scenario. Expand

We present PARADE, an end-to-end Transformer-based model that considers document-level context for document reranking. Expand

We present a search system called SLEDGE, which utilizes SciBERT to effectively re-rank articles on SARS-CoV-2. Expand

In this work, we present our submission to the TREC Complex Answer Retrieval (CAR) task. Expand