Vivek Khetan

TL;DR: The successes of neural IR thus far are highlighted, obstacles to its wider adoption are cataloged, and potentially promising directions for future research are suggested.

TL;DR: The current landscape of Neural IR research is surveyed, paying special attention to the use of learned representations of queries and documents (i.e., neural embeddings), to highlight the successes and obstacles to its wider adoption, and suggest potentially promising directions for future research.

TL;DR: The language model's capabilities for causal association among events expressed in natural language text are investigated using sentence context combined with event information, and by leveraging masked event context with in-domain and out-of-domain data distribution.

TL;DR: A new method to automatically derive (noisy) supervision for this task is proposed which is used to train a dense retrieval model; this outperforms baseline models.

TL;DR: A novel methodology was developed to detect causal sentences and identify both explicit and implicit, single and multiword cause, and the corresponding effect, as expressed in diabetes-related tweets leveraging BERT-based architectures and visualized as cause-effect network.