Deep learning models are often trained on distributed, web-scale datasets crawled from the
internet. In this paper, we introduce two new dataset poisoning attacks that intentionally …

Deep learning has become the dominant approach in addressing various tasks in Natural
Language Processing (NLP). Although text inputs are typically represented as a sequence …

Answering real-world complex queries, such as complex product search, often requires
accurate retrieval from semi-structured knowledge bases that involve blend of unstructured …

Abstract Knowledge Graphs (KG) are multi-relational graphs consisting of entities as nodes
and relations among them as typed edges. Goal of the Question Answering over KG (KGQA) …

In the 1940s, Claude Shannon developed the information theory focusing on quantifying the
maximum data rate that can be supported by a communication channel. Guided by this …

Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-
based natural language (NL) understanding tasks. Such models are typically trained on free …

Hybrid data combining both tabular and textual content (eg, financial reports) are quite
pervasive in the real world. However, Question Answering (QA) over such hybrid data is …