Deep learning excels at learning low-level task information from large amounts of data, but
struggles with learning high-level domain knowledge, which can often be directly and …

We demonstrate a library for the integration of domain knowledge in deep learning
architectures. Using this library, the structure of the data is expressed symbolically via graph …

In this paper, we present an analysis of computationally generated mixed-modality definite
referring expressions using combinations of gesture and linguistic descriptions. In doing so …

When evaluating an answer choice for Reading Comprehension task, other answer choices
available for the question and the answers of related questions about the same paragraph …

In this work, we study collaborative online conversations. Such conversations are rich in
content, constructive and motivated by a shared goal. Automatically identifying such …

Abstract Reasoning over procedural text, which encompasses texts such as recipes,
manuals, and'how to'tutorials, presents formidable challenges due to the dynamic nature of …

In this work, we model latent discourse indicators to classify constructive and collaborative
conversations online. Such conversations are considered goodas they are rich in content …

In this paper, we discuss the work in progress on designing a prototype for a novel
declarative learningbased programming system and present our preliminary results. The …

Data rarely lies on uniquely Euclidean spaces. Even data typically represented in regular
domains, such as images, can have a higher level of relational information, either between …