Learning Structured Information from Language

Speaker Name: 
Arzoo Katiyar
Speaker Title: 
Ph.D candidate
Speaker Organization: 
Cornell University
Start Time: 
Thursday, February 14, 2019 - 11:00am
End Time: 
Thursday, February 14, 2019 - 12:15pm
Location: 
E2-599
Organizer: 
Luca de Alfaro

Abstract:

Extracting information from text entails deriving a structured, and typically domain-specific, representation of entities and relations from unstructured text. The information thu extracted can potentially facilitate applications such as question answering, information retrieval, conversational dialogue and opinion analysis. However, extracting information from text in a structured form is difficult: it requires understanding words and the relations that exist between them in the context of both the current sentence and the document  as a whole.

In this talk, I will present my research on neural models that learn structured output representations comprised of textual mentions of entities and relations within a sentence. In particular, I will propose the use of novel output representations that allow the neural models to learn better dependencies in the output structure and achieve state-of-the-art performance on both tasks as well as on nested variations. I will also describe our recent work on expanding the input context beyond sentences by incorporating coreference resolution to learn entity-level rather than mention-level representations and show that these representations can further improve relation extraction by capturing the information regarding the saliency of entities in the document.

Bio:

Arzoo Katiyar is a PhD candidate in Computer Science at Cornell University, where she is advised by Claire Cardie. Her research interests include natural language processing and machine learning. In particular, she is interested in developing neural network based models for structured prediction problems in natural language processing which can help extract information from text. Previously, she received her BTech-MTech degree in Computer Science and Engineering from IIT Kanpur.