• Publications
  • Influence
Identifying Metaphorical Word Use with Tree Kernels
tl;dr
A metaphor is a figure of speech that refers to one concept in terms of another, as in “He is such a sweet person”. Expand
  • 67
  • 15
  • Open Access
Using content and interactions for discovering communities in social networks
tl;dr
In recent years, social networking sites have not only enabled people to connect with each other using social links but have also allowed them to share, communicate and interact over diverse geographical regions. Expand
  • 166
  • 8
  • Open Access
Learning Answer-Entailing Structures for Machine Comprehension
tl;dr
We present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs), and uses what it learns to answer machine comprehension questions on novel texts. Expand
  • 49
  • 6
  • Open Access
Contextual Parameter Generation for Universal Neural Machine Translation
tl;dr
We propose a simple modification to existing neural machine translation (NMT) models that enables using a single universal model to translate between multiple languages while allowing for language specific parameterization, and that can also be used for domain adaptation. Expand
  • 54
  • 4
  • Open Access
Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition
tl;dr
We train a bidirectional language model (BiLM) on unlabeled text data to improve the performance of NER models. Expand
  • 22
  • 4
  • Open Access
Machine Comprehension using Rich Semantic Representations
tl;dr
We propose an approach using the Abstract Meaning Representation (AMR) formalism for the task of machine comprehension. Expand
  • 25
  • 3
  • Open Access
Spatial compactness meets topical consistency: jointly modeling links and content for community detection
tl;dr
In this paper, we address the problem of discovering topically meaningful, yet compact (densely connected) communities in a social network. Expand
  • 20
  • 3
  • Open Access
Self-Training for Jointly Learning to Ask and Answer Questions
tl;dr
We propose a self-training method for jointly learning to ask as well as answer questions, leveraging unlabeled text along with labeled question answer pairs for learning. Expand
  • 30
  • 2
  • Open Access
Learning Concept Taxonomies from Multi-modal Data
tl;dr
We study the problem of automatically building hypernym taxonomies from textual and visual data and propose a probabilistic model based on distributed representations of images and words. Expand
  • 16
  • 2
  • Open Access
A Structured Distributional Semantic Model for Event Co-reference
tl;dr
We present a novel approach to modelling distributional semantics that represents meaning as distributions over relations in syntactic neighborhoods. Expand
  • 19
  • 2
  • Open Access