• Publications
  • Influence
Identifying Metaphorical Word Use with Tree Kernels
TLDR
This work uses SVMs with tree-kernels on a balanced corpus of 3872 instances, created by bootstrapping from available metaphor lists to identify metaphorical use and outperform two baselines, a sequential and a vectorbased approach. Expand
Using content and interactions for discovering communities in social networks
TLDR
This paper proposes generative models that can discover communities based on the discussed topics, interaction types and the social connections among people and shows that it performs better than existing community discovery models. Expand
Contextual Parameter Generation for Universal Neural Machine Translation
TLDR
This approach requires no changes to the model architecture of a standard NMT system, but instead introduces a new component, the contextual parameter generator (CPG), that generates the parameters of the system (e.g., weights in a neural network). Expand
Learning Answer-Entailing Structures for Machine Comprehension
TLDR
A unified max-margin framework is presented that learns to find hidden structures that explain the relation between the question, correct answer, and text, and is extended to incorporate multi-task learning on the different subtasks that are required to perform machine comprehension. Expand
Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition
TLDR
This work trains a bidirectional language model (BiLM) on unlabeled data and transfers its weights to "pretrain" an NER model with the same architecture as the BiLM, which results in a better parameter initialization of the NER models. Expand
Machine Comprehension using Rich Semantic Representations
TLDR
A unified max-margin framework is presented that learns to find a latent mapping of the question-answer mean representation graph onto the text meaning representation graph that explains the answer, and uses what it learns to answer questions on novel texts. Expand
Spatial compactness meets topical consistency: jointly modeling links and content for community detection
TLDR
This paper transforms the social network to be an integer-weighted graph, and proposes a mixed-membership model to identify compact communities using this transformation, and augment the representation and the model to incorporate user-content information imposing topical consistency in the communities. Expand
Learning Concept Taxonomies from Multi-modal Data
TLDR
This work proposes a probabilistic model for taxonomy induction by jointly leveraging text and images and designs end-to-end features based on distributed representations of images and words to avoid hand-crafted feature engineering. Expand
Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems
TLDR
A system that learns to parse Newtonian physics problems in textbooks, Nuts&Bolts, learns a pipeline process that incorporates existing code, pre-learned machine learning models, and human engineered rules to prevent propagation of errors. Expand
Self-Training for Jointly Learning to Ask and Answer Questions
TLDR
This work proposes 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, and demonstrates significant improvements over a number of established baselines. Expand
...
1
2
3
4
5
...