Identifying Metaphorical Word Use with Tree Kernels
- Dirk Hovy, Shashank Shrivastava, E. Hovy
- Computer Science
- 1 June 2013
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.
Contextual Parameter Generation for Universal Neural Machine Translation
- Emmanouil Antonios Platanios, Mrinmaya Sachan, Graham Neubig, Tom Michael Mitchell
- Computer ScienceConference on Empirical Methods in Natural…
- 1 August 2018
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).
Using content and interactions for discovering communities in social networks
- Danish Contractor, Mrinmaya Sachan, Danish Contractor, T. Faruquie, L. V. Subramaniam
- Computer ScienceThe Web Conference
- 16 April 2012
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.
Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition
- Devendra Singh Sachan, P. Xie, Mrinmaya Sachan, E. Xing
- Computer ScienceMachine Learning in Health Care
- 21 November 2017
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.
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
- K. Murugesan, Mattia Atzeni, Murray Campbell
- Computer ScienceAAAI Conference on Artificial Intelligence
- 8 October 2020
This paper designs a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances, and shows that agents which incorporate Commonsense knowledge in TWC perform better, while acting more efficiently.
Learning Answer-Entailing Structures for Machine Comprehension
- Mrinmaya Sachan, Kumar Avinava Dubey, E. Xing, Matthew Richardson
- Computer ScienceAnnual Meeting of the Association for…
- 1 July 2015
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.
Learning Concept Taxonomies from Multi-modal Data
- H. Zhang, Zhiting Hu, Yuntian Deng, Mrinmaya Sachan, Zhicheng Yan, E. Xing
- Computer ScienceAnnual Meeting of the Association for…
- 29 June 2016
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.
Self-Training for Jointly Learning to Ask and Answer Questions
- Mrinmaya Sachan, E. Xing
- Computer Science, EducationNorth American Chapter of the Association for…
- 1 June 2018
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.
Machine Comprehension using Rich Semantic Representations
- Mrinmaya Sachan, E. Xing
- Computer ScienceAnnual Meeting of the Association for…
- 1 August 2016
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.
Spatial compactness meets topical consistency: jointly modeling links and content for community detection
- Mrinmaya Sachan, Kumar Avinava Dubey, Shashank Srivastava, E. Xing, E. Hovy
- Computer ScienceWeb Search and Data Mining
- 24 February 2014
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.
...
...