• Publications
  • Influence
An Autoencoder Approach to Learning Bilingual Word Representations
TLDR
We explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are coherent between two languages, while not relying on word-level alignments. Expand
  • 293
  • 21
  • PDF
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
TLDR
We introduce the task of Complex Sequential QA which combines the two tasks of (i) answering factual questions through complex inferencing over a realistic-sized KG of millions of entities, and (ii) learning to converse through a series of coherently linked QA pairs. Expand
  • 80
  • 21
  • PDF
Show Me Your Evidence - an Automatic Method for Context Dependent Evidence Detection
TLDR
We propose the task of automatically detecting such evidences from unstructured text that support a given claim. Expand
  • 151
  • 20
  • PDF
Diversity driven attention model for query-based abstractive summarization
TLDR
Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. Expand
  • 87
  • 19
  • PDF
Correlational Neural Networks
TLDR
In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Expand
  • 102
  • 16
  • PDF
Towards Exploiting Background Knowledge for Building Conversation Systems
TLDR
We create a new dataset containing movie chats wherein each response is explicitly generated by copying and/or modifying sentences from unstructured background knowledge such as plots, comments and reviews about the movie. Expand
  • 60
  • 16
  • PDF
DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension
TLDR
We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets. Expand
  • 51
  • 11
  • PDF
iNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages
TLDR
In this paper, we introduce NLP resources for 11 major Indian languages from two major language families. These resources include: (a) large-scale sentence-level monolingual corpora, (b) pre-trained word embeddings, and (c) multiple NLU evaluation datasets. Expand
  • 26
  • 11
  • PDF
Towards Building Large Scale Multimodal Domain-Aware Conversation Systems
TLDR
We propose a large-scale multimodal conversational dataset in the fashion domain that embodies the required generic capabilities for such autonomous agents. Expand
  • 36
  • 9
Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks
TLDR
We show that using a simple random pruning strategy we can achieve significant speed up in object detection (74% improvement in fps) while retaining the same accuracy as that of the original Faster RCNN model. Expand
  • 38
  • 7
  • PDF
...
1
2
3
4
5
...