activity
20162024
most citedSummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents

750 citations · 1.6k across the 35 of their papers we have counts for

collaborators
Showing 2019Show all

7 papers · 1 filter

cs.CL2019★ 5 cited

Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer

Henghui Zhu, Feng Nan, Zhiguo Wang +2

Conversation structure is useful for both understanding the nature of conversation dynamics and for providing features for many downstream applications such as summarization of con…

cs.CL2019★ 40 cited

Universal Text Representation from BERT: An Empirical Study

Xiaofei Ma, Zhiguo Wang, Patrick Ng +2

We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transfe…

cs.CL2019★ 24 cited

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

Zhiguo Wang, Patrick Ng, Xiaofei Ma +2

BERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training…

cs.LG2019★ 3 cited

Multi Sense Embeddings from Topic Models

Shobhit Jain, Sravan Babu Bodapati, Ramesh Nallapati +1

Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations…

cs.IR2019★ 1 cited

Topic Modeling with Wasserstein Autoencoders

Feng Nan, Ran Ding, Ramesh Nallapati +1

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on…

cs.IR2019★ 16 cited

Passage Ranking with Weak Supervision

Peng Xu, Xiaofei Ma, Ramesh Nallapati +1

In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage mul…

cs.CV2019★ 55 cited

OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations

Pramuditha Perera, Ramesh Nallapati, Bing Xiang

We present a novel model called OCGAN for the classical problem of one-class novelty detection, where, given a set of examples from a particular class, the goal is to determine if…