activity
20182022
most citedRevisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

72 citations · 74 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL20221 cited

Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions

Cuong Hoang, Devendra Sachan, Prashant Mathur +2

Several recent studies have reported dramatic performance improvements in neural machine translation (NMT) by augmenting translation at inference time with fuzzy-matches retrieved…

cs.CL20221 cited

Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions

Cuong Hoang, Devendra Sachan, Prashant Mathur +2

We explore zero-shot adaptation, where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. We build on the id…

cs.CL2021

End-to-End Training of Neural Retrievers for Open-Domain Question Answering

Devendra Singh Sachan, Mostofa Patwary, Mohammad Shoeybi +4

Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised approaches. However, it remains unclear how unsu…

cs.CL2020

Stronger Transformers for Neural Multi-Hop Question Generation

Devendra Singh Sachan, Lingfei Wu, Mrinmaya Sachan +1

Prior work on automated question generation has almost exclusively focused on generating simple questions whose answers can be extracted from a single document. However, there is a…

cs.CL202072 cited

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

Devendra Singh Sachan, Manzil Zaheer, Ruslan Salakhutdinov

In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semi-supervised approaches. Several prior works have suggested that…

cs.CL2020

Do Syntax Trees Help Pre-trained Transformers Extract Information?

Devendra Singh Sachan, Yuhao Zhang, Peng Qi +1

Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency…