Search Results for author: Sourav Dutta

Found 24 papers, 7 papers with code

UdS-DFKI@WMT20: Unsupervised MT and Very Low Resource Supervised MT for German-Upper Sorbian

no code implementations WMT (EMNLP) 2020 Sourav Dutta, Jesujoba Alabi, Saptarashmi Bandyopadhyay, Dana Ruiter, Josef van Genabith

This paper describes the UdS-DFKI submission to the shared task for unsupervised machine translation (MT) and very low-resource supervised MT between German (de) and Upper Sorbian (hsb) at the Fifth Conference of Machine Translation (WMT20).

Translation Unsupervised Machine Translation

Cross-lingual Sentence Embedding using Multi-Task Learning

no code implementations EMNLP 2021 Koustava Goswami, Sourav Dutta, Haytham Assem, Theodorus Fransen, John P. McCrae

We demonstrate the efficacy of an unsupervised as well as a weakly supervised variant of our framework on STS, BUCC and Tatoeba benchmark tasks.

Multi-Task Learning Semantic Similarity +3

DTAFA: Decoupled Training Architecture for Efficient FAQ Retrieval

no code implementations SIGDIAL (ACL) 2021 Haytham Assem, Sourav Dutta, Edward Burgin

Automated Frequently Asked Question (FAQ) retrieval provides an effective procedure to provide prompt responses to natural language based queries, providing an efficient platform for large-scale service-providing companies for presenting readily available information pertaining to customers’ questions.

Semantic Similarity Semantic Textual Similarity +1

Deep Neural Compression Via Concurrent Pruning and Self-Distillation

no code implementations30 Sep 2021 James O' Neill, Sourav Dutta, Haytham Assem

Pruning aims to reduce the number of parameters while maintaining performance close to the original network.

Knowledge Distillation Language Modelling

Self-Distilled Pruning Of Neural Networks

no code implementations29 Sep 2021 James O' Neill, Sourav Dutta, Haytham Assem

Pruning aims to reduce the number of parameters while maintaining performance close to the original network.

Knowledge Distillation Language Modelling

EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT

no code implementations29 Sep 2021 Svetlana Tchistiakova, Jesujoba Alabi, Koel Dutta Chowdhury, Sourav Dutta, Dana Ruiter

We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021).

Fine-tuning Machine Translation +1

Sequence-to-Sequence Learning on Keywords for Efficient FAQ Retrieval

no code implementations23 Aug 2021 Sourav Dutta, Haytham Assem, Edward Burgin

Frequently-Asked-Question (FAQ) retrieval provides an effective procedure for responding to user's natural language based queries.

Keyword Extraction Question Answering

Data-driven reduced order modeling of environmental hydrodynamics using deep autoencoders and neural ODEs

2 code implementations6 Jul 2021 Sourav Dutta, Peter Rivera-Casillas, Orie M. Cecil, Matthew W. Farthing, Emma Perracchione, Mario Putti

Model reduction for fluid flow simulation continues to be of great interest across a number of scientific and engineering fields.

Neural Ordinary Differential Equations for Data-Driven Reduced Order Modeling of Environmental Hydrodynamics

2 code implementations22 Apr 2021 Sourav Dutta, Peter Rivera-Casillas, Matthew W. Farthing

Model reduction for fluid flow simulation continues to be of great interest across a number of scientific and engineering fields.

Neural Sampling Machine with Stochastic Synapse allows Brain-like Learning and Inference

no code implementations20 Feb 2021 Sourav Dutta, Georgios Detorakis, Abhishek Khanna, Benjamin Grisafe, Emre Neftci, Suman Datta

We experimentally show that the inherent stochastic switching of the selector element between the insulator and metallic state introduces a multiplicative stochastic noise within the synapses of NSM that samples the conductance states of the FeFET, both during learning and inference.

Bayesian Inference Decision Making +1

Unsupervised Word Translation Pairing using Refinement based Point Set Registration

no code implementations26 Nov 2020 Silviu Oprea, Sourav Dutta, Haytham Assem

Cross-lingual alignment of word embeddings play an important role in knowledge transfer across languages, for improving machine translation and other multi-lingual applications.

Fine-tuning Machine Translation +3

Towards Quantifying the Distance between Opinions

no code implementations27 Jan 2020 Saket Gurukar, Deepak Ajwani, Sourav Dutta, Juho Lauri, Srinivasan Parthasarathy, Alessandra Sala

Similarly, in a supervised setting, our opinion distance measure achieves considerably better accuracy (up to 20% increase) compared to extant approaches that rely on text similarity, stance similarity, and sentiment similarity

Learning fine-grained search space pruning and heuristics for combinatorial optimization

no code implementations5 Jan 2020 Juho Lauri, Sourav Dutta, Marco Grassia, Deepak Ajwani

For the classical maximum clique enumeration problem, we show that our framework can prune a large fraction of the input graph (around 99 % of nodes in case of sparse graphs) and still detect almost all of the maximum cliques.

Combinatorial Optimization

Mapping Supervised Bilingual Word Embeddings from English to low-resource languages

1 code implementation14 Oct 2019 Sourav Dutta

It is very challenging to work with low-resource languages due to the inadequate availability of data.

Machine Translation Translation +1

Whatcha lookin' at? DeepLIFTing BERT's Attention in Question Answering

1 code implementation14 Oct 2019 Ekaterina Arkhangelskaia, Sourav Dutta

There has been great success recently in tackling challenging NLP tasks by neural networks which have been pre-trained and fine-tuned on large amounts of task data.

Question Answering

Learning Multi-Stage Sparsification for Maximum Clique Enumeration

no code implementations12 Sep 2019 Marco Grassia, Juho Lauri, Sourav Dutta, Deepak Ajwani

Compared to the state-of-the-art heuristics and preprocessing strategies, the advantages of our approach are that (i) it does not require any estimate on the maximum clique size at runtime and (ii) we demonstrate it to be effective also for dense graphs.

Fine-grained Search Space Classification for Hard Enumeration Variants of Subset Problems

no code implementations22 Feb 2019 Juho Lauri, Sourav Dutta

We propose a simple, powerful, and flexible machine learning framework for (i) reducing the search space of computationally difficult enumeration variants of subset problems and (ii) augmenting existing state-of-the-art solvers with informative cues arising from the input distribution.

General Classification

Credible Review Detection with Limited Information using Consistency Analysis

no code implementations7 May 2017 Subhabrata Mukherjee, Sourav Dutta, Gerhard Weikum

Online reviews provide viewpoints on the strengths and shortcomings of products/services, influencing potential customers' purchasing decisions.

Topic Models

KOGNAC: Efficient Encoding of Large Knowledge Graphs

1 code implementation16 Apr 2016 Jacopo Urbani, Sourav Dutta, Sairam Gurajada, Gerhard Weikum

We propose KOGNAC, a dictionary-encoding algorithm designed to improve SPARQL querying with a judicious combination of statistical and semantic techniques.

Knowledge Graphs

Cross-Document Co-Reference Resolution using Sample-Based Clustering with Knowledge Enrichment

no code implementations TACL 2015 Sourav Dutta, Gerhard Weikum

Second, we reduce the computational cost by a new algorithm that embeds sample-based bisection, using spectral clustering or graph partitioning, in a hierarchical clustering process.

Coreference Resolution graph partitioning +1

Advanced Bloom Filter Based Algorithms for Efficient Approximate Data De-Duplication in Streams

1 code implementation17 Dec 2012 Suman K. Bera, Sourav Dutta, Ankur Narang, Souvik Bhattacherjee

In this work, we present several novel algorithms for the problem of approximate detection of duplicates in data streams.

Cannot find the paper you are looking for? You can Submit a new open access paper.