Search Results for author:
Found 33 papers, 10 papers with code
DTAFA: Decoupled Training Architecture for Efficient FAQ Retrieval
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.
Multi-Stage Framework with Refinement Based Point Set Registration for Unsupervised Bi-Lingual Word Alignment
Cross-lingual alignment of word embeddings are important in knowledge transfer across languages, for improving machine translation and other multi-lingual applications.
UdS-DFKI@WMT20: Unsupervised MT and Very Low Resource Supervised MT for German-Upper Sorbian
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).
Cross-lingual Sentence Embedding using Multi-Task Learning
We demonstrate the efficacy of an unsupervised as well as a weakly supervised variant of our framework on STS, BUCC and Tatoeba benchmark tasks.
Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification
Evaluations on the CLINC-150, Stackoverflow, and Banking77 datasets demonstrate DETER's efficacy.
AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification
As a solution, we propose AdaSent, which decouples SEPT from DAPT by training a SEPT adapter on the base PLM.
Gradient Sparsification For Masked Fine-Tuning of Transformers
We introduce GradDrop and variants thereof, a class of gradient sparsification methods that mask gradients during the backward pass, acting as gradient noise.
Attention over pre-trained Sentence Embeddings for Long Document Classification
When compared with the current state-of-the-art models using standard fine-tuning, the studied method obtains competitive results (even if there is no clear best model in this configuration).
AI-assisted Improved Service Provisioning for Low-latency XR over 5G NR
Extended Reality (XR) is one of the most important 5G/6G media applications that will fundamentally transform human interactions.
Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models
We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models.
AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis
Aspect Based Sentiment Analysis is a dominant research area with potential applications in social media analytics, business, finance, and health.
Aspect-Based Sentiment Analysis
Aspect Category Sentiment Analysis
+2
Aligned Weight Regularizers for Pruning Pretrained Neural Networks
While various avenues of research have been explored for iterative pruning, little is known what effect pruning has on zero-shot test performance and its potential implications on the choice of pruning criteria.
Deep Neural Compression Via Concurrent Pruning and Self-Distillation
Pruning aims to reduce the number of parameters while maintaining performance close to the original network.
EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT
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).
Self-Distilled Pruning Of Neural Networks
Pruning aims to reduce the number of parameters while maintaining performance close to the original network.
Sequence-to-Sequence Learning on Keywords for Efficient FAQ Retrieval
Frequently-Asked-Question (FAQ) retrieval provides an effective procedure for responding to user's natural language based queries.
Data-driven reduced order modeling of environmental hydrodynamics using deep autoencoders and neural ODEs
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
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
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.
Unsupervised Word Translation Pairing using Refinement based Point Set Registration
Cross-lingual alignment of word embeddings play an important role in knowledge transfer across languages, for improving machine translation and other multi-lingual applications.
Towards Quantifying the Distance between Opinions
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
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.
Inherent Weight Normalization in Stochastic Neural Networks
Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks.
Mapping Supervised Bilingual Word Embeddings from English to low-resource languages
It is very challenging to work with low-resource languages due to the inadequate availability of data.
Whatcha lookin' at? DeepLIFTing BERT's Attention in Question Answering
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.
Learning Multi-Stage Sparsification for Maximum Clique Enumeration
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.
Automated assessment of knowledge hierarchy evolution: comparing directed acyclic graphs
In this paper, we focus on measures that leverage structural properties of the knowledge hierarchy graph to assess the temporal changes.
Fine-grained Search Space Classification for Hard Enumeration Variants of Subset Problems
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.
Credible Review Detection with Limited Information using Consistency Analysis
Online reviews provide viewpoints on the strengths and shortcomings of products/services, influencing potential customers' purchasing decisions.
KOGNAC: Efficient Encoding of Large Knowledge Graphs
We propose KOGNAC, a dictionary-encoding algorithm designed to improve SPARQL querying with a judicious combination of statistical and semantic techniques.
Cross-Document Co-Reference Resolution using Sample-Based Clustering with Knowledge Enrichment
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.
Advanced Bloom Filter Based Algorithms for Efficient Approximate Data De-Duplication in Streams
In this work, we present several novel algorithms for the problem of approximate detection of duplicates in data streams.
