
-
JUNLP@Dravidian-CodeMix-FIRE2020: Sentiment Classification of Code-Mixed Tweets using Bi-Directional RNN and Language Tags
Sentiment analysis has been an active area of research in the past two d...
read it
-
Development of POS tagger for English-Bengali Code-Mixed data
Code-mixed texts are widespread nowadays due to the advent of social med...
read it
-
Preparation of Sentiment tagged Parallel Corpus and Testing its effect on Machine Translation
In the current work, we explore the enrichment in the machine translatio...
read it
-
JUNLP@SemEval-2020 Task 9:Sentiment Analysis of Hindi-English code mixed data
Code-mixing is a phenomenon which arises mainly in multilingual societie...
read it
-
Code-Mixed to Monolingual Translation Framework
The use of multilingualism in the new generation is widespread in the fo...
read it
-
K-TanH: Hardware Efficient Activations For Deep Learning
We propose K-TanH, a novel, highly accurate, hardware efficient approxim...
read it
-
High Performance Scalable FPGA Accelerator for Deep Neural Networks
Low-precision is the first order knob for achieving higher Artificial In...
read it
-
Modeling Engagement Dynamics of Online Discussions using Relativistic Gravitational Theory
Online discussions are valuable resources to study user behaviour on a d...
read it
-
JUMT at WMT2019 News Translation Task: A Hybrid approach to Machine Translation for Lithuanian to English
In the current work, we present a description of the system submitted to...
read it
-
JUCBNMT at WMT2018 News Translation Task: Character Based Neural Machine Translation of Finnish to English
In the current work, we present a description of the system submitted to...
read it
-
Mixed Precision Training With 8-bit Floating Point
Reduced precision computation for deep neural networks is one of the key...
read it
-
A Study of BFLOAT16 for Deep Learning Training
This paper presents the first comprehensive empirical study demonstratin...
read it
-
SMT vs NMT: A Comparison over Hindi & Bengali Simple Sentences
In the present article, we identified the qualitative differences betwee...
read it
-
Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers
As deep learning methods form a critical part in commercially important ...
read it
-
How did the discussion go: Discourse act classification in social media conversations
We propose a novel attention based hierarchical LSTM model to classify d...
read it
-
Sentiment Analysis of Code-Mixed Indian Languages: An Overview of SAIL_Code-Mixed Shared Task @ICON-2017
Sentiment analysis is essential in many real-world applications such as ...
read it
-
Preparing Bengali-English Code-Mixed Corpus for Sentiment Analysis of Indian Languages
Analysis of informative contents and sentiments of social users has been...
read it
-
Language Identification of Bengali-English Code-Mixed data using Character & Phonetic based LSTM Models
Language identification of social media text still remains a challenging...
read it
-
Mixed Precision Training of Convolutional Neural Networks using Integer Operations
The state-of-the-art (SOTA) for mixed precision training is dominated by...
read it
-
On Scale-out Deep Learning Training for Cloud and HPC
The exponential growth in use of large deep neural networks has accelera...
read it
-
Analyzing Roles of Classifiers and Code-Mixed factors for Sentiment Identification
Multilingual speakers often switch between languages to express themselv...
read it
-
RAIL: Risk-Averse Imitation Learning
Imitation learning algorithms learn viable policies by imitating an expe...
read it
-
Ternary Residual Networks
Sub-8-bit representation of DNNs incur some discernible loss of accuracy...
read it
-
Determining sentiment in citation text and analyzing its impact on the proposed ranking index
Whenever human beings interact with each other, they exchange or express...
read it
-
Sentiment Identification in Code-Mixed Social Media Text
Sentiment analysis is the Natural Language Processing (NLP) task dealing...
read it
-
Complexity Metric for Code-Mixed Social Media Text
An evaluation metric is an absolute necessity for measuring the performa...
read it
-
Ternary Neural Networks with Fine-Grained Quantization
We propose a novel fine-grained quantization (FGQ) method to ternarize p...
read it
-
Mixed Low-precision Deep Learning Inference using Dynamic Fixed Point
We propose a cluster-based quantization method to convert pre-trained fu...
read it
-
Authorship Verification - An Approach based on Random Forest
Authorship attribution, being an important problem in many areas in-clud...
read it
-
Labeling of Query Words using Conditional Random Field
This paper describes our approach on Query Word Labeling as an attempt i...
read it