Search Results for author: Arjun Mukherjee

Found 33 papers, 5 papers with code

Improving Evidence Retrieval with Claim-Evidence Entailment

no code implementations RANLP 2021 Fan Yang, Eduard Dragut, Arjun Mukherjee

Claim verification is challenging because it requires first to find textual evidence and then apply claim-evidence entailment to verify a claim.

On the Usefulness of Personality Traits in Opinion-oriented Tasks

no code implementations RANLP 2021 Marjan Hosseinia, Eduard Dragut, Dainis Boumber, Arjun Mukherjee

We use a deep bidirectional transformer to extract the Myers-Briggs personality type from user-generated data in a multi-label and multi-class classification setting.

Authorship Verification Classification +3

Opinion Prediction with User Fingerprinting

1 code implementation RANLP 2021 Kishore Tumarada, Yifan Zhang, Fan Yang, Eduard Dragut, Omprakash Gnawali, Arjun Mukherjee

Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.

Sentiment Analysis Time Series

Claim Verification using a Multi-GAN based Model

no code implementations RANLP 2021 Amartya Hatua, Arjun Mukherjee, Rakesh M. Verma

This article describes research on claim verification carried out using a multiple GAN-based model.

Language Modelling

Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution

no code implementations15 Dec 2020 Yifan Zhang, Fan Yang, Marjan Hosseinia, Arjun Mukherjee

In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM).

Sentiment Analysis

Towards Demystifying Dimensions of Source Code Embeddings

1 code implementation29 Aug 2020 Md. Rafiqul Islam Rabin, Arjun Mukherjee, Omprakash Gnawali, Mohammad Amin Alipour

A popular approach in representing source code is neural source code embeddings that represents programs with high-dimensional vectors computed by training deep neural networks on a large volume of programs.

Cannot Predict Comment Volume of a News Article before (a few) Users Read It

no code implementations14 Aug 2020 Lihong He, Chen Shen, Arjun Mukherjee, Slobodan Vucetic, Eduard Dragut

We show that the early arrival rate of comments is the best indicator of the eventual number of comments.

Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models

no code implementations1 Aug 2020 Daniel Lee, Rakesh Verma, Avisha Das, Arjun Mukherjee

In this paper, we revisit the challenging problem of unsupervised single-document summarization and study the following aspects: Integer linear programming (ILP) based algorithms, Parameterized normalization of term and sentence scores, and Title-driven approaches for summarization.

Document Summarization Extractive Summarization

Stance Prediction for Contemporary Issues: Data and Experiments

1 code implementation WS 2020 Marjan Hosseinia, Eduard Dragut, Arjun Mukherjee

We investigate whether pre-trained bidirectional transformers with sentiment and emotion information improve stance detection in long discussions of contemporary issues.

Stance Detection

Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network

no code implementations7 Feb 2019 Abhishek Laddha, Arjun Mukherjee

The attention mechanism captures the importance of context words on a particular aspect opinion expression when multiple aspects are present in a sentence via location and content based memory.

Sentiment Analysis

ENWalk: Learning Network Features for Spam Detection in Twitter

no code implementations11 Apr 2017 K. C. Santosh, Suman Kalyan Maity, Arjun Mukherjee

We propose ENWalk, a framework to detect the spammers by learning the feature representations of the users in the social media.

Spam detection

Detecting Sockpuppets in Deceptive Opinion Spam

no code implementations9 Mar 2017 Marjan Hosseinia, Arjun Mukherjee

This paper explores the problem of sockpuppet detection in deceptive opinion spam using authorship attribution and verification approaches.

Leveraging Multiple Domains for Sentiment Classification

no code implementations COLING 2016 Fan Yang, Arjun Mukherjee, Yifan Zhang

In addition, the learned feature representation can be used as classifier since our model defines the meaning of feature value and arranges high-level features in a prefixed order, so it is not necessary to train another classifier on top of the new features.

Classification Domain Adaptation +3

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