Welcome to ICON 2021!



Guidelines for Camera-ready Submission


1. Authors must follow the ACL Author Guidelines

2. Authors must download the ACL 2020 style sheets from ICON 2021 mainpage and uncomment line 26 (\aclfinalcopy) in the 'acl2020.tex' file.

3. The deadline for submission of both long and short papers is 15 October, 2021 (GMT -12).

4. The final submission site will be available at https://www.softconf.com/icon2021/papers/ from 25 November, 2021 to 5 December, 2021




Final List of Accepted Papers



Long Papers


Submission IDPaper Title

24

Impact of Microphone position Measurement Error on Multi Channel Distant Speech Recognition & Intelligibility

33

Encoder Decoder Approach to Automated Essay Scoring For Deeper Semantic Analysis

36

Aspect Based Sentiment Analysis Using Spectral Temporal Graph Neural Network

37

ABB-BERT: A BERT model for disambiguating abbreviations and contractions

44

An Effective Approach for Generating Product Description with GPT-2

45

Deep Embedding of Conversation Segments

54

Stress Rules from Surface Forms: Experiments with Program Synthesis

55

CAWESumm: A Contextual and Anonymous Walk Embedding Based Extractive Summarization of Legal Bills

56

A Method to Disambiguate a Word by Using Restricted Boltzmann Machine

58

IE-CPS Lexicon: An Automatic Speech Recognition Oriented Indian-English Pronunciation Dictionary

61

lakṣyārtha (Indicated Meaning) of Śabdavyāpāra (Function of a Word) framework from kāvyaśāstra (The Science of Literary Studies) in Samskṛtam : Its application to Literary Machine Translation and other NLP tasks

67

Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models

71

Prediction of Video Game Development Problems Based on Postmortems using Different Word Embedding Techniques

74

Diformer: Directional Transformer for Neural Machine Translation

78

An Investigation of Hybrid architectures for Low Resource Multilingual Speech Recognition system in Indian context

79

Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation

80

On the Universality of Deep Contextual Language Models

83

Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models

84

Part of Speech Tagging for a Resource Poor Language : Sindhi in Devanagari Script using HMM and CRF

85

Towards Explainable Dialogue System: Explaining Intent Classification using Saliency Techniques

87

Cross-lingual Alignment of Knowledge Graph Triples with Sentences

89

EduMT: Developing Machine Translation System for Educational Content in Indian Languages

90

Multi-task pre-finetuning for zero-shot cross lingual transfer

95

Comparing in context: Improving cosine similarity measures with a metric tensor

97

How vulnerable are you? A Novel Computational Psycholinguistic Analysis for Phishing Influence Detection

98

Semantics of Spatio-Directional Geometric Terms of Indian Languages

103

Context Matters in Semantically Controlled Language Generation for Task-oriented Dialogue Systems

109

Retrofitting of Pre-trained Emotion Words with VAD-dimensions and the Plutchik Emotions

110

Multi-document Text Summarization using Semantic Word and Sentence Similarity: A Combined Approach

113

Weakly Supervised Extraction of Tasks from Text

120

Improve Sinhala Speech Recognition Through e2e LF-MMI Model

130

Assessing Post-editing Effort in the English-Hindi Direction

144

Towards Multimodal Vision-Language Models Generating Non-Generic Text

148

Data Augmentation for Mental Health Classification on Social Media

149

VAE based Text Style Transfer with Pivot Words Enhancement Learning

152

#covid is war and #vaccine is weapon? COVID-19 metaphors in India

156

Image Caption Generation Framework for Assamese News using Attention Mechanism

157

Training data reduction for multilingual Spoken Language Understanding systems

164

Co-attention based Multimodal Factorized Bilinear Pooling for Internet Memes Analysis

168

Leveraging Expectation Maximization for Identifying Claims in Low Resource Indian Languages

170

Studies Towards Language Independent Fake News Detection

171

MRE : Multi Relationship Extractor for Persona based Empathetic Conversational Model

172

Multi-Turn Target-Guided Topic Prediction with Monte Carlo Tree Search

174

Morpheme boundary Detection & Grammatical feature Prediction for Gujarati : Dataset & Model

177

An On-device Deep-Learning Approach for Attribute Extraction from Heterogeneous Unstructured Text

179

Auditing Keyword Queries Over Text Documents

181

Performance of BERT on Persuasion for Good

185

Introduction to ProverbNet: An Online Multilingual Database of Proverbs and Comprehensive Metadata

187

An Experiment on Speech-to-Text Translation Systems for Manipuri to English on Low Resource Setting

188

An Efficient Keyframes Selection Based Framework for Video Captioning

189

Wikipedia Current Events Summarization using Particle Swarm Optimization

190

On the Transferability of Massively Multilingual Pretrained Models in the Pretext of the Indo-Aryan and Tibeto-Burman Languages

191

A Scaled Encoder Decoder Network for Image Captioning in Hindi

203

DialogActs based Search and Retrieval for Response Generation in Conversation Systems

206

Automated Evidence Collection for Fake News Detection



Short Papers


Submission IDPaper Title

7

Generating Slogans with Linguistic Features using Sequence-to-Sequence Transformer

9

Using Integrated Gradients and Constituency Parse Trees to explain Linguistic Acceptability learnt by BERT

18

Resolving Prepositional Phrase Attachment Ambiguities with Contextualized Word Embeddings

28

Constrained Decoding for Technical Term Retention in English-Hindi MT

35

An End-to-End Speech Recognition for the Nepali Language

40

A German Corpus of Reflective Sentences

47

Multi-Source Cross-Lingual Constituency Parsing

52

The Importance of Context in Very Low Resource Language Modeling

73

How effective is incongruity? Implications for code-mixed sarcasm detection

75

Sentiment Analysis For Bengali Using Transformer Based Models

77

Analysis of Manipuri Tones in ManiTo: A Tonal Contrast Database

82

IndicFed: A Federated Approach for Sentiment Analysis in Indic Languages

91

Deep Learning Based Approach For Detecting Suicidal Ideation in Hindi-English Code-Mixed Text: Baseline and Corpus

106

eaVQA: An Experimental Analysis on Visual Question Answering Models

108

Building a Linguistic Resource : A Word Frequency List for Sinhala

115

Temporal Question Generation from History Text

121

Contrastive Learning of Sentence Representations

129

Classifying Verses of the Quran using Doc2vec

131

Kannada Sandhi Generator for Lopa and Adesha Sandhi

143

Evaluating Pretrained Transformer Models for Entity Linking inTask-Oriented Dialog

150

Named Entity-Factored Transformer for Proper Noun Translation

154

Multi-Task Learning for Improving Gender Accuracy in Neural Machine Translation

158

Data Augmentation for Low-Resource Named Entity Recognition Using Backtranslation

173

Stylistic MR-to-Text Generation Using Pre-trained Language Models

176

Cascading Adaptors to Leverage English Data to Improve Performance of Question Answering for Low-Resource Languages

184

An Efficient BERT Based Approach to Detect Aggression and Misogyny

196

Small Batch Sizes Improve Training of Low-Resource Neural MT



Doctoral Consortium Papers


Submission IDPaper Title

2

Bypassing Optimization Complexity through Transfer Learning & Deep Neural Nets for Speech Intelligibility Improvement

3

Design and Development of Spoken Dialogue System in Indic Languages