Search Results for author: Aditya Joshi

Found 54 papers, 8 papers with code

IISERB Brains at SemEval-2022 Task 6: A Deep-learning Framework to Identify Intended Sarcasm in English

no code implementations SemEval (NAACL) 2022 Tanuj Shekhawat, Manoj Kumar, Udaybhan Rathore, Aditya Joshi, Jasabanta Patro

This paper describes the system architectures and the models submitted by our team “IISERB Brains” to SemEval 2022 Task 6 competition.

BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM

no code implementations17 Jun 2024 Zhewen Shen, Aditya Joshi, Ruey-Cheng Chen

Children from bilingual backgrounds benefit from interactions with parents and teachers to re-acquire their heritage language.

Continual Pretraining Zero-Shot Learning

Spectraformer: A Unified Random Feature Framework for Transformer

1 code implementation24 May 2024 Duke Nguyen, Aditya Joshi, Flora Salim

We identify the need for a systematic comparison of different combinations of weight matrix and component functions for attention learning in Transformer.

Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy

no code implementations16 May 2024 Aditya Joshi, Jake Renzella, Pushpak Bhattacharyya, Saurav Jha, Xiangyu Zhang

While deep learning approaches represent the state-of-the-art of natural language processing (NLP) today, classical algorithms and approaches still find a place in NLP textbooks and courses of recent years.

Evaluating Dialect Robustness of Language Models via Conversation Understanding

1 code implementation9 May 2024 Dipankar Srirag, Aditya Joshi

With an evergrowing number of LLMs reporting superlative performance for English, their ability to perform equitably for different dialects of English (i. e., dialect robustness) needs to be ascertained.

Natural Language Processing for Dialects of a Language: A Survey

no code implementations11 Jan 2024 Aditya Joshi, Raj Dabre, Diptesh Kanojia, Zhuang Li, Haolan Zhan, Gholamreza Haffari, Doris Dippold

Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.

Attribute Machine Translation +4

Relation Extraction from News Articles (RENA): A Tool for Epidemic Surveillance

no code implementations31 Oct 2023 Jaeff Hong, Duong Dung, Danielle Hutchinson, Zubair Akhtar, Rosalie Chen, Rebecca Dawson, Aditya Joshi, Samsung Lim, C Raina MacIntyre, Deepti Gurdasani

Relation Extraction from News Articles (RENA) is a browser-based tool designed to extract key entities and their semantic relationships in English language news articles related to infectious diseases.

Relation Relation Extraction

Stacking the Odds: Transformer-Based Ensemble for AI-Generated Text Detection

1 code implementation29 Oct 2023 Duke Nguyen, Khaing Myat Noe Naing, Aditya Joshi

This paper reports our submission under the team name `SynthDetectives' to the ALTA 2023 Shared Task.

Text Detection

Evaluation of large language models using an Indian language LGBTI+ lexicon

no code implementations26 Oct 2023 Aditya Joshi, Shruta Rawat, Alpana Dange

The methodology presented in this paper can be useful for LGBTI+ lexicons in other languages as well as other domain-specific lexicons.

Machine Translation Natural Language Understanding

Applications and Challenges of Sentiment Analysis in Real-life Scenarios

no code implementations24 Jan 2023 Diptesh Kanojia, Aditya Joshi

Sentiment analysis has benefited from the availability of lexicons and benchmark datasets created over decades of research.

Selection bias Sentiment Analysis

Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks

no code implementations Findings (ACL) 2022 Ashutosh Kumar, Aditya Joshi

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models.

Classification

IISERB Brains at SemEval 2022 Task 6: A Deep-learning Framework to Identify Intended Sarcasm in English

1 code implementation4 Mar 2022 Tanuj Singh Shekhawat, Manoj Kumar, Udaybhan Rathore, Aditya Joshi, Jasabanta Patro

This paper describes the system architectures and the models submitted by our team "IISERBBrains" to SemEval 2022 Task 6 competition.

Recommendation Chart of Domains for Cross-Domain Sentiment Analysis: Findings of A 20 Domain Study

no code implementations LREC 2020 Akash Sheoran, Diptesh Kanojia, Aditya Joshi, Pushpak Bhattacharyya

Cross-domain sentiment analysis (CDSA) helps to address the problem of data scarcity in scenarios where labelled data for a domain (known as the target domain) is unavailable or insufficient.

Sentence Sentiment Analysis +1

Recommendation Chart of Domains for Cross-Domain Sentiment Analysis:Findings of A 20 Domain Study

no code implementations9 Apr 2020 Akash Sheoran, Diptesh Kanojia, Aditya Joshi, Pushpak Bhattacharyya

Cross-domain sentiment analysis (CDSA) helps to address the problem of data scarcity in scenarios where labelled data for a domain (known as the target domain) is unavailable or insufficient.

Sentence Sentiment Analysis +1

Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection

no code implementations ACL 2019 Adith Iyer, Aditya Joshi, Sarvnaz Karimi, Ross Sparks, Cecile Paris

The introduction of figurative usage detection results in an average improvement of 2. 21% F-score of personal health mention detection, in the case of the feature augmentation-based approach.

Sentence

Does Multi-Task Learning Always Help?: An Evaluation on Health Informatics

no code implementations ALTA 2019 Aditya Joshi, Sarvnaz Karimi, Ross Sparks, Cecile Paris, C Raina MacIntyre

Multi-Task Learning (MTL) has been an attractive approach to deal with limited labeled datasets or leverage related tasks, for a variety of NLP problems.

Classification General Classification +1

Red-faced ROUGE: Examining the Suitability of ROUGE for Opinion Summary Evaluation

no code implementations ALTA 2019 Wenyi Tay, Aditya Joshi, Xiuzhen Zhang, Sarvnaz Karimi, Stephen Wan

Opinion summarisation requires to correctly pair two types of semantic information: (1) aspect or opinion target; and (2) polarity of candidate and reference summaries.

Survey of Text-based Epidemic Intelligence: A Computational Linguistic Perspective

no code implementations14 Mar 2019 Aditya Joshi, Sarvnaz Karimi, Ross Sparks, Cecile Paris, C Raina MacIntyre

Epidemic intelligence deals with the detection of disease outbreaks using formal (such as hospital records) and informal sources (such as user-generated text on the web) of information.

Event Detection General Classification

Hate Speech Detection from Code-mixed Hindi-English Tweets Using Deep Learning Models

1 code implementation13 Nov 2018 Satyajit Kamble, Aditya Joshi

This paper reports an increment to the state-of-the-art in hate speech detection for English-Hindi code-mixed tweets.

Hate Speech Detection

Computational Sarcasm

no code implementations EMNLP 2017 Pushpak Bhattacharyya, Aditya Joshi

In case of each of these algorithms, we refer to our work on sarcasm detection and share our learnings.

Sarcasm Detection Sentiment Analysis

Expect the unexpected: Harnessing Sentence Completion for Sarcasm Detection

no code implementations19 Jul 2017 Aditya Joshi, Samarth Agrawal, Pushpak Bhattacharyya, Mark Carman

However, since the exact word where such an incongruity occurs may not be known in advance, we present two approaches: an All-words approach (which consults sentence completion for every content word) and an Incongruous words-only approach (which consults sentence completion for the 50% most incongruous content words).

Sarcasm Detection Sentence +1

`Who would have thought of that!': A Hierarchical Topic Model for Extraction of Sarcasm-prevalent Topics and Sarcasm Detection

no code implementations WS 2016 Aditya Joshi, Prayas Jain, Pushpak Bhattacharyya, Mark Carman

Designed on the basis of the intuition that sarcastic tweets are likely to have a mixture of words of both sentiments as against tweets with literal sentiment (either positive or negative), our hierarchical topic model discovers sarcasm-prevalent topics and topic-level sentiment.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text

3 code implementations COLING 2016 Ameya Prabhu, Aditya Joshi, Manish Shrivastava, Vasudeva Varma

We introduce a Hindi-English (Hi-En) code-mixed dataset for sentiment analysis and perform empirical analysis comparing the suitability and performance of various state-of-the-art SA methods in social media.

Opinion Mining Sentiment Analysis

Automatic Identification of Sarcasm Target: An Introductory Approach

no code implementations22 Oct 2016 Aditya Joshi, Pranav Goel, Pushpak Bhattacharyya, Mark Carman

To compare our approach, we use two baselines: a na\"ive baseline and another baseline based on work in sentiment target identification.

Sarcasm Detection Sentence

Are Word Embedding-based Features Useful for Sarcasm Detection?

no code implementations EMNLP 2016 Aditya Joshi, Vaibhav Tripathi, Kevin Patel, Pushpak Bhattacharyya, Mark Carman

For example, this augmentation results in an improvement in F-score of around 4\% for three out of these four feature sets, and a minor degradation in case of the fourth, when Word2Vec embeddings are used.

Sarcasm Detection Semantic Similarity +2

A Computational Approach to Automatic Prediction of Drunk Texting

no code implementations4 Oct 2016 Aditya Joshi, Abhijit Mishra, Balamurali AR, Pushpak Bhattacharyya, Mark Carman

Alcohol abuse may lead to unsociable behavior such as crime, drunk driving, or privacy leaks.

That'll Do Fine!: A Coarse Lexical Resource for English-Hindi MT, Using Polylingual Topic Models

no code implementations LREC 2016 Diptesh Kanojia, Aditya Joshi, Pushpak Bhattacharyya, Mark James Carman

As demonstrated by the quality of our coarse lexical resource and its benefit to MT, we believe that our sentential approach to create such a resource will help MT for resource-constrained languages.

Machine Translation Topic Models +1

Language Recognition using Random Indexing

no code implementations22 Dec 2014 Aditya Joshi, Johan Halseth, Pentti Kanerva

Random Indexing is a simple implementation of Random Projections with a wide range of applications.

Cost and Benefit of Using WordNet Senses for Sentiment Analysis

no code implementations LREC 2012 Balamurali AR, Aditya Joshi, Pushpak Bhattacharyya

However, a moot question is ''''''``is the accuracy improvement commensurate with the cost incurred in annotation''''''''?

Sentiment Analysis

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