Papers by Tirthankar Ghosal

11 papers
DeepSentiPeer: Harnessing Sentiment in Review Texts to Recommend Peer Review Decisions (P19-1)

Copied to clipboard

Challenge: Existing peer review system is not straightforward and requires domain knowledge, expertise, and intelligence of human reviewers, which is somewhat elusive with the current state of AI.
Approach: They propose to use peer review texts to predict acceptance or rejection of a manuscript based on reviewer sentiment.
Outcome: The proposed deep neural architecture achieves significant performance improvement over baselines (29% error reduction) in a recently released dataset of peer reviews.
MixRevDetect: Towards Detecting AI-Generated Content in Hybrid Peer Reviews. (2025.naacl-short)

Copied to clipboard

Challenge: Existing methods for detecting fully AI-generated peer reviews fail to detect finer-grained AI-generated points within mixed-authorship reviews.
Approach: They propose a method to identify AI-generated points in peer reviews using large language models . their approach achieved an F1 score of 88.86%, significantly outperforming existing methods .
Outcome: The proposed method outperforms existing methods in identifying AI-generated points in peer reviews.
Longform Multimodal Lay Summarization of Scientific Papers: Towards Automatically Generating Science Blogs from Research Articles (2024.lrec-main)

Copied to clipboard

Challenge: Science blogs and lay-speak are critical to communicating scientific information to the general public and policymakers.
Approach: They propose to use presentation transcripts and slides to generate a scientific blog from a research article in layperson's terms.
Outcome: The proposed approach can generate a blog text and select the most relevant figures to explain a research article in layperson’s terms, essentially a science blog.
When Reviewers Lock Horns: Finding Disagreements in Scientific Peer Reviews (2023.emnlp-main)

Copied to clipboard

Challenge: despite being widely accepted standard for validating scholarly research, peer-review process has faced criticism.
Approach: They propose a task of automatically identifying contradictions among reviewers on a given article.
Outcome: The proposed model detects contradictory statements from the review pairs and makes it publicly available for further investigations.
Novelty Goes Deep. A Deep Neural Solution To Document Level Novelty Detection (C18-1)

Copied to clipboard

Challenge: Existing methods for document-level novelty detection are limited and do not require manual feature engineering.
Approach: They propose a deep Convolutional Neural Networks based model to classify a document as novel or redundant on the basis of documents already seen by the system.
Outcome: The proposed model outperforms the state-of-the-art on a document-level novelty detection dataset by a margin of 5% in terms of accuracy.
The lack of theory is painful: Modeling Harshness in Peer Review Comments (2022.aacl-main)

Copied to clipboard

Challenge: a new study shows that peer-review has a power imbalance, making it fraught for authors . authors argue that a little more effort to remain critical but be constructive would help foster a positive outcome .
Approach: They propose to use a dataset to show peer-review comments' harshness scores . they argue that this moderation could help authors to be more constructive .
Outcome: The proposed dataset shows that it can be used to make peer reviews less hurtful and more welcoming.
ELITR Minuting Corpus: A Novel Dataset for Automatic Minuting from Multi-Party Meetings in English and Czech (2022.lrec-1)

Copied to clipboard

Challenge: Automated minuting is a rather unstructured writing activity and can be difficult due to a variety of factors including the quality of automatic speech recorders, availability of public meeting data, subjective knowledge of the minuter, etc.
Approach: They propose a dataset on automatic minuting which includes transcripts from ASRs and minuted by annotators.
Outcome: The proposed dataset covers more than 160 hours of meeting content.
TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection (L18-1)

Copied to clipboard

Challenge: Detecting novelty of an entire document is an AI frontier problem . present state-of-the-art text matching techniques are unable to process such redundancy.
Approach: They propose a document-level novelty detection resource that can be used to benchmark techniques . they crawl news documents across several domains and use it to find out whether they contain new information .
Outcome: The proposed dataset is compared with a standard system for document novelty detection . the proposed system can detect elements that have not appeared before, or new or original .
‘Quis custodiet ipsos custodes?’ Who will watch the watchmen? On Detecting AI-generated peer-reviews (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on generic AI-generated text detection or estimating fraction of peer-reviews that can be AI-generated.
Approach: They propose a model that detects whether a peer-review is written by ChatGPT and a reviewer-generated model that generates similar outputs upon re-prompting.
Outcome: The proposed model is more robust, but paraphrasing is more effective.
MMM: An Emotion and Novelty-aware Approach for Multilingual Multimodal Misinformation Detection (2022.findings-aacl)

Copied to clipboard

Challenge: Increasing presence of multimedia content on the web promotes misinformation . detecting this category of misleading information is almost impossible without prior knowledge .
Approach: They propose a novel multilingual multimodal misinformation dataset that includes background knowledge of misleading articles.
Outcome: The proposed model outperforms the state-of-the-art on misinformation detection task.
Can Large Language Models Unlock Novel Scientific Research Ideas? (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) and ChatGPT have marked a turning point in the integration of Artificial Intelligence (AI) into people’s everyday lives.
Approach: They conduct a human evaluation of the novelty, relevancy, and feasibility of the generated future research ideas.
Outcome: The proposed models generate more diverse ideas than GPT-4, GPT-3.5, and Gemini 1.0.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations