Papers by Vasudeva Varma

10 papers
ELDEN: Improved Entity Linking Using Densified Knowledge Graphs (N18-1)

Copied to clipboard

Challenge: Entity Linking (EL) systems aim to automatically map mentions of an entity in text to the corresponding entity in Knowledge Graph (KG).
Approach: They propose to densify the Knowledge Graph (KG) with co-occurrence statistics and then use the densified KG to train entity embeddings.
Outcome: The proposed system outperforms state-of-the-art EL systems on benchmark datasets and outperformed state- of-the art systems on sparsely connected entities in the KG.
Leveraging Mental Health Forums for User-level Depression Detection on Social Media (2022.lrec-1)

Copied to clipboard

Challenge: Existing methods to detect depression on social media platforms are limited due to the vastness of social media content and the lack of linguistic features.
Approach: They propose to optimize the performance of user-level depression classification to lessen the burden on computational resources.
Outcome: The proposed system outperforms baselines across standard metrics for the task of depression detection in text.
Multi-label Categorization of Accounts of Sexism using a Neural Framework (D19-1)

Copied to clipboard

Challenge: Sexism manifests in blatant as well as subtle ways, authors say . existing work on sexism classification has limitations in terms of categories used . authors: categorization of accounts of sexist behavior can aid in countering sextism .
Approach: They propose a neural solution that can combine sentence representations with distributional and linguistic word embeddings.
Outcome: a new method outperforms deep learning and traditional methods by an appreciable margin . the proposed method outpersforms several deep learning as well as traditional baselines by an approval margin compared to baselines .
Predicting Clickbait Strength in Online Social Media (2020.coling-main)

Copied to clipboard

Challenge: Clickbaits are sensational, provocative or controversial posts that entice readers to click on them.
Approach: They propose to model clickbait strength prediction using transformers to predict clickbaiting intensity.
Outcome: The proposed model outperforms existing methods on a benchmark dataset with 39K posts on 3K posts.
Extraction of Message Sequence Charts from Software Use-Case Descriptions (N19-2)

Copied to clipboard

Challenge: Software Requirement Specification documents provide natural language descriptions of the core functional requirements as a set of use-cases.
Approach: They propose a linguistic knowledge-based approach to extract software requirements from use-cases using a textual representation of the core functional requirements.
Outcome: The proposed method performs better than existing techniques and improves performance.
All Prompts Are Created Equal? Evaluating Robustness of LLM Judges Against Non-Adversarial Prompt Variations (2026.findings-acl)

Copied to clipboard

Challenge: Our work establishes new standards for assessing LLM judge reliability beyond simple accuracy metrics.
Approach: They propose a diagnostic framework grounded in attribute verifiability that enables principled decisions about evaluation automation.
Outcome: The proposed framework establishes new standards for assessing LLM judge reliability beyond simple accuracy metrics.
When science journalism meets artificial intelligence : An interactive demonstration (D18-2)

Copied to clipboard

Challenge: Existing tools for automating science journalism do not provide adequate training for AIs to be trained.
Approach: They propose an online tool that generates titles of blog titles by mimicking a human science journalist.
Outcome: The proposed tool generates blog titles by mimicking a human science journalist . it is evaluated using standard metrics to show its viability .
Identification of Alias Links among Participants in Narratives (P18-2)

Copied to clipboard

Challenge: Identifying distinct and independent participants in a narrative is crucial for many NLP applications.
Approach: They propose an approach based on linguistic knowledge for identification of aliases mentioned using proper nouns, pronouns or noun phrases with common noun headword.
Outcome: The proposed approach performs better than the state-of-the-art approach on four diverse history narratives of varying complexity.
Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification (2020.coling-main)

Copied to clipboard

Challenge: Sexism is a form of oppression based on one's sex and is reported online in numerous ways.
Approach: They propose a multi-task approach for fine-grained multi-label sexism classification that leverages several supporting tasks without incurring manual labeling cost.
Outcome: The proposed method outperforms the state-of-the-art for multi-label sexism classification on a recently released dataset across five standard metrics.
A Workbench for Rapid Generation of Cross-Lingual Summaries (L18-1)

Copied to clipboard

Challenge: a tool for automating cross-lingual information access is needed in multilingual societies . current state of machine translation is not able to generate publishable articles from English .
Approach: They propose a web-based tool for human editing of cross-lingual summaries . it generates publishable summary in a number of Indian Languages for news articles originally published in english .
Outcome: The proposed tool can generate publishable summaries in multiple languages with minimal human effort and collect detailed logs on the process.

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