Papers by Amith Ananthram

6 papers
Event-Guided Denoising for Multilingual Relation Learning (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for general purpose relation extraction use a fixed set of predetermined relations, but research has shifted to the identification of unseen relations in any language.
Approach: They propose a method for collecting high quality relation training data for relation extraction from unlabeled text that achieves a near-recreation of their zero-shot and few-shot results at a fraction of the training cost.
Outcome: The proposed method achieves comparable results to the current state-of-the-art when trained on a smaller multilingual encoder .
Seeded Hierarchical Clustering for Expert-Crafted Taxonomies (2022.findings-emnlp)

Copied to clipboard

Challenge: Practitioners from many disciplines use expert-crafted taxonomies to make sense of large, unlabeled corpora.
Approach: They propose a weakly supervised algorithm for seeded hierarchical clustering that fits unlabeled data to taxonomies using a small set of labeled examples.
Outcome: The proposed algorithm outperforms baselines on three real-world datasets.
Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence (2023.findings-acl)

Copied to clipboard

Challenge: Existing fact-checking benchmarks require systems to verify claims from everyday text against evidence from scientific journal articles.
Approach: They propose a benchmark system that checks claims from news against scientific journal articles and veracity labels.
Outcome: The new benchmark achieves F1 scores of 76.99 and 69.90 on both a fact-checking specific system and GPT-3.5, respectively.
FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context (2023.tacl-1)

Copied to clipboard

Challenge: Experimental results shed light on the emotional connotation of color in context . color is a powerful tool for conveying emotion across cultures .
Approach: They propose a multimodal dataset for exploring the emotional connotation of color as mediated by line, stroke, texture, shape, and language.
Outcome: The proposed model sheds light on the emotional connotation of color in context and the potential for future studies.
Data Caricatures: On the Representation of African American Language in Pretraining Corpora (2025.acl-long)

Copied to clipboard

Challenge: Recent work in linguistics and NLP has investigated the quantity and quality of AAL representation in pretraining corpora.
Approach: They examine the quantity and quality of African American Language (AAL) representation in pretraining corpora.
Outcome: The results show that AAL is underrepresented in all evaluated corpora compared to US demographics . they also show that most automated filters are more likely to conserve white Mainstream English (WME) texts over AAL .
Social Orientation: A New Feature for Dialogue Analysis (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on social orientations in dialogues show they improve performance in low-resource settings.
Approach: They propose to use social orientation tags to model dialogue outcomes . they introduce a new set of dialogue utterances machine-labeled with social orientation tag.
Outcome: The proposed model improves on English and Chinese language benchmarks and shows that social orientation tags explain the outcomes of social interactions when used in neural models.

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