Papers by Surya Nepal

4 papers
Recognising Agreement and Disagreement between Stances with Reason Comparing Networks (P19-1)

Copied to clipboard

Challenge: Existing methods for (dis)agreement detection focus on conversational settings . however, non-dialogic stance-bearing utterances are common in real-world scenarios .
Approach: They propose a reason comparing network to leverage reason information for stance comparison.
Outcome: The proposed method outperforms baselines on a well-known stance corpus.
Cross-Target Stance Classification with Self-Attention Networks (P18-2)

Copied to clipboard

Challenge: In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually trained for prediction on the same target.
Approach: They propose a neural model that can generalize classifiers between different targets by finding useful information shared between relevant targets.
Outcome: The proposed model can generalize between relevant targets and find useful information shared between relevant target domains which improves generalization in certain scenarios.
Assessing Social License to Operate from the Public Discourse on Social Media (2020.coling-industry)

Copied to clipboard

Challenge: Social License to Operate (SLO) is the level of support organisations gain from the public.
Approach: They propose to extract and transform peoples’ stances towards an organisation into SLO levels by performing a chain of three text classification tasks.
Outcome: The proposed system extracts and transforms peoples’ stances towards an organisation into SLO levels.
Adversarial Attacks Against Automated Fact-Checking: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Existing fact-checking systems are vulnerable to adversarial attacks that manipulate or generate claims, evidence, or claim-evidence pairs.
Approach: They examine the impact of adversarial attacks on existing AFC systems and examine their impact on existing ones.
Outcome: The findings highlight the need for resilient fact-checking frameworks in limiting misinformation spread and supporting public trust.

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