activity
20152026
most citedNeural Module Networks for Reasoning over Text

51 citations · 76 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL2026

CT: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees

S M Rafiuddin, Atriya Sen

Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study…

cs.CL2024

Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM

Zheng Wei Lim, Nitish Gupta, Honglin Yu +1

Multilingual large language models (LLMs) are great translators, but this is largely limited to high-resource languages. For many LLMs, translating in and out of low-resource langu…

cs.CL2024

IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages

Harman Singh, Nitish Gupta, Shikhar Bharadwaj +2

As large language models (LLMs) see increasing adoption across the globe, it is imperative for LLMs to be representative of the linguistic diversity of the world. India is a lingui…

cs.CL2023

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages

Sebastian Ruder, Jonathan H. Clark, Alexander Gutkin +24

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) -- languages for which NLP re-search is part…

cs.CL2021

Enforcing Consistency in Weakly Supervised Semantic Parsing

Nitish Gupta, Sameer Singh, Matt Gardner

The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate searc…

cs.CL2021

Paired Examples as Indirect Supervision in Latent Decision Models

Nitish Gupta, Sameer Singh, Matt Gardner +1

Compositional, structured models are appealing because they explicitly decompose problems and provide interpretable intermediate outputs that give confidence that the model is not…