12 citations · 14 across the 5 of their papers we have counts for
5 papers · 1 filter
Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference
Pedro Colon-Hernandez, Nanxi Liu, Chelsea Joe +5
Generating commonsense assertions within a given story context remains a difficult task for modern language models. Previous research has addressed this problem by aligning commons…
Modeling Empathic Similarity in Personal Narratives
Jocelyn Shen, Maarten Sap, Pedro Colon-Hernandez +2
The most meaningful connections between people are often fostered through expression of shared vulnerability and emotional experiences in personal narratives. We introduce a new ta…
Adversarial Transformer Language Models for Contextual Commonsense Inference
Pedro Colon-Hernandez, Henry Lieberman, Yida Xin +3
Contextualized or discourse aware commonsense inference is the task of generating coherent commonsense assertions (i.e., facts) from a given story, and a particular sentence from t…
RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations
Pedro Colon-Hernandez, Yida Xin, Henry Lieberman +3
Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). However, retrofitting…
Combining pre-trained language models and structured knowledge
Pedro Colon-Hernandez, Catherine Havasi, Jason Alonso +2
In recent years, transformer-based language models have achieved state of the art performance in various NLP benchmarks. These models are able to extract mostly distributional info…