Search Results for author:
Found 15 papers, 10 papers with code
Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics
In this study, we probe different families of Large Language Models such as GPT-4 for their knowledge of the lexical semantics of scalar adjectives and one specific aspect of their pragmatics, namely scalar diversity.
STEntConv: Predicting Disagreement with Stance Detection and a Signed Graph Convolutional Network
The rise of social media platforms has led to an increase in polarised online discussions, especially on political and socio-cultural topics such as elections and climate change.
Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
Reasoning about asynchronous plans is challenging since it requires sequential and parallel planning to optimize time costs.
Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology
We propose a fully unsupervised method to detect bias in contextualized embeddings.
Forecasting COVID-19 Caseloads Using Unsupervised Embedding Clusters of Social Media Posts
We present a novel approach incorporating transformer-based language models into infectious disease modelling.
Geographic Adaptation of Pretrained Language Models
While pretrained language models (PLMs) have been shown to possess a plethora of linguistic knowledge, the existing body of research has largely neglected extralinguistic knowledge, which is generally difficult to obtain by pretraining on text alone.
Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks
To address this issue, we propose two contrasting paradigms for data annotation.
Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsity
The increasing polarization of online political discourse calls for computational tools that automatically detect and monitor ideological divides in social media.
Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media
Token-level analysis shows that temporal adaptation captures event-driven changes in language use in the downstream task, but not those changes that are actually relevant to task performance.
Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words
How does the input segmentation of pretrained language models (PLMs) affect their interpretations of complex words?
HateCheck: Functional Tests for Hate Speech Detection Models
Detecting online hate is a difficult task that even state-of-the-art models struggle with.
Dynamic Contextualized Word Embeddings
Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts.
DagoBERT: Generating Derivational Morphology with a Pretrained Language Model
Can pretrained language models (PLMs) generate derivationally complex words?
A model of grassroots changes in linguistic systems
But most linguistic changes are grassroots developments that originate with ordinary people.
