Search Results for author:
Found 17 papers, 9 papers with code
Learning Shortcuts: On the Misleading Promise of NLU in Language Models
The advent of large language models (LLMs) has enabled significant performance gains in the field of natural language processing.
Calibration Error Estimation Using Fuzzy Binning
Neural network-based decisions tend to be overconfident, where their raw outcome probabilities do not align with the true decision probabilities.
COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models
A characteristic feature of human semantic cognition is its ability to not only store and retrieve the properties of concepts observed through experience, but to also facilitate the inheritance of properties (can breathe) from superordinate concepts (animal) to their subordinates (dog) -- i. e. demonstrate property inheritance.
A Property Induction Framework for Neural Language Models
To what extent can experience from language contribute to our conceptual knowledge?
On Information Hiding in Natural Language Systems
With data privacy becoming more of a necessity than a luxury in today's digital world, research on more robust models of privacy preservation and information security is on the rise.
Towards The Automatic Coding of Medical Transcripts to Improve Patient-Centered Communication
The result showed that there is evidence to distinguish the codes, and this is considered to be sufficient for training of human annotators.
Do language models learn typicality judgments from text?
Building on research arguing for the possibility of conceptual and categorical knowledge acquisition through statistics contained in language, we evaluate predictive language models (LMs) -- informed solely by textual input -- on a prevalent phenomenon in cognitive science: typicality.
Fuzzy Classification of Multi-intent Utterances
In this work, we propose a scheme to address the ambiguity in single-intent as well as multi-intent natural language utterances by creating degree memberships over fuzzified intent classes.
Low Anisotropy Sense Retrofitting (LASeR) : Towards Isotropic and Sense Enriched Representations
Contextual word representation models have shown massive improvements on a multitude of NLP tasks, yet their word sense disambiguation capabilities remain poorly explained.
Finding Fuzziness in Neural Network Models of Language Processing
Humans often communicate by using imprecise language, suggesting that fuzzy concepts with unclear boundaries are prevalent in language use.
Modeling Fuzzy Cluster Transitions for Topic Tracing
Twitter can be viewed as a data source for Natural Language Processing (NLP) tasks.
Tracing Topic Transitions with Temporal Graph Clusters
Twitter serves as a data source for many Natural Language Processing (NLP) tasks.
Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification
We propose a hybrid Graph-of-Tweets (GoT) model which combines the word- and document-level structures for modeling Tweets.
Misspelling Correction with Pre-trained Contextual Language Model
While many programs provide spelling correction functionality, many systems do not take context into account.
Model Choices Influence Attributive Word Associations: A Semi-supervised Analysis of Static Word Embeddings
Static word embeddings encode word associations, extensively utilized in downstream NLP tasks.
Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming
Models trained to estimate word probabilities in context have become ubiquitous in natural language processing.
An Event Detection Approach Based On Twitter Hashtags
We adopted the feature extraction used in STREAMCUBE and applied a clustering K-means approach to it.
