Search Results for author:
Found 11 papers, 3 papers with code
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little Cost
State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words. To address this issue, we follow the principle of mimick-like models to generate vectors for unseen words, by learning the behavior of pre-trained embeddings using only the surface form of words. We present a simple contrastive learning framework, LOVE, which extends the word representation of an existing pre-trained language model (such as BERT) and makes it robust to OOV with few additional parameters. Extensive evaluations demonstrate that our lightweight model achieves similar or even better performances than prior competitors, both on original datasets and on corrupted variants.
Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation
Speech characteristics vary from speaker to speaker.
MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification
We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets.
YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy
Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval.
BELLA: Black box model Explanations by Local Linear Approximations
BELLA provides explanations in the form of a linear model trained in the feature space.
Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey
General-purpose knowledge bases (KBs) are a cornerstone of knowledge-centric AI.
Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
Equipping machines with comprehensive knowledge of the world's entities and their relationships has been a long-standing goal of AI.
NeuroQuery: comprehensive meta-analysis of human brain mapping
Reaching a global view of brain organization requires assembling evidence on widely different mental processes and mechanisms.
Text to brain: predicting the spatial distribution of neuroimaging observations from text reports
In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms.
