Search Results for author:
Found 12 papers, 3 papers with code
Explainable Assessment of Healthcare Articles with QA
The healthcare domain suffers from the spread of poor quality articles on the Internet.
Self-Supervised Pretraining for Heterogeneous Hypergraph Neural Networks
SPHH is consist of two self-supervised pretraining tasks that aim to simultaneously learn both local and global representations of the entities in the hypergraph by using informative representations derived from the hypergraph structure.
Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?
In the past few years, deep learning methods have attracted a lot of research, and are now heavily used in modern real-world recommender systems.
KILT: a Benchmark for Knowledge Intensive Language Tasks
We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance.
Ranked #3 on
Entity Linking
on KILT: WNED-CWEB
Concept Matching for Low-Resource Classification
We propose a model to tackle classification tasks in the presence of very little training data.
How Decoding Strategies Affect the Verifiability of Generated Text
A generated sentence is verifiable if it can be corroborated or disproved by Wikipedia, and we find that the verifiability of generated text strongly depends on the decoding strategy.
Soft Token Matching for Interpretable Low-Resource Classification
We propose a model to tackle classification tasks in the presence of very little training data.
attr2vec: Jointly Learning Word and Contextual Attribute Embeddings with Factorization Machines
Our experimental results on a text classification task demonstrate that using attr2vec to jointly learn embeddings for words and Part-of-Speech (POS) tags improves results compared to learning the embeddings independently.
A Comparison of Two Paraphrase Models for Taxonomy Augmentation
Our results show that paraphrasing is a viable method to enrich a taxonomy with more terms, and that Moses consistently outperforms the sequence-to-sequence neural model.
Say the Right Thing Right: Ethics Issues in Natural Language Generation Systems
We discuss the ethical implications of Natural Language Generation systems.
Ethical by Design: Ethics Best Practices for Natural Language Processing
While a number of previous works exist that discuss ethical issues, in particular around big data and machine learning, to the authors{'} knowledge this is the first account of NLP and ethics from the perspective of a principled process.
