Search Results for author:
Found 10 papers, 7 papers with code
Towards Reproducible Machine Learning Research in Natural Language Processing
While recent progress in the field of ML has been significant, the reproducibility of these cutting-edge results is often lacking, with many submissions lacking the necessary information in order to ensure subsequent reproducibility.
Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning
Hence, contrastive losses are not sufficient to learn task-optimal representations, i. e., representations that contain all task-relevant information shared between the image and associated captions.
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
By including approximate nearest neighbour phrases (ANN-P) in the context list, we encourage the learned representation to disambiguate between similar, but not identical, biasing phrases.
A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing
The validity of "attention as explanation" has so far been evaluated by computing the rank correlation between attention-based explanations and existing feature attribution explanations using LSTM-based models.
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval
We add an additional decoder to the contrastive ICR framework, to reconstruct the input caption in a latent space of a general-purpose sentence encoder, which prevents the image and caption encoder from suppressing predictive features.
Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?
Recent progress in metric learning has given rise to new loss functions that outperform the triplet loss on tasks such as image retrieval and representation learning.
Extending CLIP for Category-to-image Retrieval in E-commerce
One aspect of this data is a category tree that is being used in search and recommendation.
Reproducibility as a Mechanism for Teaching Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence
In this work, we explain the setup for a technical, graduate-level course on Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence (FACT-AI) at the University of Amsterdam, which teaches FACT-AI concepts through the lens of reproducibility.
Conditional Image Generation and Manipulation for User-Specified Content
This can be done by conditioning the model on additional information.
Bidirectional Scene Text Recognition with a Single Decoder
We introduce the bidirectional Scene Text Transformer (Bi-STET), a novel bidirectional STR method with a single decoder for bidirectional text decoding.
