Ranking Loss
Related Papers
Specialized Models and Ranking for Coreference Resolution
This paper investigates two strategies for im- proving coreference resolution: (1) training separate models that specialize in particu- lar types of mentions (e.g., pronouns versus proper nouns) and (2) using …...
Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data
AbstractIn practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context …...
Ranking-Based Autoencoder for Extreme Multi-label Classification
AbstractExtreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the …...
Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
AbstractIn this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in …...
Contrastive Fine-tuning Improves Robustness for Neural Rankers
The performance of state-of-the-art neural rankers can deteriorate substantially when ex- posed to noisy inputs or applied to a new domain. In this paper, we present a novel method for …...