13 citations · 17 across the 6 of their papers we have counts for
12 papers · 1 filter
Understanding Hard Negatives in Noise Contrastive Estimation
Wenzheng Zhang, Karl Stratos
The choice of negative examples is important in noise contrastive estimation. Recent works find that hard negatives -- highest-scoring incorrect examples under the model -- are eff…
Fast and Effective Biomedical Entity Linking Using a Dual Encoder
Rajarshi Bhowmik, Karl Stratos, Gerard de Melo
Biomedical entity linking is the task of identifying mentions of biomedical concepts in text documents and mapping them to canonical entities in a target thesaurus. Recent advancem…
Data-to-text Generation by Splicing Together Nearest Neighbors
Sam Wiseman, Arturs Backurs, Karl Stratos
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions…
Unsupervised Label Refinement Improves Dataless Text Classification
Zewei Chu, Karl Stratos, Kevin Gimpel
Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising…
Corrected CBOW Performs as well as Skip-gram
Ozan İrsoy, Adrian Benton, Karl Stratos
Mikolov et al. (2013a) observed that continuous bag-of-words (CBOW) word embeddings tend to underperform Skip-gram (SG) embeddings, and this finding has been reported in subsequent…
Mining Knowledge for Natural Language Inference from Wikipedia Categories
Mingda Chen, Zewei Chu, Karl Stratos +1
Accurate lexical entailment (LE) and natural language inference (NLI) often require large quantities of costly annotations. To alleviate the need for labeled data, we introduce Wik…