Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation

D Cer, M Diab, E Agirre, I Lopez-Gazpio… - ar** for a large number of clicks and potentially high social shares, journalists of various
news media outlets publish sensationalist headlines on social media. These headlines lure …

Parameter-free sentence embedding via orthogonal basis

Z Yang, C Zhu, W Chen - arxiv preprint arxiv:1810.00438, 2018 - arxiv.org
We propose a simple and robust non-parameterized approach for building sentence
representations. Inspired by the Gram-Schmidt Process in geometric theory, we build an …

Card-660: Cambridge rare word dataset-a reliable benchmark for infrequent word representation models

MT Pilehvar, D Kartsaklis, V Prokhorov… - arxiv preprint arxiv …, 2018 - arxiv.org
Rare word representation has recently enjoyed a surge of interest, owing to the crucial role
that effective handling of infrequent words can play in accurate semantic understanding …