Skip to content
conftrace_
2020 AAAI AAAI 2020

A Critique of the Smooth Inverse Frequency Sentence Embeddings (Student Abstract)

Abstract

Abstract We critically review the smooth inverse frequency sentence embedding method of Arora, Liang, and Ma (2017), and show inconsistencies in its setup, derivation and evaluation.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - theoretical analysis

Authors

Aidana Karipbayeva, Alena Sorokina, Zhenisbek Assylbekov

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Theory Natural Language Processing > Resources & Methods > Lexical Semantics Natural Language Processing > Resources & Methods > Text Representation Deep Learning > Models > Language Modeling

Keywords

unsupervised learning natural language inference lexical semantics text representation theoretical analysis word embedding sentence embedding smooth inverse frequency
Download PDF

More from AAAI 2020

All AAAI 2020 papers →
Leveraging BERT with Mixup for Sentence Classification (Student Abstract)
Determining the Possibility of Transfer Learning in Deep Reinforcement Learning Using Grad-CAM (Student Abstract)
Exploring the Benefits of Depth Information in Object Pixel Masking (Student Abstract)
Multidimensional Analysis of Trust in News Articles (Student Abstract)
Algorithmic Bias in Recidivism Prediction: A Causal Perspective (Student Abstract)
New Off-Board Solution for Predicting Vehicles' Intentions in the Highway On-Ramp Using Probabilistic Classifiers (Student Abstract)