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.
A Critique of the Smooth Inverse Frequency Sentence Embeddings
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- Pitfalls in the Evaluation of Sentence Embeddings (2019)52% match
- Learning and Evaluating Sparse Interpretable Sentence Embeddings (2018)50% match
- Audio-Linguistic Embeddings for Spoken Sentences (2019)50% match
- Evaluation of sentence embeddings in downstream and linguistic probing tasks (2018)49% match
- In Search for Linear Relations in Sentence Embedding Spaces (2019)49% match
- Finding Meaning in Embeddings: Concept Separation Curves (2026)49% match
- On the Sentence Embeddings from Pre-trained Language Models (2020)49% match
- When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation (2026)49% match