Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS
This work addresses a critical gap in evaluating sentence encoders for NLP researchers, though it is incremental as it builds on existing benchmark methods.
The authors tackled the problem that existing sentence encoder benchmarks only measure overall similarity with a single number and lack high lexical overlap pairs, by introducing HEROS, a diagnostic dataset of minimal pairs with high lexical overlap, and found that most unsupervised encoders are insensitive to negation and that training data determines similarity judgments, revealing blind spots in traditional benchmarks.
Existing sentence textual similarity benchmark datasets only use a single number to summarize how similar the sentence encoder's decision is to humans'. However, it is unclear what kind of sentence pairs a sentence encoder (SE) would consider similar. Moreover, existing SE benchmarks mainly consider sentence pairs with low lexical overlap, so it is unclear how the SEs behave when two sentences have high lexical overlap. We introduce a high-quality SE diagnostic dataset, HEROS. HEROS is constructed by transforming an original sentence into a new sentence based on certain rules to form a \textit{minimal pair}, and the minimal pair has high lexical overlaps. The rules include replacing a word with a synonym, an antonym, a typo, a random word, and converting the original sentence into its negation. Different rules yield different subsets of HEROS. By systematically comparing the performance of over 60 supervised and unsupervised SEs on HEROS, we reveal that most unsupervised sentence encoders are insensitive to negation. We find the datasets used to train the SE are the main determinants of what kind of sentence pairs an SE considers similar. We also show that even if two SEs have similar performance on STS benchmarks, they can have very different behavior on HEROS. Our result reveals the blind spot of traditional STS benchmarks when evaluating SEs.