Is Probing All You Need? Indicator Tasks as an Alternative to Probing Embedding Spaces
This addresses the issue of entanglement in probing methods for researchers in NLP, offering an incremental improvement for explainability and bias removal.
The paper tackles the problem of evaluating linguistic information in word embeddings by introducing indicator tasks as a non-trainable alternative to probes, showing they provide a more accurate picture in test cases like gender debiasing and morphological erasure.
The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple classification tasks, termed probes, to evaluate the information encoded in the embedding space. However, the involvement of a trainable classifier leads to entanglement between the probe's results and the classifier's nature. As a result, contemporary works on probing include tasks that do not involve training of auxiliary models. In this work we introduce the term indicator tasks for non-trainable tasks which are used to query embedding spaces for the existence of certain properties, and claim that this kind of tasks may point to a direction opposite to probes, and that this contradiction complicates the decision on whether a property exists in an embedding space. We demonstrate our claims with two test cases, one dealing with gender debiasing and another with the erasure of morphological information from embedding spaces. We show that the application of a suitable indicator provides a more accurate picture of the information captured and removed compared to probes. We thus conclude that indicator tasks should be implemented and taken into consideration when eliciting information from embedded representations.