Focused Contrastive Training for Test-based Constituency Analysis
This work addresses a domain-specific challenge in computational linguistics for researchers and practitioners, representing an incremental improvement over existing methods.
The paper tackles the problem of improving grammaticality models for constituency analysis by introducing a focused contrastive training scheme that selects specific positive instances based on syntactic test transformations, resulting in consistent gains in performance.
We propose a scheme for self-training of grammaticality models for constituency analysis based on linguistic tests. A pre-trained language model is fine-tuned by contrastive estimation of grammatical sentences from a corpus, and ungrammatical sentences that were perturbed by a syntactic test, a transformation that is motivated by constituency theory. We show that consistent gains can be achieved if only certain positive instances are chosen for training, depending on whether they could be the result of a test transformation. This way, the positives, and negatives exhibit similar characteristics, which makes the objective more challenging for the language model, and also allows for additional markup that indicates the position of the test application within the sentence.