GAPX: Generalized Autoregressive Paraphrase-Identification X
This addresses a specific issue in NLP for researchers and practitioners, but it is incremental as it builds on existing methods to mitigate bias.
The paper tackled the problem of performance drop in paraphrase identification models due to distribution shift, particularly from biases in negative examples, by proposing a method using two separate models and a perplexity-based metric to adjust their weighting, achieving strong empirical results.
Paraphrase Identification is a fundamental task in Natural Language Processing. While much progress has been made in the field, the performance of many state-of-the-art models often suffer from distribution shift during inference time. We verify that a major source of this performance drop comes from biases introduced by negative examples. To overcome these biases, we propose in this paper to train two separate models, one that only utilizes the positive pairs and the other the negative pairs. This enables us the option of deciding how much to utilize the negative model, for which we introduce a perplexity based out-of-distribution metric that we show can effectively and automatically determine how much weight it should be given during inference. We support our findings with strong empirical results.