Timezone: »

GAPX: Generalized Autoregressive Paraphrase-Identification X
Yifei Zhou · Renyu Li · Hayden Housen · Ser Nam Lim

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #232

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.

Author Information

Yifei Zhou (Department of Computer Science, Cornell University)
Renyu Li (Cornell University)
Hayden Housen (Cornell University)
Ser Nam Lim (Facebook AI)

More from the Same Authors