When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate linguistically richer dialogues, since the acquisition of language proficiency takes longer than learning the guessing task. By comparing models playing different games (GuessWhat, GuessWhich, and Mutual Friends), we show that this discrepancy is model- and task-agnostic. We investigate whether and when better language quality could lead to higher task success. We show that in GuessWhat, models could increase their accuracy if they learn to ground, encode, and decode also words that do not occur frequently in the training set.
翻译:当培训优惠对话猜游戏的模式时,最佳模式通常是根据其成功的任务选择。我们证明,在流行的端对端方法中,这种选择阻止了模式学习以产生语言上更丰富的对话,因为语言熟练程度的获得比学习猜谜任务需要更长的时间。我们通过比较不同游戏的模型(Guess what, Guesswhat, Guesswide, and Common Friends),表明这种差异是模型和任务不可知性的。我们调查更好的语言质量是否和何时能带来更高的任务成功。我们在GuessWhat中显示,如果模型能够学习到地面、编码和解码,那么它们也会提高准确性。