arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09462cs.CLcs.LG
收藏

领域转换下的选择性问答

Selective Question Answering under Domain Shift

Stanford University(斯坦福大学)

Amita Kamath, Robin Jia, Percy Liang

摘要:

为了避免给出错误的答案,问答(QA)模型需要知道何时放弃回答。此外,用户经常会问一些与模型的训练数据不同的问题,这使得错误更有可能发生,从而使预防更加关键。在这项工作中,我们提出了域转移下的选择性问答的设置,其中QA模型在域内和域外数据的混合物上进行测试,并且必须回答(即,不弃权)尽可能多的问题,同时保持高准确性。完全基于模型的softmax概率的弃权策略表现不佳,因为模型对域外输入过于自信。相反,我们训练校准器来识别QA模型出错的输入,并在它预测可能出错时弃权。至关重要的是,校准器可以从观察模型对域外数据的行为中获益,即使这些数据来自与测试数据不同的域。我们将此方法与SQuAD训练的QA模型相结合,并在SQuAD和其他五个QA数据集的混合物上进行评估。我们的方法回答了56%的问题,同时保持了80%的准确率;相比之下,直接使用模型的概率在80%的准确率下只回答了48%。

英文摘要:

To avoid giving wrong answers, question answering (QA) models need to know when to abstain from answering. Moreover, users often ask questions that diverge from the model's training data, making errors more likely and thus abstention more critical. In this work, we propose the setting of selective question answering under domain shift, in which a QA model is tested on a mixture of in-domain and out-of-domain data, and must answer (i.e., not abstain on) as many questions as possible while maintaining high accuracy. Abstention policies based solely on the model's softmax probabilities fare poorly, since models are overconfident on out-of-domain inputs. Instead, we train a calibrator to identify inputs on which the QA model errs, and abstain when it predicts an error is likely. Crucially, the calibrator benefits from observing the model's behavior on out-of-domain data, even if from a different domain than the test data. We combine this method with a SQuAD-trained QA model and evaluate on mixtures of SQuAD and five other QA datasets. Our method answers 56% of questions while maintaining 80% accuracy; in contrast, directly using the model's probabilities only answers 48% at 80% accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑