arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.14648cs.CLcs.AI
收藏

通过子部分对齐实现鲁棒的问答

Robust Question Answering Through Sub-part Alignment

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Jifan Chen, Greg Durrett

摘要:

目前的文本问答模型在域内测试集上取得了很好的性能,但通常是通过拟合数据中的表面模式来实现的,因此它们无法推广到分布外的设置。为了使问答系统更加健壮和易于理解,我们将问答建模为对齐问题。我们根据现成的语义表示(这里是语义角色)将问题和上下文分解为更小的单元,并将问题与上下文的子图对齐,以便找到答案。我们将我们的模型制定为结构化SVM,通过BERT计算对齐分数,尽管使用束搜索进行近似推理,我们仍然可以进行端到端的训练。我们显式使用对齐允许我们探索一组约束,通过这些约束,我们可以禁止跨域设置中出现的某些类型的不良模型行为。此外,通过调查不同潜在答案的得分差异,我们可以试图了解输入的哪些特定方面导致模型选择答案,而不依赖于事后解释技术。我们在SQuAD v1.1上训练我们的模型,并在几个对抗性和域外数据集上对其进行测试。结果表明,我们的模型是更强大的跨域比标准的BERT QA模型,来自比对分数的约束,使我们能够有效地权衡覆盖率和准确性。

英文摘要:

Current textual question answering models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns in the data, so they fail to generalize to out-of-distribution settings. To make a more robust and understandable QA system, we model question answering as an alignment problem. We decompose both the question and context into smaller units based on off-the-shelf semantic representations (here, semantic roles), and align the question to a subgraph of the context in order to find the answer. We formulate our model as a structured SVM, with alignment scores computed via BERT, and we can train end-to-end despite using beam search for approximate inference. Our explicit use of alignments allows us to explore a set of constraints with which we can prohibit certain types of bad model behavior arising in cross-domain settings. Furthermore, by investigating differences in scores across different potential answers, we can seek to understand what particular aspects of the input lead the model to choose the answer without relying on post-hoc explanation techniques. We train our model on SQuAD v1.1 and test it on several adversarial and out-of-domain datasets. The results show that our model is more robust cross-domain than the standard BERT QA model, and constraints derived from alignment scores allow us to effectively trade off coverage and 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。

↑