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 2301.10309cs.LGcs.AIcs.CL
收藏

交互式链消解:基于交互的跨语言条件生成歧义消解

Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interaction

Google Research(谷歌研究院);Mila(米拉研究所);Polytechnique Montreal(蒙特利尔综合理工学院)

Jonathan Pilault, Xavier Garcia, Arthur Bražinskas, Orhan Firat

摘要:

跨语言条件生成(例如,机器翻译)长期以来一直享受着缩放的好处。尽管如此,仍然有一些问题是单靠规模可能无法克服的。例如,一种语言的源查询可能会产生另一种语言的几个翻译选项,而无需任何额外的上下文。然而,只有一种翻译是可以接受的,这取决于译者的偏好和目标。选择不正确的选项可能会严重影响翻译的实用性和质量。我们提出了一种新的方法互动链提示-一系列的问题,回答和生成中间步骤之间的翻译模型和用户模型-减少翻译成一系列的子问题解决歧义,然后解决这些子问题之前,产生最终的文本要翻译。为了检查歧义解决能力和评估翻译质量,我们创建了一个数据集,展示了不同的语言现象,这导致了四种语言的推理歧义。为了鼓励在这个方向上的进一步探索,我们发布了所有数据集。我们注意到,交互式链提示,使用八个交互作为范例,始终超过基于直接存取背景信息,以解决歧义的方法。

英文摘要:

Crosslingual conditional generation (e.g., machine translation) has long enjoyed the benefits of scaling. Nonetheless, there are still issues that scale alone may not overcome. A source query in one language, for instance, may yield several translation options in another language without any extra context. Only one translation could be acceptable however, depending on the translator's preferences and goals. Choosing the incorrect option might significantly affect translation usefulness and quality. We propose a novel method interactive-chain prompting -- a series of question, answering and generation intermediate steps between a Translator model and a User model -- that reduces translations into a list of subproblems addressing ambiguities and then resolving such subproblems before producing the final text to be translated. To check ambiguity resolution capabilities and evaluate translation quality, we create a dataset exhibiting different linguistic phenomena which leads to ambiguities at inference for four languages. To encourage further exploration in this direction, we release all datasets. We note that interactive-chain prompting, using eight interactions as exemplars, consistently surpasses prompt-based methods with direct access to background information to resolve ambiguities.

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。

↑