SGER: Exploiting Alternative Packagings of Source Meaning in Statistical Machine Translation

SGER：在统计机器翻译中利用源语言意义的替代包装目前的统计机器翻译（MT）方法忽略了一个关键事实：源语言句子并不是表达作者意义的唯一方式。 源句只是潜在意义的各种“包装”之一的想法当然是语际翻译方法的一个常见动机;然而，语际语义表征通常被放弃，因为难以定义，并且一旦定义就很难准确获得广泛的覆盖范围。 在这个项目中，我们正在重新审视意义的“包装”的概念，但探索它的实际方法与统计机器翻译的当前实践相一致。 与语义迁移或语际方法不同，我们将替代方案编码为源释义格，这种表示使我们能够利用源语言的概括，同时仍然保持表征统计技术状态的表面到表面的方向。我们的探索性工作侧重于使用词汇化良好基础语法（LWFG）捕获句法和语义变化，最近的一种形式主义，平衡了表达能力与实际和可证明的可学习性结果。 我们正在量化和表征源释义格中可用的信息，评估浅层释义的价值，并探索使用LWFG和其他基于约束的语法框架进行源释义生成的更深层次技术的相对前景。 通过源释义捕捉概括的能力可能会在少数民族和濒危语言的翻译中开辟新的可能性，这些语言缺乏支持标准统计MT技术所需的规模的训练语料库。

SGER: Exploiting Alternative Packagings of Source Meaning in Statistical Machine TranslationCurrent approaches in statistical machine translation (MT) miss a keyfact: the source language sentence is not the only way the author's meaning could have been expressed. The idea that the source sentence is just one of various ``packagings'' of underlying meaning was, of course, one familiar motivation for interlingual approaches to translation; however, interlingual semantic representations have generally been abandoned as notoriously difficult to define, and equally difficult to obtain accurately with broad coverage once defined. In this project, we are revisiting the idea of "packagings" of meaning, but exploring it in practical ways consistent with current practice in statistical MT. Unlike semantic transfer or interlingualapproaches, we encode alternatives as source paraphrase lattices, a representation that allows us to exploit generalizations about the source language while still maintaining the surface-to-surface orientation that characterizes the statistical state of the art. Our exploratory work focuses on capturing syntactic and semantic variation using Lexicalized Well Founded Grammars (LWFG), a recent formalism that balances expressiveness with practical and provable learnability results. We are quantifying and characterizing the information available in source paraphrase lattices, assessing the value of shallow paraphrasing, and exploring the relative promise of deeper techniques for source paraphase generation using LWFG and other constraint-based grammatical frameworks. The ability to capturegeneralizations via source paraphrase may open new possibilities in the translation of minority and endangered languages, which lack training corpora on the scale necessary to support standard statistical MT techniques.