RI-Small: Learning to Generate High Quality Paraphrases with a Broad Coverage Lexicalized Grammar

自动释义被认为是机器翻译（MT），问答，摘要和对话系统等各种应用程序的关键。最近还表明，释义持有承诺的自动方法评估MT，当释义是足够高的质量。该项目研究了新的方法，用于获取和生成这种高质量的释义，以自动近似的人工注释错误率（HTER）度量MT评估，其中人类注释后编辑MT输出到可接受的释义的参考翻译。该项目强调使用一个语言学上知情的，基于语法的分析器和实现器，用于使用析取逻辑形式（DLF）获取和生成释义，与最近的工作完全依赖于浅层方法形成鲜明对比。 具体来说，该项目研究了以下方法：（1）从CCGbank中设计一个覆盖面很广的英语语法，并集成了Propbank中的语义角色;（2）扩展OpenCCG，以便使用该语法进行有效的解析和实现，采用超标记和解析排名方法进行生成;（3）调整和扩展以前的获取释义的方法，以便在DLF上工作;（4）生成一个或多个参考句子的高质量n最佳释义;以及（5）实验性地评估自动生成的释义是否可以与当前MT度量一起使用以产生与翻译质量的人类判断的改进的相关性。通过提供一种自动近似HTER指标的方法，该项目将有助于推动未来的MT研究。此外，通过极大地扩展OpenCCG的实现能力，该项目有望使广泛的NLP任务受益，其中目标文本的广度至关重要。

Automatic paraphrasing is considered vital to applications as diverse as machine translation (MT), question answering, summarization, and dialogue systems. Paraphrasing has also been shown recently to hold promise for automatic methods of evaluating MT, when the paraphrases are of sufficiently high quality. This project investigates novel methods for acquiring and generating such highquality paraphrases in order to automatically approximate the human translationerror rate (HTER) metric for MT evaluation, where human annotators post-edit MToutputs into acceptable paraphrases of the reference translations. The projectemphasizes the use of a linguistically informed, grammar-based parser andrealizer for acquiring and generating paraphrases using disjunctive logicalforms (DLFs), in sharp contrast to most recent work that relies entirely onshallow methods. Specifically, the project investigates methods of (1)engineering a broad coverage English grammar from the CCGbank, with semanticroles integrated from Propbank; (2) scaling up OpenCCG for efficient parsing and realization with this grammar, adapting supertagging and parse ranking methods for generation; (3) adapting and extending previous methods of acquiring paraphrases to work on DLFs; (4) generating high quality n-best paraphrases of one or more reference sentences; and (5) experimentally evaluating whether the automatically generated paraphrases can be used with current MT metrics to yield improved correlations with human judgments of translation quality. By providing a way to automatically approximate the HTER metric, the project will help drive future MT research. Additionally, by dramatically extending the realization capacity of OpenCCG, the project promises to benefit a wide range of NLP tasks where the breadth of target texts is of crucial importance.