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

自动释义被认为对机器翻译(MT)、问题回答、摘要和对话系统等各种应用至关重要。最近也表明，当释义的质量足够高时，释义也有望成为评估机器翻译的自动方法。本项目研究获取和生成这种高质量释义的新方法，以便自动逼近机器翻译评估的人工翻译错误率(HTER)度量，其中人工注释员将MT输出编辑为参考翻译的可接受释义。该项目强调使用语言信息的、基于语法的解析器和实现器来获取和生成使用析取逻辑形式(DFL)的释义，这与最近完全依赖于肤浅方法的工作形成了鲜明对比。具体地说，该项目研究了以下方法：(1)从CCGbank设计一个覆盖范围广泛的英语语法，并从Propbank集成语义角色；(2)扩展OpenCCG以使用该语法进行有效的分析和实现，采用超标记和分析排名方法进行生成；(3)修改和扩展以前获取释义的方法，以用于DLFS；(4)为一个或多个参考句子生成高质量的n-Best释义；以及(5)实验评估自动生成的释义是否可以与当前的机器翻译度量标准一起使用，以改善与人类对翻译质量的判断的相关性。通过提供一种自动近似HTER度量的方法，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，该项目有望使目标文本的广度至关重要的广泛的NLP任务受益。

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.