RI: Small: Fast and Accurate Natural Language Parsing and Generation by Marrying Deep Learning with Dynamic Programming

RI：小型：将深度学习与动态规划相结合，快速准确地进行自然语言解析和生成

• 批准号: 1817231
• 负责人: Liang Huang
• 金额: $ 40万
• 依托单位: Oregon State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1817231&HistoricalAwards=false
• 关键词: RI; Small; Fast; Accurate; Natural

This grant aims to improve automatic understanding, generation, and translation of natural language by machines. Automated natural language processing has already changed the way we interact with digital assistants such as Amazon Echo and Apple Siri on smartphones and other devices. Automated machine translation reduces information barriers on the Web, where most information is inaccessible to most users because it is in a language they do not understand. Today's natural language systems, however, are limited to short exchanges and often make errors. These limitations are due to need for the systems to respond very quickly: current methods for more accurate understanding and generation take too long. This project will overcome this problem by developing new, fast, principled algorithms for these tasks. This project also supports STEM education of underrepresented minorities (who do not speak English natively) by recruiting them in machine translation studies.This grant aims to construct fast (linear-time) and accurate natural language parsers and generators (including translators) that utilize the power of both deep learning (for accurate and automatic feature engineering) and dynamic programming (to speed up the search). This project focuses on Recurrent Neural Network-based models (RNNs) such as Long Short Term Memory (LSTMs). In particular, this project aims to (1) Develop linear-time dynamic programming-based neural parsers by using RNNs to summarize the input text and extend them to joint syntactic-discourse parsing and predictive parsing. (2) Develop approximate dynamic programming algorithms and principled beam search methods for text generation and machine translation systems that use RNN-based decoders to model output text. (3) Combine the above two directions with an innovative application of simultaneous translation using predictive parsing.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这笔赠款旨在提高机器对自然语言的自动理解、生成和翻译。自动自然语言处理已经改变了我们与智能手机和其他设备上的 Amazon Echo 和 Apple Siri 等数字助理交互的方式。 自动机器翻译减少了网络上的信息障碍，大多数用户无法访问大多数信息，因为这些信息采用的是他们无法理解的语言。 然而，当今的自然语言系统仅限于简短的交流，并且经常出错。 这些限制是由于系统需要非常快速地响应而造成的：当前用于更准确理解和生成的方法需要太长时间。 该项目将通过为这些任务开发新的、快速的、有原则的算法来克服这个问题。 该项目还通过招募机器翻译研究来支持代表性不足的少数群体（母语不是英语）的 STEM 教育。该赠款旨在构建快速（线性时间）且准确的自然语言解析器和生成器（包括翻译器），利用深度学习（用于准确和自动的特征工程）和动态编程（以加速搜索）的力量。该项目重点关注基于循环神经网络的模型 (RNN)，例如长短期记忆 (LSTM)。具体来说，该项目的目标是（1）通过使用 RNN 来总结输入文本，开发基于线性时间动态规划的神经解析器，并将其扩展到联合句法-语篇解析和预测解析。 (2) 为使用基于 RNN 的解码器对输出文本进行建模的文本生成和机器翻译系统开发近似动态规划算法和原则性波束搜索方法。 (3) 将上述两个方向与使用预测解析的同声翻译的创新应用相结合。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings

通过合并伪引用并减少重新排序来改进同声翻译

• DOI: 10.18653/v1/2021.emnlp-main.473
• 发表时间: 2021-01
• 期刊: Proceedings of EMNLP 2021
• 作者: Chen, Junkun;Zheng, Renjie;Kita, Atsuhito;Ma, Mingbo;Huang, Liang
• 通讯作者: Huang, Liang

Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation

打破束搜索魔咒：神经机器翻译（重新）评分方法和停止标准的研究

• 发表时间: 2018-11
• 期刊: Proceedings of EMNLP 2018
• 作者: Yang, Yilin;Huang, Liang;Ma, Mingbo
• 通讯作者: Ma, Mingbo

LinearPartition: linear-time approximation of RNA folding partition function and base-pairing probabilities

LinearPartition：RNA 折叠分配函数和碱基配对概率的线性时间近似

• DOI: 10.1093/bioinformatics/btaa460
• 发表时间: 2019-12-31
• 期刊: Bioinformatics
• 影响因子: 5.8
• 作者: He Zhang;Liang Zhang;D. Mathews;Liang Huang
• 通讯作者: Liang Huang

LinearTurboFold: Linear-time global prediction of conserved structures for RNA homologs with applications to SARS-CoV-2

LinearTurboFold：RNA 同系物保守结构的线性时间全局预测及其在 SARS-CoV-2 中的应用

• DOI: 10.1073/pnas.2116269118
• 发表时间: 2021-12-28
• 期刊: Proceedings of the National Academy of Sciences
• 作者: Li S;Zhang H;Zhang L;Liu K;Liu B;Mathews DH;Huang L
• 通讯作者: Huang L

Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report

多模态机器翻译的集成序列级训练：OSU-百度 WMT18 多模态机器翻译系统报告

• 发表时间: 2018-11
• 期刊: In Proceedings of WMT 2018
• 作者: Zheng, Renjie;Yang, Yilin;Ma, Mingbo;Huang, Liang
• 通讯作者: Huang, Liang