RI: Small: Cache transition systems for sentence understanding and generation

RI：小型：用于句子理解和生成的缓存转换系统

• 批准号: 1813823
• 负责人: Daniel Gildea
• 金额: $ 40万
• 依托单位: University of Rochester
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1813823&HistoricalAwards=false
• 关键词: RI; Small; Cache; transition; systems

Graph-based semantic representations allow computers to store and process information in natural language text. Such graphs contain nodes representing events and entities, and edges between nodes representing relations. This project will develop algorithms that operate directly on graphs, and will allow statistical natural processing techniques to better represent semantic structures. These advances can improve systems that extract information from text, translate between human languages such as English and Chinese, and interact with humans in natural language dialog. Improved language understanding can help in accessing the enormous amount of information available in unstructured text on the web as well as in databases of newspapers and scanned books. Improved translation between languages increases opportunities for trade as well as for dissemination of information generally between nations and cultures.Graph-based representations of the meaning of natural language sentences are being used to an increasing degree for reasoning tasks including question answering, merging information from disparate sources, and generating responses in dialog systems. However, automatic interpretation of sentences into such structures remains a very difficult task, despite recent progress in syntactic parsing. This project will develop algorithms for parsing into and generating text from semantic graphs, focusing on Abstract Meaning Representation or AMR, although the techniques generalize to other representations. Existing statistical systems for the AMR parsing task generally use ad-hoc algorithmic approaches; fundamentally new algorithms are necessary to advance the state of the art. This project is based on a new transition system, called a cache transition system, tailored to the task of parsing into graph structures. Preliminary experiments show that the system is a good match to real datasets of semantic graphs, in that it is able to produce the vast majority of graphs observed while at the same time simplifying the machine learning problem of predicting the next transition at each step. This project aims to advance the state of the art in semantic parsing and generation by developing and training a neural version of the transition system to predict semantic graphs from input strings. In its final year, the project will apply the parsing and generation methods to the task of machine translation, providing semantic graphs along with source language strings to a neural machine translation system.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.

基于图的语义表示允许计算机存储和处理自然语言文本中的信息。 这样的图包含代表事件和实体的节点，以及代表关系的节点之间的边缘。 该项目将开发直接在图上运行的算法，并允许统计自然处理技术更好地表示语义结构。 这些进步可以改善从文本中提取信息，在英语和中文等人类语言之间转化的系统，并在自然语言对话中与人类互动。 改进的语言理解可以帮助访问网络上非结构化文本中可用的大量信息，以及报纸和扫描书籍的数据库中。 语言之间的改进翻译增加了贸易的机会以及通常在国家和文化之间的信息传播的机会。基于图表的自然语言句子的含义的表示形式已被逐步用于推理任务，包括问题答案，从不同的来源合并信息，并在对话框系统中产生回答。 但是，尽管句法解析最近取得了进展，但将句子自动解释为这种结构仍然是一项非常艰巨的任务。 该项目将开发用于从语义图中解析和生成文本的算法，重点介绍抽象含义表示或AMR，尽管该技术概括为其他表示。 AMR解析任务的现有统计系统通常使用临时算法方法；从根本上讲，新算法对于推进最新技术是必要的。 该项目基于一个新的过渡系统，称为“缓存过渡系统”，该系统是根据解析为图结构的任务量身定制的。 初步实验表明，该系统与语义图的真实数据集非常匹配，因为它能够生成观察到的绝大多数图形，同时简化了机器学习的问题，即在每个步骤中预测下一个过渡。 该项目旨在通过开发和培训过渡系统的神经版本来预测输入字符串的语义图，以在语义解析和产生中推进最新技术。 在最后一年，该项目将将解析和生成方法应用于机器翻译的任务，将语义图以及源语言字符串以及神经机器翻译系统提供。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子优点和更广泛影响的审查标准来通过评估来支持的。

项目成果

Ordered Tree Decomposition for HRG Rule Extraction

HRG 规则提取的有序树分解

• DOI: 10.1162/coli_a_00350
• 发表时间: 2019
• 期刊: Computational Linguistics
• 影响因子: 9.3
• 作者: Gildea, Daniel;Satta, Giorgio;Peng, Xiaochang
• 通讯作者: Peng, Xiaochang

SEMBLEU: A Robust Metric for AMR Parsing Evaluation

SEMBLEU：AMR 解析评估的稳健指标

• 发表时间: 2019
• 期刊: Association for Computational Linguistics (ACL
• 作者: Song, Linfeng;Gildea, Daniel
• 通讯作者: Gildea, Daniel

Efficient Outside Computation

高效的外部计算

• DOI: 10.1162/coli_a_00386
• 发表时间: 2021
• 期刊: Computational Linguistics
• 影响因子: 9.3
• 作者: Gildea, Daniel

Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation

• DOI: 10.18653/v1/2022.acl-short.80
• 发表时间: 2022
• 作者: Lisa Jin;D. Gildea

Generalized Shortest-Paths Encoders for AMR-to-Text Generation

• DOI: 10.18653/v1/2020.coling-main.181
• 发表时间: 2020-12
• 作者: Lisa Jin;D. Gildea