Symbolic sentence meaning representations, such as AMR (Abstract Meaning Representation) provide expressive and structured semantic graphs that act as intermediates that simplify downstream NLP tasks. However, the instruction-following capability of large language models (LLMs) offers a shortcut to effectively solve NLP tasks, questioning the utility of semantic graphs. Meanwhile, recent work has also shown the difficulty of using meaning representations merely as a helpful auxiliary for LLMs. We revisit the position of semantic graphs in syntactic simplification, the task of simplifying sentence structures while preserving their meaning, which requires semantic understanding, and evaluate it on a new complex and natural dataset. The AMR-based method that we propose, AMRS$^3$, demonstrates that state-of-the-art meaning representations can lead to easy-to-implement simplification methods with competitive performance and unique advantages in cost, interpretability, and generalization. With AMRS$^3$ as an anchor, we discover that syntactic simplification is a task where semantic graphs are helpful in LLM prompting. We propose AMRCoC prompting that guides LLMs to emulate graph algorithms for explicit symbolic reasoning on AMR graphs, and show its potential for improving LLM on semantic-centered tasks like syntactic simplification.
Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplification
School of Information and Engineering, Yangzhou University（扬州大学信息工程学院）；School of Computer Science and Information Technology, Hefei University of Technology（合肥工业大学计算机与信息学院）
Transition-based Semantic Role Labeling with Pointer Networks
Universidade da Coruña（拉科鲁尼亚大学）
语义角色标注（Semantic role labeling，SRL）主要用于识别句子中的谓词-论元结构，在机器翻译和问答等自然语言处理任务中起着重要作用。实际上，所有可用的方法都不执行完整的SRL，因为它们依赖于预先确定的谓词，并且它们中的大多数遵循管道策略，使用特定的模型来执行一个或多个SRL子任务。此外，以前的方法有很强的依赖于语法信息，以实现最先进的性能，尽管语法树同样难以产生。这些简化和要求使得大多数SRL系统对于现实世界的应用是不切实际的。在这篇文章中，我们提出了第一个基于转换的SRL方法，该方法能够在一个从左到右的过程中完全处理输入句子，既不利用句法信息，也不诉诸于额外的模块。得益于我们基于指针网络的实现，完整的SRL可以在$O(n^2)$中准确高效地完成，在CoNLL-2009共享任务的大多数语言上实现了迄今为止的最佳性能。
Hallucination-Resistant Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
Shanghai Jiao Tong University（上海交通大学）；University of California San Diego（加州大学圣地亚哥分校）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Alibaba Group（阿里巴巴集团）
