Challenge: Existing methods to embed signatures by adjusting token selection preferences during text generation are highly sensitive to paraphrasing and synonyms.
Approach: They propose a framework that embeds watermark signatures into the semantic structure of a sentence using Abstract Meaning Representation (AMR).
Outcome: Empirical evaluation shows SWAN matches state-of-the-art detection performance on unaltered watermarked text while improving robustness against paraphrasing.

Similar Papers

Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies on multilingual sentence embeddings focus on cross-lingual semantic textual similarity and transfer tasks.
Approach: They propose a method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR) . they compare existing multi-lingual sentence embedded with AMR and improve their versions by reducing the surface variations across different languages and expressions.
Outcome: The proposed method improves state-of-the-art multilingual sentence embeddings on transfer tasks and semantic textual similarity tests.
Abstract Meaning Representation for Paraphrase Detection (N18-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsing is ideal for paraphrase detection . it abstracts away from the syntactic realization of a sentence, and denotes only its meaning in a canonical form.
Approach: They propose a technique that uses latent semantic analysis to translate sentences into AMR graphs . they show that the technique can be used to detect whether two sentences have the same meaning .
Outcome: The proposed technique significantly advances state-of-the-art paraphrase detection for the Microsoft Research Paraphrase Corpus.
A Robust Semantics-based Watermark for Large Language Model against Paraphrasing (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to detect LLM-generated content use simple hashes of precedent tokens to partition vocabulary.
Approach: They propose a semantics-based watermark framework to enhance the robustness against paraphrase.
Outcome: The proposed framework is robust under different paraphrases and the semantic meaning of the sentences will be likely preserved under paraphrase.
Factorising AMR generation through syntax (N19-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic annotation framework which abstracts away from the surface form of text to capture the core 'who did what to whom' structure.
Approach: They propose to decompose the generation process into two steps: first generate a syntactic structure, and then generate the surface form.
Outcome: The proposed approach generates meaning-preserving syntactic paraphrases of the same graph, as judged by humans.
A Survey of AMR Applications (2024.emnlp-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic representation that takes the form of a rooted, directed graph.
Approach: They analyze more than 100 papers which use Abstract Meaning Representation (AMR) they highlight the range of applications for which AMR has been harnessed and techniques for incorporating it . they also highlight broader AMR engineering patterns and outline areas of future work that seem ripe for AMR incorporation.
Outcome: The results highlight the range of applications for which AMR has been harnessed and the techniques for incorporating it into those applications.
SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Experimental results demonstrate that SimMark surpasses previous sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains.
Approach: They propose a sentence-level watermarking algorithm that makes LLM outputs traceable without requiring access to model internals.
Outcome: The proposed algorithm surpasses previous sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains while maintaining the text quality and fluency.
Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction (2021.naacl-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (IE) and Information Extraction (IE), both focus on extracting the main information from natural language texts.
Approach: They propose an AMR-guided framework for joint information extraction using a pre-trained AMR parser.
Outcome: The proposed framework achieves state-of-the-art on all IE subtasks.
AMR-DA: Data Augmentation by Abstract Meaning Representation (2022.findings-acl)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic representation for NLP/NLU.
Approach: They propose to use AMR-DA for data augmentation in NLP . they use sentence-level techniques like back translation and token-level methods like EDA .
Outcome: The proposed method outperforms EDA and AEDA and improves on STS and text classification tasks.
CAMRA: Copilot for AMR Annotation (2023.emnlp-demo)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a formalism for deep lexical semantic representation.
Approach: They introduce a web-based tool for constructing AMR from natural language text . CAMRA incorporates AMR parser models as coding co-pilots .
Outcome: The proposed tool is based on the prototyping of existing AMR editors and integrates Propbank roleset lookup as an autocomplete feature.
“You Are An Expert Linguistic Annotator”: Limits of LLMs as Analyzers of Abstract Meaning Representation (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) demonstrate proficiency and fluency in the use of language, but do they have the linguistic knowledge to serve as an expert linguistic annotator?
Approach: They examine the successes and limitations of large language models using the Abstract Meaning Representation (AMR) parsing formalism.
Outcome: The proposed models can reproduce the basic format of AMR, as well as some core event, argument, and modifier structure, but they have virtually no fully accurate parses.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations