| Challenge: | Topological data analysis (TDA) focuses on the inherent shape of (spatial) data. |
| Approach: | They propose to use topological data analysis to represent document structure as story trees . story trees are hierarchical representations created from semantic vector representations of sentences . |
| Outcome: | The proposed methods can be used to extract summary summaries from news stories using story trees. |
Similar Papers
The Shape of Word Embeddings: Quantifying Non-Isometry with Topological Data Analysis (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that word embeddings represent language vocabularies as clouds of d-dimensional points . authors assume that word embedded in different languages are essentially isometric . |
| Approach: | They use persistent homology to measure distances between language pairs from unlabeled embeddings . they construct language phylogenetic trees over 81 Indo-European languages . |
| Outcome: | The proposed tree shows that the embeddings differ from the reference tree. |
Artificial Text Detection via Examining the Topology of Attention Maps (2021.emnlp-main)
Copied to clipboard
Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
| Challenge: | Existing methods for text detection lack interpretability and robustness towards unseen models. |
| Approach: | They propose three new types of interpretable topological features based on topological data analysis which is currently understudied in the field of NLP. |
| Outcome: | The proposed features outperform count- and neural-based baselines up to 10% on three common datasets and tend to be the most robust towards unseen GPT-style generation models. |
Topic Modeling With Topological Data Analysis (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent topic modelling approaches that use clustering on word, token or document embeddings can ex-tract coherent topics. |
| Approach: | They propose an unsupervised topic mod-elling method which uses TopologicalData Analysis to extract a topologicalskeleton of the manifold upon which word embeddings lie. |
| Outcome: | The proposed method performs on par with a baseline and can construct a network of coherent topics with meaningful relationships between them. |
Semantic Topology: a New Perspective for Communication Style Characterization (2025.findings-acl)
Copied to clipboard
| Challenge: | a new framework for discourse analysis uses Circuit Topology to quantify the semantic arrangement of sentences in textual structure. |
| Approach: | They propose a framework that leverages Circuit Topology to quantify the semantic arrangement of sentences in a text. |
| Outcome: | The proposed framework can quantify the semantic arrangement of sentences in a text. |
Lingua-Graph: A Unified Representation of Cross-Task Common Substructures for Analytic Language Processing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing structural-analytic tasks are fragmented by inconsistent task requirements . we propose a solution for the representation layer, called Lingua-Graph . |
| Approach: | They propose a representation-then-decision paradigm for structural-analytic tasks . they propose Graph-based representations that capture entities, facts, and relations . |
| Outcome: | The proposed model improves interpretability and higher hostability of entities, facts, and relations . the proposed model is available on github.com/rudaoshi/Lingua . |
CLAUSE-ATLAS: A Corpus of Narrative Information to Scale up Computational Literary Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | XIX and XX century English novels annotated automatically contain 41,715 labeled clauses . a new approach to analyze novels based on clauses captures structural patterns within books, as well as qualitative differences between them. |
| Approach: | They propose to use a corpus of XIX and XX century English novels annotated automatically to study stories as sequences of eventive, subjective and contextual information. |
| Outcome: | The proposed method captures structural patterns within books, as well as qualitative differences between them. |
Storytelling from Structured Data and Knowledge Graphs : An NLG Perspective (P19-4)
Copied to clipboard
| Challenge: | tutorial aims to explain the basic concepts of translating structured data into natural language . Various solutions for structured data translation will be discussed . |
| Approach: | tutorial aims to cover foundational, methodological, and system development aspects of translating structured data into natural language . Various solutions starting from traditional rule based/heuristic driven and modern data-driven will be discussed . |
| Outcome: | The tutorial aims to convey challenges and nuances in structured data translation, data representation techniques, and domain adaptable solutions for translation of the data into natural language form. |
Learning and Evaluating Character Representations in Novels (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in word embeddings have proven successful in learning entity representations from short texts but do not capture full book-level information. |
| Approach: | They propose two novel ways to learn fixed-length vector representations of characters from novels . they use graph neural network-based embeddings from a full corpus-based character network . |
| Outcome: | The proposed methods outperform text-based embeddings in four tasks. |
Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations (D19-3)
Copied to clipboard
| Challenge: | Currently, the main alternatives to deal with sequences are Recurrent Neural Networks (RNN) architectures and the Transformer. |
| Approach: | They propose a web-based tool that visualizes the sentence and token representations of RNNs and Transformer architectures at the sentence level. |
| Outcome: | The proposed visualization tool analyses gender inequalities in contextual word embeddings and the common language representation in a multilingual machine translation system. |
The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces (2026.acl-srw)
Copied to clipboard
Angelina Tsai, Shreya Subramanian, Catherine Liu, Kimberly Lopez, Leif Zinn-Brooks, Alexia E. Schulz, Adaku Uchendu
| Challenge: | Large Language Models (LLMs) have unprecedented capabilities, but they pose security concerns . current adversarial attacks exploit vulnerabilities in the embedding space of language models, allowing attackers to bypass safety guardrails and cause significant harmful consequences. |
| Approach: | They propose to use topological data analysis to characterize how adversarial perturbations act on text inputs by computing persistent homology metrics from attention maps across different model architectures. |
| Outcome: | The proposed visualizations show that adversarial perturbations alter higher-dimensional topological features in ways that distinguish them from clean, non-adversarial inputs. |