Mining Asymmetric Intertextuality
- URL: http://arxiv.org/abs/2410.15145v1
- Date: Sat, 19 Oct 2024 16:12:22 GMT
- Title: Mining Asymmetric Intertextuality
- Authors: Pak Kin Lau, Stuart Michael McManus,
- Abstract summary: Asymmetric intertextuality refers to one-sided relationships between texts.
We propose a scalable and adaptive approach for mining asymmetric intertextuality.
Our system handles intertextuality at various levels, from direct quotations to paraphrasing and cross-document influence.
- Score: 0.0
- License:
- Abstract: This paper introduces a new task in Natural Language Processing (NLP) and Digital Humanities (DH): Mining Asymmetric Intertextuality. Asymmetric intertextuality refers to one-sided relationships between texts, where one text cites, quotes, or borrows from another without reciprocation. These relationships are common in literature and historical texts, where a later work references aclassical or older text that remain static. We propose a scalable and adaptive approach for mining asymmetric intertextuality, leveraging a split-normalize-merge paradigm. In this approach, documents are split into smaller chunks, normalized into structured data using LLM-assisted metadata extraction, and merged during querying to detect both explicit and implicit intertextual relationships. Our system handles intertextuality at various levels, from direct quotations to paraphrasing and cross-document influence, using a combination of metadata filtering, vector similarity search, and LLM-based verification. This method is particularly well-suited for dynamically growing corpora, such as expanding literary archives or historical databases. By enabling the continuous integration of new documents, the system can scale efficiently, making it highly valuable for digital humanities practitioners in literacy studies, historical research and related fields.
Related papers
- Unified Multi-Modal Interleaved Document Representation for Information Retrieval [57.65409208879344]
We produce more comprehensive and nuanced document representations by holistically embedding documents interleaved with different modalities.
Specifically, we achieve this by leveraging the capability of recent vision-language models that enable the processing and integration of text, images, and tables into a unified format and representation.
arXiv Detail & Related papers (2024-10-03T17:49:09Z) - Text-Video Retrieval with Global-Local Semantic Consistent Learning [122.15339128463715]
We propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL)
GLSCL capitalizes on latent shared semantics across modalities for text-video retrieval.
Our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost.
arXiv Detail & Related papers (2024-05-21T11:59:36Z) - Explaining Relationships Among Research Papers [14.223038413516685]
We propose a feature-based, LLM-prompting approach to generate richer citation texts.
We find a strong correlation between human preference and integrative writing style, suggesting that humans prefer high-level, abstract citations.
arXiv Detail & Related papers (2024-02-20T23:38:39Z) - BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence [20.507596002357655]
Coherent texts inherently manifest a sequential and cohesive interplay among sentences.
BBScore is a reference-free metric grounded in Brownian bridge theory for assessing text coherence.
arXiv Detail & Related papers (2023-12-28T08:34:17Z) - A Comprehensive Survey of Document-level Relation Extraction (2016-2023) [3.0204640945657326]
Document-level relation extraction (DocRE) is an active area of research in natural language processing (NLP)
This paper aims to provide a comprehensive overview of recent advances in this field, highlighting its different applications in comparison to sentence-level relation extraction.
arXiv Detail & Related papers (2023-09-28T12:43:32Z) - Description-Based Text Similarity [59.552704474862004]
We identify the need to search for texts based on abstract descriptions of their content.
We propose an alternative model that significantly improves when used in standard nearest neighbor search.
arXiv Detail & Related papers (2023-05-21T17:14:31Z) - Beyond Contrastive Learning: A Variational Generative Model for
Multilingual Retrieval [109.62363167257664]
We propose a generative model for learning multilingual text embeddings.
Our model operates on parallel data in $N$ languages.
We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
arXiv Detail & Related papers (2022-12-21T02:41:40Z) - Nutribullets Hybrid: Multi-document Health Summarization [36.95954983680022]
We present a method for generating comparative summaries that highlights similarities and contradictions in input documents.
Our framework leads to more faithful, relevant and aggregation-sensitive summarization -- while being equally fluent.
arXiv Detail & Related papers (2021-04-08T01:44:29Z) - Topical Change Detection in Documents via Embeddings of Long Sequences [4.13878392637062]
We formulate the task of text segmentation as an independent supervised prediction task.
By fine-tuning on paragraphs of similar sections, we are able to show that learned features encode topic information.
Unlike previous approaches, which mostly operate on sentence-level, we consistently use a broader context.
arXiv Detail & Related papers (2020-12-07T12:09:37Z) - Extractive Summarization as Text Matching [123.09816729675838]
This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
We formulate the extractive summarization task as a semantic text matching problem.
We have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1)
arXiv Detail & Related papers (2020-04-19T08:27:57Z) - Learning to Select Bi-Aspect Information for Document-Scale Text Content
Manipulation [50.01708049531156]
We focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer.
In detail, the input is a set of structured records and a reference text for describing another recordset.
The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference.
arXiv Detail & Related papers (2020-02-24T12:52:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.