fPLSA: Learning Semantic Structures in Document Collections Using Foundation Models

• URL: http://arxiv.org/abs/2410.05481v1
• Date: Mon, 7 Oct 2024 20:25:52 GMT
• Title: fPLSA: Learning Semantic Structures in Document Collections Using Foundation Models
• Authors: Weijia Xu, Nebojsa Jojic, Nicolas Le Roux,
• Abstract summary: We introduce fPLSA, a foundation-model-based Probabilistic Latent Semantic Analysis (PLSA) method. PLSA iteratively clusters and tags document segments based on document-level contexts. Our experiments on story writing, math, and multi-step reasoning datasets demonstrate that fPLSA tags help reconstruct the original texts better than existing tagging methods.
• Score: 19.099810900404357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans have the ability to learn new tasks by inferring high-level concepts from existing solution, then manipulating these concepts in lieu of the raw data. Can we automate this process by deriving latent semantic structures in a document collection using foundation models? We introduce fPLSA, a foundation-model-based Probabilistic Latent Semantic Analysis (PLSA) method that iteratively clusters and tags document segments based on document-level contexts. These tags can be used to model the structure of given documents and for hierarchical sampling of new texts. Our experiments on story writing, math, and multi-step reasoning datasets demonstrate that fPLSA tags help reconstruct the original texts better than existing tagging methods. Moreover, when used for hierarchical sampling, fPLSA produces more diverse outputs with a higher likelihood of hitting the correct answer than direct sampling and hierarchical sampling with existing tagging methods.

Related papers

• When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs [64.27273946787344]
  Recent Long-Context Language Models can process hundreds of thousands of tokens in a single prompt.<n>We recast reasoning as reusable thought caches, derived from prior problem solving traces.<n>We propose an update strategy that iteratively refines templates derived from training data through natural-language feedback.
  arXiv  Detail & Related papers  (2025-10-08T19:52:35Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• DISRetrieval: Harnessing Discourse Structure for Long Document Retrieval [51.89673002051528]
  DISRetrieval is a novel hierarchical retrieval framework that leverages linguistic discourse structure to enhance long document understanding.<n>Our studies confirm that discourse structure significantly enhances retrieval effectiveness across different document lengths and query types.
  arXiv  Detail & Related papers  (2025-05-26T14:45:12Z)
• Cequel: Cost-Effective Querying of Large Language Models for Text Clustering [15.179854529085544]
  Text clustering aims to automatically partition a collection of documents into coherent groups based on their linguistic features.<n>Recent advances in large language models (LLMs) have significantly improved this field by providing high-quality contextualized embeddings.<n>We propose Cequel, a cost-effective framework that achieves accurate text clustering under a limited budget of LLM queries.
  arXiv  Detail & Related papers  (2025-04-22T06:57:49Z)
• FRASE: Structured Representations for Generalizable SPARQL Query Generation [2.5782420501870296]
  This paper introduces FRASE (FRAme-based Semantic Enhancement), a novel approach that leverages Frame Semantic Role Labeling (FSRL) to address this limitation.<n>We also present LC-QuAD 3.0, a new dataset derived from LC-QuAD 2.0, in which each question is enriched using FRASE through frame detection and the mapping of frame-elements to their argument.<n>Our results demonstrate that integrating frame-based structured representations consistently improves SPARQL generation performance.
  arXiv  Detail & Related papers  (2025-03-28T04:39:52Z)
• New Evaluation Paradigm for Lexical Simplification [15.890439726439276]
  Lexical Simplification (LS) methods use a three-step pipeline: complex word identification, substitute generation, and substitute ranking.<n>We found large language models (LLMs) can simplify sentences directly with a single prompt, bypassing the traditional pipeline.<n>We propose a new annotation method for constructing an all-in-one LS dataset through human-machine collaboration.
  arXiv  Detail & Related papers  (2025-01-25T16:31:37Z)
• Text Clustering as Classification with LLMs [9.128151647718251]
  We propose a novel framework that reframes text clustering as a classification task by harnessing the in-context learning capabilities of Large Language Models.<n>By leveraging the advanced natural language understanding and generalization capabilities of LLMs, the proposed approach enables effective clustering with minimal human intervention.<n> Experimental results on diverse datasets demonstrate that our framework achieves comparable or superior performance to state-of-the-art embedding-based clustering techniques.
  arXiv  Detail & Related papers  (2024-09-30T16:57:34Z)
• Detection and Measurement of Syntactic Templates in Generated Text [58.111650675717414]
  We offer an analysis of syntactic features to characterize general repetition in models. We find that models tend to produce templated text in downstream tasks at a higher rate than what is found in human-reference texts.
  arXiv  Detail & Related papers  (2024-06-28T19:34:23Z)
• SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding [55.48936731641802]
  We present the SRFUND, a hierarchically structured multi-task form understanding benchmark. SRFUND provides refined annotations on top of the original FUNSD and XFUND datasets. The dataset includes eight languages including English, Chinese, Japanese, German, French, Spanish, Italian, and Portuguese.
  arXiv  Detail & Related papers  (2024-06-13T02:35:55Z)
• LLM Based Multi-Agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domain [2.3999111269325266]
  Large Language Models (LLMs) have enabled the creation of customized text output satisfying user requests. We propose a novel approach that combines the LLMs with prompt engineering and multi-agent systems for generating new documents compliant with a desired structure.
  arXiv  Detail & Related papers  (2024-02-21T13:54:53Z)
• Probing Representations for Document-level Event Extraction [30.523959637364484]
  This work is the first to apply the probing paradigm to representations learned for document-level information extraction. We designed eight embedding probes to analyze surface, semantic, and event-understanding capabilities relevant to document-level event extraction. We found that trained encoders from these models yield embeddings that can modestly improve argument detections and labeling but only slightly enhance event-level tasks.
  arXiv  Detail & Related papers  (2023-10-23T19:33:04Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• Document-Level Text Simplification: Dataset, Criteria and Baseline [75.58761130635824]
  We define and investigate a new task of document-level text simplification. Based on Wikipedia dumps, we first construct a large-scale dataset named D-Wikipedia. We propose a new automatic evaluation metric called D-SARI that is more suitable for the document-level simplification task.
  arXiv  Detail & Related papers  (2021-10-11T08:15:31Z)
• Text Summarization with Latent Queries [60.468323530248945]
  We introduce LaQSum, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimize a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.
  arXiv  Detail & Related papers  (2021-05-31T21:14:58Z)
• Generating Synthetic Data for Task-Oriented Semantic Parsing with Hierarchical Representations [0.8203855808943658]
  In this work, we explore the possibility of generating synthetic data for neural semantic parsing. Specifically, we first extract masked templates from the existing labeled utterances, and then fine-tune BART to generate synthetic utterances conditioning. We show the potential of our approach when evaluating on the Facebook TOP dataset for navigation domain.
  arXiv  Detail & Related papers  (2020-11-03T22:55:40Z)

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.