paper-with-me

홈 › Papers

Semantic WordRank: Generating Finer Single-Document Summarizations

2018-09-12 · Hao Zhang, Jie Wang

We present Semantic WordRank (SWR), an unsupervised method for generating an extractive summary of a single document. Built on a weighted word graph with semantic and co-occurrence edges, SWR scores sentences using an article-structure-biased PageRank algorithm with a Softplus function adjustment, and promotes topic diversity using spectral subtopic clustering under the Word-Movers-Distance metric. We evaluate SWR on the DUC-02 and SummBank datasets and show that SWR produces better summaries than the state-of-the-art algorithms over DUC-02 under common ROUGE measures. We then show that, under the same measures over SummBank, SWR outperforms each of the three human annotators (aka. judges) and compares favorably with the combined performance of all judges.

📄 PDF Abstract BibTeX arXiv:1809.04649

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringDiversity

Methods 이 논문이 사용한 방법론

(TravEL!!Guide)How Do I File a Claim with Expedia? How Do I File a Claim with Expedia? Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help & Exclusive Travel Discounts!Need to file a claim with…

Similar Papers 제목 키워드 기반

TextCNN with Attention for Text Classification

2021-08-04 · Ibrahim Alshubaily

The vast majority of textual content is unstructured, making automated classification an important task for many applications. The goal of text classification is to automatically classify text documents into one or more …

ClassificationNetwork EmbeddingSentenceSentence Classification+2

WordRank: Learning Word Embeddings via Robust Ranking

2015-06-09 · EMNLP 2016 11 · Shihao Ji, Hyokun Yun, Pinar Yanardag, Shin Matsushima 외

Embedding words in a vector space has gained a lot of attention in recent years. While state-of-the-art methods provide efficient computation of word similarities via a low-dimensional matrix embedding, their motivation …

Learning Word EmbeddingsWord EmbeddingsWord Similarity

Hierarchical Document Refinement for Long-context Retrieval-augmented Generation

2025-05-15 · Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang 외

Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefin…

Multi-Task LearningRAGRetrievalRetrieval-augmented Generation

Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities

2024-06-17 · Zhonghao Li, Xuming Hu, Aiwei Liu, Kening Zheng 외

Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks …

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Efficient Vector Representation for Documents through Corruption

2017-07-08 · Minmin Chen

We present an efficient document representation learning framework, Document Vector through Corruption (Doc2VecC). Doc2VecC represents each document as a simple average of word embeddings. It ensures a representation gen…

Document ClassificationRepresentation LearningSentiment AnalysisWord Embeddings