Open Information Extraction via Chunks

2023-05-05 · Kuicai Dong, Aixin Sun, Jung-jae Kim, XiaoLi Li

Open Information Extraction (OIE) aims to extract relational tuples from open-domain sentences. Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. We instead propose Sentence as Chunk sequence (SaC) and recognize chunk spans as tuple relations and arguments. We argue that SaC has better quantitative and qualitative properties for OIE than sentence as token sequence, and evaluate four choices of chunks (i.e., CoNLL chunks, simple phrases, NP chunks, and spans from SpanOIE) against gold OIE tuples. Accordingly, we propose a simple BERT-based model for sentence chunking, and propose Chunk-OIE for tuple extraction on top of SaC. Chunk-OIE achieves state-of-the-art results on multiple OIE datasets, showing that SaC benefits OIE task.

📄 PDF Abstract BibTeX arXiv:2305.03299

Code (1)

daviddongkc/chunk_oie 공식 구현 pytorch

Tasks

Chunking Open Information ExtractionSentence

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dilated Convolution 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Average Pooling 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

SAC 설명 없음

Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory

2025-12-23 · Tao An arxiv

A growing class of conversational-memory systems compresses dialogue history into structured artifacts (extracted facts, decisions, or events) on the premise that distilled structure retrieves better than raw text. We te…

MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG

2026-03-08 · Bhavik Mangla arxiv

RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction. We present MDKeyChunke…

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 Answering RAG Retrieval Retrieval-augmented Generation

Driver Behavior Extraction from Videos in Naturalistic Driving Datasets with 3D ConvNets

2020-11-30 · Hanwen Miao, Shengan Zhang, Carol Flannagan

Naturalistic driving data (NDD) is an important source of information to understand crash causation and human factors and to further develop crash avoidance countermeasures. Videos recorded while driving are often includ…

Continuous Perception Benchmark

2024-08-15 · Zeyu Wang, Zhenzhen Weng, Serena Yeung-Levy

Humans continuously perceive and process visual signals. However, current video models typically either sample key frames sparsely or divide videos into chunks and densely sample within each chunk. This approach stems fr…

Question Answering Video Question Answering