paper-with-me

Papers

Unsupervised Chunking with Hierarchical RNN

2023-09-10 · Zijun Wu, Anup Anand Deshmukh, Yongkang Wu, Jimmy Lin, Lili Mou

In Natural Language Processing (NLP), predicting linguistic structures, such as parsing and chunking, has mostly relied on manual annotations of syntactic structures. This paper introduces an unsupervised approach to chunking, a syntactic task that involves grouping words in a non-hierarchical manner. We present a two-layer Hierarchical Recurrent Neural Network (HRNN) designed to model word-to-chunk and chunk-to-sentence compositions. Our approach involves a two-stage training process: pretraining with an unsupervised parser and finetuning on downstream NLP tasks. Experiments on the CoNLL-2000 dataset reveal a notable improvement over existing unsupervised methods, enhancing phrase F1 score by up to 6 percentage points. Further, finetuning with downstream tasks results in an additional performance improvement. Interestingly, we observe that the emergence of the chunking structure is transient during the neural model's downstream-task training. This study contributes to the advancement of unsupervised syntactic structure discovery and opens avenues for further research in linguistic theory.

📄 PDF Abstract BibTeX arXiv:2309.04919

Code (1)

manga-uofa/uchrnn 공식 구현 pytorch

Tasks

ChunkingSentence

Similar Papers 제목 키워드 기반

Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach

2021-11-01 · Findings (EMNLP) 2021 11 · Anup Anand Deshmukh, Qianqiu Zhang, Ming Li, Jimmy Lin 외

In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages…

ChunkingTransfer Learning

MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents

2026-04-14 · Joongmin Shin, Chanjun Park, Jeongbae Park, Jaehyung Seo 외 arxiv

RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial document structures, causing information lo…

From Dionysius Emerges Apollo -- Learning Patterns and Abstractions from Perceptual Sequences

2025-03-14 · Shuchen Wu

Cognition swiftly breaks high-dimensional sensory streams into familiar parts and uncovers their relations. Why do structures emerge, and how do they enable learning, generalization, and prediction? What computational pr…

Chunking

Offline RL with Hierarchical Action Chunking

2026-07-23 · Ahad Jawaid arxiv

Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse …

Reinforcement LearningOffline RL

SUNTA: Hierarchical Video Prediction with Surprise-based Chunking

2026-07-02 · Tomoshi Iiyama, Masahiro Suzuki, Yutaka Matsuo arxiv

Hierarchical state-space models (HSSMs) offer a promising approach to long-horizon prediction by segmenting sequences into temporal chunks. However, their performance hinges on how chunk boundaries are determined. While …

Boundary DetectionVideo Prediction