Mirror: A Universal Framework for Various Information Extraction Tasks
- URL: http://arxiv.org/abs/2311.05419v2
- Date: Sun, 26 Nov 2023 17:12:20 GMT
- Title: Mirror: A Universal Framework for Various Information Extraction Tasks
- Authors: Tong Zhu, Junfei Ren, Zijian Yu, Mengsong Wu, Guoliang Zhang, Xiaoye
Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Min Zhang
- Abstract summary: We propose a universal framework for various IE tasks, namely Mirror.
We recast existing IE tasks as a multi-span cyclic graph extraction problem and devise a non-autoregressive graph decoding algorithm.
Our model has decent compatibility and outperforms or reaches competitive performance with SOTA systems.
- Score: 28.43708291298155
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Sharing knowledge between information extraction tasks has always been a
challenge due to the diverse data formats and task variations. Meanwhile, this
divergence leads to information waste and increases difficulties in building
complex applications in real scenarios. Recent studies often formulate IE tasks
as a triplet extraction problem. However, such a paradigm does not support
multi-span and n-ary extraction, leading to weak versatility. To this end, we
reorganize IE problems into unified multi-slot tuples and propose a universal
framework for various IE tasks, namely Mirror. Specifically, we recast existing
IE tasks as a multi-span cyclic graph extraction problem and devise a
non-autoregressive graph decoding algorithm to extract all spans in a single
step. It is worth noting that this graph structure is incredibly versatile, and
it supports not only complex IE tasks, but also machine reading comprehension
and classification tasks. We manually construct a corpus containing 57 datasets
for model pretraining, and conduct experiments on 30 datasets across 8
downstream tasks. The experimental results demonstrate that our model has
decent compatibility and outperforms or reaches competitive performance with
SOTA systems under few-shot and zero-shot settings. The code, model weights,
and pretraining corpus are available at https://github.com/Spico197/Mirror .
Related papers
- PyTorch-IE: Fast and Reproducible Prototyping for Information Extraction [6.308539010172309]
PyTorch-IE is a framework designed to enable swift, reproducible, and reusable implementations of Information Extraction models.
We propose task modules to decouple the concerns of data representation and model-specific representations.
PyTorch-IE also extends support for widely used libraries such as PyTorch-Lightning for training, HuggingFace datasets for dataset reading, and Hydra for experiment configuration.
arXiv Detail & Related papers (2024-05-16T12:23:37Z) - A Regularization-based Transfer Learning Method for Information
Extraction via Instructed Graph Decoder [29.242560023747252]
We propose a regularization-based transfer learning method for IE (TIE) via an instructed graph decoder.
Specifically, we first construct an instruction pool for datasets from all well-known IE tasks, and then present an instructed graph decoder.
In this way, the common knowledge shared with existing datasets can be learned and transferred to a new dataset with new labels.
arXiv Detail & Related papers (2024-03-01T13:04:12Z) - List-aware Reranking-Truncation Joint Model for Search and
Retrieval-augmented Generation [80.12531449946655]
We propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently.
GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture.
Our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs.
arXiv Detail & Related papers (2024-02-05T06:52:53Z) - An Efficient General-Purpose Modular Vision Model via Multi-Task
Heterogeneous Training [79.78201886156513]
We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently.
Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
arXiv Detail & Related papers (2023-06-29T17:59:57Z) - FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction [109.52244418498974]
Universal Information Extraction (UIE) has been introduced as a unified framework for various Information Extraction (IE) tasks.
We propose the Fuzzy Span Universal Information Extraction (FSUIE) framework.
Specifically, our contribution consists of two concepts: fuzzy span loss and fuzzy span attention.
arXiv Detail & Related papers (2023-06-19T15:59:28Z) - Universal Information Extraction with Meta-Pretrained Self-Retrieval [39.69130086395689]
Universal Information Extraction(Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner.
Retrieving knowledge from external knowledge bases may help models to overcome this problem but it is impossible to construct a knowledge base suitable for various IE tasks.
We propose MetaRetriever to retrieve task-specific knowledge from PLMs to enhance universal IE.
arXiv Detail & Related papers (2023-06-18T00:16:00Z) - CodeIE: Large Code Generation Models are Better Few-Shot Information
Extractors [92.17328076003628]
Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning ability on many NLP tasks.
In this paper, we propose to recast the structured output in the form of code instead of natural language.
arXiv Detail & Related papers (2023-05-09T18:40:31Z) - ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT [89.49161588240061]
Zero-shot information extraction (IE) aims to build IE systems from the unannotated text.
Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings.
We transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE)
arXiv Detail & Related papers (2023-02-20T12:57:12Z) - MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware
Ambidextrous Bin Picking via Physics-based Metaverse Synthesis [72.85526892440251]
We introduce MetaGraspNet, a large-scale photo-realistic bin picking dataset constructed via physics-based metaverse synthesis.
The proposed dataset contains 217k RGBD images across 82 different article types, with full annotations for object detection, amodal perception, keypoint detection, manipulation order and ambidextrous grasp labels for a parallel-jaw and vacuum gripper.
We also provide a real dataset consisting of over 2.3k fully annotated high-quality RGBD images, divided into 5 levels of difficulties and an unseen object set to evaluate different object and layout properties.
arXiv Detail & Related papers (2022-08-08T08:15:34Z)
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.