English
Related papers

Related papers: Universal Information Extraction as Unified Semant…

200 papers

In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing. We first introduce a cascade model for UDS parsing that decomposes the complex parsing task into semantically appropriate subtasks.…

Computation and Language · Computer Science 2023-07-26 Hexuan Deng , Xin Zhang , Meishan Zhang , Xuebo Liu , Min Zhang

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making,…

Information Extraction (IE) stands as a cornerstone in natural language processing, traditionally segmented into distinct sub-tasks. The advent of Large Language Models (LLMs) heralds a paradigm shift, suggesting the feasibility of a…

Computation and Language · Computer Science 2023-11-14 Chengguang Gan , Qinghao Zhang , Tatsunori Mori

An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale extraction should be faithful (reflective of LM's actual…

Computation and Language · Computer Science 2023-02-28 Aaron Chan , Maziar Sanjabi , Lambert Mathias , Liang Tan , Shaoliang Nie , Xiaochang Peng , Xiang Ren , Hamed Firooz

Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM…

Computation and Language · Computer Science 2025-12-16 Yushen Fang , Jianjun Li , Mingqian Ding , Chang Liu , Xinchi Zou , Wenqi Yang

Open information extraction (Open IE) is a challenging task especially due to its brittle data basis. Most of Open IE systems have to be trained on automatically built corpus and evaluated on inaccurate test set. In this work, we first…

Computation and Language · Computer Science 2019-11-22 Junlang Zhan , Hai Zhao

Tree ensembles are very popular machine learning models, known for their effectiveness in supervised classification and regression tasks. Their performance derives from aggregating predictions of multiple decision trees, which are renowned…

Optimization and Control · Mathematics 2025-01-14 Lorenzo Bonasera , Emilio Carrizosa

This paper introduces the Unified Opinion Concepts (UOC) ontology to integrate opinions within their semantic context. The UOC ontology bridges the gap between the semantic representation of opinion across different formulations. It is a…

Computation and Language · Computer Science 2025-05-27 Gaurav Negi , Dhairya Dalal , Omnia Zayed , Paul Buitelaar

Large language model (LLM)-based recommender systems have achieved high-quality performance by bridging the discrepancy between the item space and the language space through item tokenization. However, existing item tokenization methods…

Information Retrieval · Computer Science 2025-11-18 Yu Hou , Won-Yong Shin

Image coding for machines (ICM) aims to compress images to support downstream AI analysis instead of human perception. For ICM, developing a unified codec to reduce information redundancy while empowering the compressed features to support…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 Ruoyu Feng , Jinming Liu , Xin Jin , Xiaohan Pan , Heming Sun , Zhibo Chen

Effective recommendation is crucial for large-scale online platforms. Traditional recommendation systems primarily rely on ID tokens to uniquely identify items, which can effectively capture specific item relationships but suffer from…

Information Retrieval · Computer Science 2025-02-25 Guanyu Lin , Zhigang Hua , Tao Feng , Shuang Yang , Bo Long , Jiaxuan You

One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora. The diversity of open domain corpora and the variety of natural language expressions further exacerbate this…

Computation and Language · Computer Science 2021-03-08 Jialong Tang , Yaojie Lu , Hongyu Lin , Xianpei Han , Le Sun , Xinyan Xiao , Hua Wu

Previous studies in Open Information Extraction (Open IE) are mainly based on extraction patterns. They manually define patterns or automatically learn them from a large corpus. However, these approaches are limited when grasping the…

Computation and Language · Computer Science 2016-05-26 Byungsoo Kim , Hwanjo Yu , Gary Geunbae Lee

Open Information Extraction (OIE) is the task of the unsupervised creation of structured information from text. OIE is often used as a starting point for a number of downstream tasks including knowledge base construction, relation…

Computation and Language · Computer Science 2018-08-23 Paul Groth , Michael Lauruhn , Antony Scerri , Ron Daniel

Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified…

Computation and Language · Computer Science 2025-07-25 Urchade Zaratiana , Gil Pasternak , Oliver Boyd , George Hurn-Maloney , Ash Lewis

Information Extraction (IE) is the task of automatically extracting structured information from unstructured/semi-structured machine-readable documents. Among various IE tasks, extracting actionable intelligence from ever-increasing amount…

Computation and Language · Computer Science 2013-11-19 Seyed-Mehdi-Reza Beheshti , Srikumar Venugopal , Seung Hwan Ryu , Boualem Benatallah , Wei Wang

With the advancement of multimedia technologies, news documents and user-generated content are often represented as multiple modalities, making Multimedia Event Extraction (MEE) an increasingly important challenge. However, recent MEE…

Computation and Language · Computer Science 2024-10-03 Philipp Seeberger , Dominik Wagner , Korbinian Riedhammer

Structured and grounded representation of text is typically formalized by closed information extraction, the problem of extracting an exhaustive set of (subject, relation, object) triplets that are consistent with a predefined set of…

Computation and Language · Computer Science 2022-04-14 Martin Josifoski , Nicola De Cao , Maxime Peyrard , Fabio Petroni , Robert West

Objectives: Despite the recent adoption of large language models (LLMs) for biomedical information extraction, challenges in prompt engineering and algorithms persist, with no dedicated software available. To address this, we developed…

Machine Learning · Computer Science 2025-04-02 Enshuo Hsu , Kirk Roberts

Large Language Models (LLMs) exhibit the ability to perform in-context learning (ICL), where they acquire new tasks directly from examples provided in demonstrations. This process is thought to operate through an implicit task selection…

Computation and Language · Computer Science 2024-12-17 Xingwei Qu , Yiming Liang , Yucheng Wang , Tianyu Zheng , Tommy Yue , Xingyuan Bu , Lei Ma , Stephen W. Huang , Jiajun Zhang , Yinan Shi , Chenghua Lin , Jie Fu , Ge Zhang