OpenID Research Articles

A Zero-Shot Framework for Low-Resource Relation Extraction via Distant Supervision and Large Language Models

While Large Language Models (LLMs) have significantly advanced various benchmarks in Natural Language Processing (NLP), the challenge of low-resource tasks persists, primarily due to the scarcity of data and difficulties in annotation. This study introduces LoRE, a framework designed for zero-shot relation extraction in low-resource settings, which blends distant supervision with the powerful capabilities of LLMs. LoRE addresses the challenges of data sparsity and noise inherent in traditional distant supervision methods, enabling high-quality relation extraction without requiring extensive labeled data. By leveraging LLMs for zero-shot open information extraction and incorporating heuristic entity and relation alignment with semantic disambiguation, LoRE enhances the accuracy and relevance of the extracted data. Low-resource tasks refer to scenarios where labeled data are extremely limited, making traditional supervised learning approaches impractical. This study aims to develop a robust framework that not only tackles these challenges but also demonstrates the theoretical and practical implications of zero-shot relation extraction. The Chinese Person Relationship Extraction (CPRE) dataset, developed under this framework, demonstrates LoRE’s proficiency in extracting person-related triples. The CPRE dataset consists of 1000 word pairs, capturing diverse semantic relationships. Extensive experiments on the CPRE, IPRE, and DuIE datasets show significant improvements in dataset quality and a reduction in manual annotation efforts. These findings highlight the potential of LoRE to advance both the theoretical understanding and practical applications of relation extraction in low-resource settings. Notably, the performance of LoRE on the manually annotated DuIE dataset attests to the quality of the CPRE dataset, rivaling that of manually curated datasets, and highlights LoRE’s potential for reducing the complexities and costs associated with dataset construction for zero-shot and low-resource tasks.

Multi-level feature interaction for open knowledge base canonicalization

Open Information Extraction (OpenIE) aims to construct expansive open knowledge bases (OKBs) by extracting triples (noun phrase, relation phrase, noun phrase) from unstructured text. One critical problem in OKBs is the lack of canonicalization for noun phrases and relation phrases, leading to the storage of redundant and ambiguous facts. Consequently, open knowledge base canonicalization, which clusters synonymous phrases into the same group, has emerged as an active research area. Existing approaches either leverage fact triples or source context in isolation, or at best, interact them at the clustering level. However, these approaches lack explicit interaction or only loosely couple the two types of knowledge, resulting in the potential loss of valuable intermediate information. In this paper, we propose MuFIC, a novel unsupervised framework that interacts the fact triples and source context at the feature level to address these limitations. In order to capture and integrate fine-grained fact and context knowledge, we design three levels of feature interaction: low-level context-guided feature interaction, mid-level fact-guided feature interaction, and high-level gated fusion feature interaction. Furthermore, we introduce an additional objective function via contrastive learning to improve the quality of extracted features and reduce knowledge-specific noise. Finally, we design a bidirectional feedback mechanism to better guide the learning process of joint features by harnessing side information prototype learning, and to dynamically optimize side information based on the clustering results formed by joint features. Extensive experiments on three public benchmark datasets demonstrate the superiority of our proposed framework.

Integrating Arabic Open Information Extraction Model by Machine Learning to Extract Relation

Integrating Arabic Open Information Extraction Model by Machine Learning to Extract Relation

Cnosso, a novel method for business document automation based on open information extraction

The state-of-the-art in automated processing of unstructured business documents has evolved from manual labor to advanced AI systems in the span of mere decades. Such systems involve learning techniques, rule or clause sets, neural models – either used alone or in combination – for the extraction to work. As an example, rule-based processes operate on a perceived layout or positioning of the information, whereas model-based frameworks adopt a semantic, and often uninspectable, approach. Verb-Based Semantic Role Labeling (VBSRL) is a novel system presented in a former paper that uses a hybrid foundation to inform the extraction phase via a set of rules modeling natural language. We propose a new VBSRL-based document processing method, aided by valuable and innovative architectural choices, which has been implemented for the Italian language and experimented upon with promising results. Even in its infancy, in fact, the first implementation of this system shows better results than comparable IE solutions, obtaining an aggregate, average F-measure of nearly 79%.

Structuring Information from Plant Morphological Descriptions using Open Information Extraction

Structuring Information from Plant Morphological Descriptions using Open Information Extraction

OIE4PA: open information extraction for the public administration

Tenders are powerful means of investment of public funds and represent a strategic development resource. Despite the efforts made so far by governments at national and international levels to digitalise documents related to the Public Administration sector, most of the information is still available in an unstructured format only. With the aim of bridging this gap, we present OIE4PA, our latest study on extracting and classifying relations from tenders of the Public Administration. Our work focuses on the Italian language, where the availability of linguistic resources to perform Natural Language Processing tasks is considerably limited. Nevertheless, OIE4PA adopts a multilingual approach so it can be applied to several languages by providing appropriate training data. Rather than purely training a classifier on a portion of the extracted relations, the backbone idea of our learning strategy is to put a supervised method based on self-training to the proof and to assess whether or not it improves the performance of the classifier. For evaluation purposes, we built a dataset composed of 2,000 triples which have been manually annotated by two human experts. The in-vitro evaluation shows that OIE4PA achieves a MacroF1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_1$$\\end{document} equal to 0.89 and a 91%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} accuracy. In addition, OIE4PA was used as the pillar of a prototype search engine, which has been evaluated through an in-vivo experiment with positive feedback from 32 final users, obtaining a SUS score equal to 83.98.

AI-based decision support system for public procurement

Tenders are powerful means of investment of public funds and represent a strategic development resource. Thus, improving the efficiency of procuring entities and developing evaluation models turn out to be essential to facilitate e-procurement procedures. With this contribution, we introduce our research to create a supporting system for the decision-making and monitoring process during the entire course of investments and contracts. This system employs artificial intelligence techniques based on natural language processing, focused on providing instruments for extracting useful information from both structured and unstructured (i.e., text) data. Therefore, we developed a framework based on a web app that provides integrated tools such as a semantic search engine, a summariser, an open information extraction engine in the form of triples (subject–predicate–object) for tender documents, and dashboards for analysing tender data.

Spatio-Temporal Relevance Classification from Geographic Texts Using Deep Learning

The growing proliferation of geographic information presents a substantial challenge to the traditional framework of a geographic information analysis and service. The dynamic integration and representation of geographic knowledge, such as triples, with spatio-temporal information play a crucial role in constructing a comprehensive spatio-temporal knowledge graph and facilitating the effective utilization of spatio-temporal big data for knowledge-driven service applications. The existing knowledge graph (or geographic knowledge graph) takes spatio-temporal as the attribute of entity, ignoring the role of spatio-temporal information for accurate retrieval of entity objects and adaptive expression of entity objects. This study approaches the correlation between geographic knowledge and spatio-temporal information as a text classification problem, with the aim of addressing the challenge of establishing meaningful connections among spatio-temporal data using advanced deep learning techniques. Specifically, we leverage Wikipedia as a valuable data source for collecting and filtering geographic texts. The Open Information Extraction (OpenIE) tool is employed to extract triples from each sentence, followed by manual annotation of the sentences’ spatio-temporal relevance. This process leads to the formation of quadruples (time relevance/space relevance) or quintuples (spatio-temporal relevance). Subsequently, a comprehensive spatio-temporal classification dataset is constructed for experiment verification. Ten prominent deep learning text classification models are then utilized to conduct experiments covering various aspects of time, space, and spatio-temporal relationships. The experimental results demonstrate that the Bidirectional Encoder Representations from Transformer-Region-based Convolutional Neural Network (BERT-RCNN) model exhibits the highest performance among the evaluated models. Overall, this study establishes a foundation for future knowledge extraction endeavors.

A Canonical Context-Preserving Representation for Open IE: Extracting Semantically Typed Relational Tuples from Complex Sentences

Modern systems that deal with inference in texts need automatized methods to extract meaning representations (MRs) from texts at scale. Open Information Extraction (IE) is a prominent way of extracting all potential relations from a given text in a comprehensive manner. Previous work in this area has mainly focused on the extraction of isolated relational tuples. Ignoring the cohesive nature of texts where important contextual information is spread across clauses or sentences, state-of-the-art Open IE approaches are thus prone to generating a loose arrangement of tuples that lack the expressiveness needed to infer the true meaning of complex assertions.To overcome this limitation, we present a method that allows existing Open IE systems to enrich their output with additional meta information. By leveraging the semantic hierarchy of minimal propositions generated by the discourse-aware Text Simplification (TS) approach presented in Niklaus et al. (2019), we propose a mechanism to extract semantically typed relational tuples from complex source sentences. Based on this novel type of output, we introduce a lightweight semantic representation for Open IE in the form of normalized and context-preserving relational tuples. It extends the shallow semantic representation of state-of-the-art approaches in the form of predicate-argument structures by capturing intra-sentential rhetorical structures and hierarchical relationships between the relational tuples. In that way, the semantic context of the extracted tuples is preserved, resulting in more informative and coherent predicate-argument structures which are easier to interpret.In addition, in a comparative analysis, we show that the semantic hierarchy of minimal propositions benefits Open IE approaches in a second dimension: the canonical structure of the simplified sentences is easier to process and analyze, and thus facilitates the extraction of relational tuples, resulting in an improved precision (up to 32%) and recall (up to 30%) of the extracted relations on a large benchmark corpus.

SailGenie: SAiling expertIse to knowLedge Graph through opEN Information Extraction

This work is focused on the sailing domain, for which several innovative technologies are being adopted to improve sailing efficiency, performance, and safety. In this context a knowledge graph could be used, for example, to represent information about different types of boats, sailing techniques, maritime safety, or weather conditions. Although numerous construction methods or ready-to-go knowledge graphs have been proposed in many fields, the sailing domain still needs to be explored. As the most effective methods rely on domain-specific datasets, the absence of suitable and available sailing datasets is one of the main challenges. Although several Open Information Extraction (OpenIE) methods may generate relevant triplets (the elementary units composing a knowledge graph) from arbitrary text without any additional information about its topic, such methods usually generate many incorrect triplets. In this paper, we aim (i) to address the aforementioned problem by proposing an innovative method that combines in an improved and strengthened way different OpenIE tools to generate proper triplets from domain-specific sources and, in particular, (ii) to build and release a suitable dataset for the sailing domain. Results confirm that our proposal can maximize the extracted information and infer unique information irretrievable by the classical OpenIE tools and, furthermore, that the generated dataset is significantly valuable for the sailing scenario.

Open Information Extraction Methodology for a New Curated Biomedical Literature Dataset

Open Information Extraction Methodology for a New Curated Biomedical Literature Dataset

An Online Parsing Framework for Semistructured Streaming System Logs of Internet of Things Systems

This article presents a novel log abstraction framework based on neural open information extraction (OpenIE) and dynamic word embedding principles. Though various log parsing frameworks are proposed in the literature, the existing frameworks are modeled on predefined heuristics or auto-regressive methodologies that work well in offline scenarios. However, these frameworks are less suitable for dynamic self-adaptive systems, such as the Internet of Things (IoT), where the log outputs have diverse contextual variations and disparate time irregularities. Therefore, it is essential to move away from these traditional approaches and develop a systematic model that can effectively analyze log outputs in real-time and increase the system up-time of IoT networks so that they are almost always available. To address these needs, the proposed framework used OpenIE along with term frequency/inverse document frequency (TF/IDF) vectorization for constructing a set of relational triples (aka triple-sets). Additionally, a dynamic pretrained encoder–decoder architecture is utilized to imbibe the positional and contextualized information in its resultant outputs. The adopted methodology has enabled the proposed framework to extract richer word representations with dynamic contextualization of time-sensitive event logs to enhance further downstream activities, such as failure prediction and prognostic analysis of IoT networks. The proposed framework is evaluated on the system event log traces accumulated from a long range wide-area network (LoRaWAN) IoT gateway to proactively determine the probable causes of its various failure scenarios. Additionally, the study also provided a comparative analysis of its mathematical representations with that of the current state-of-the-art (SOTA) approaches to project the advantages and benefits of the proposed model, particularly from its data analytics standpoint.

DptOIE: a Portuguese open information extraction based on dependency analysis

DptOIE: a Portuguese open information extraction based on dependency analysis

Open Information Extraction from Texts: Part III. Question Answering over an Automatically Constructed Knowledge Base

Open Information Extraction from Texts: Part III. Question Answering over an Automatically Constructed Knowledge Base

DetIE: Multilingual Open Information Extraction Inspired by Object Detection

State of the art neural methods for open information extraction (OpenIE) usually extract triplets (or tuples) iteratively in an autoregressive or predicate-based manner in order not to produce duplicates. In this work, we propose a different approach to the problem that can be equally or more successful. Namely, we present a novel single-pass method for OpenIE inspired by object detection algorithms from computer vision. We use an order-agnostic loss based on bipartite matching that forces unique predictions and a Transformer-based encoder-only architecture for sequence labeling. The proposed approach is faster and shows superior or similar performance in comparison with state of the art models on standard benchmarks in terms of both quality metrics and inference time. Our model sets the new state of the art performance of 67.7% F1 on CaRB evaluated as OIE2016 while being 3.35x faster at inference than previous state of the art. We also evaluate the multilingual version of our model in the zero-shot setting for two languages and introduce a strategy for generating synthetic multilingual data to fine-tune the model for each specific language. In this setting, we show performance improvement of 15% on multilingual Re-OIE2016, reaching 75% F1 for both Portuguese and Spanish languages. Code and models are available at https://github.com/sberbank-ai/DetIE.

An adaptable, high-performance relation extraction system for complex sentences

The rapid proliferation of text data has lead to an increase in the use of Information Extraction (IE) techniques to automatically extract key information in a fast and effective manner. Relation Extraction (RE), a sub-task of IE focuses on extracting semantic relations from free natural language text and is crucial for further applications including Question Answering, Information Retrieval, Knowledge Base construction, Text Summarization, etc. Literature shows that supervised learning approaches were widely used in RE. However, the performance of supervised methodologies depend on the availability of domain-specific annotated datasets which is not viable for many of the domains including legal, financial, insurance etc. In recent times, Open Information Extraction (OIE) techniques address this issue, by facilitating domain-independent extraction of relations from large text corpora with no demand for domain-specific tagged data and predefined relation classes. Even though OIE systems are fast and simple to implement, they are less effective in handling complex sentences, and often produce redundant extractions.This paper proposes an efficient RE system to extract domain-specific relations from natural language text, consisting of Knowledge-based and Semi-supervised learning systems, integrated with domain ontology. We evaluated the performance of proposed work on ‘judicial domain” as a use case and found that it overcomes the flaws and limitations of existing RE approaches, by achieving better results in terms of precision and recall. On further analysis, we found that the proposed system outperforms existing cutting-edge OIE systems on varying sentence length and complexity.

Adding an Inception Network to Neural Network Open Information Extraction

This article presents a method to resolve tuples from plain text by adding an inception network, and dependence path embedding to existing neural network methods of open information extraction (Open IE). Inception networks are used in analysis of computer vision, and dependence path embedding in text processing, but neither has been reported with Open IE. Performance was measured on benchmark datasets using two existing Open IE deep learning methods, one using bidirectional long short-term memory and BIO tagging (RnnOIE-verb), and another using a span-based model (SpanOIE). RnnOIE-verb was compared with RnnOIE-verb plus inception network and/or dependence path embedding. SpanOIE was compared with SpanOIE plus inception network. Performance slightly increased with the addition of inception network to RnnOIE-verb (before AUC 0.45, F1 0.59; after AUC 0.46, F1 0.60) and inception network to SpanOIE (before AUC 0.63, F1 0.748; after AUC 0.64, F1 0.764). The performance gain was minor but potentially relevant to an iterative process of improvement.

Semi-pilot cell based maximum power point tracking and coordinated current control based PMSM drive for standalone solar water pumping system

The increasing water demand of rural areas without much utility integration can be well met with solar water pumping system. The system encompasses a high gain boost converter (HBC) with bootstrap inductive and capacitive elements and Space Vector Modulation (SVM) based inverter to drive the Permanent Magnet Synchronous Motor (PMSM)-Pump Assembly. A suitable maximum power point tracking (MPPT) method is needed to extract maximum power and to produce pulses for HBC during intermittent PV supply This work proposes Semi Pilot Cell based Fractional Open Circuit Voltage (SPC-FOCV) MPPT in which the pilot cell is involved in power production rather than being involved only in open circuit information extraction. A coordinated current control with cascaded outer speed loop and inner current loop for SVM inverter is adopted to address the dynamic operations of the system with better response. The power extracted from solar PV is boosted through HBC and is used to drive the PMSM-Pump​ assembly. Suitability of the system is validated under varying irradiation through a prototype developed in the laboratory and utilizing P30F4011 and Xilinx based FPGA for controlling the system. The results seem to claim the working efficacy of the system under various irradiation conditions.

A meta learning approach for open information extraction

A meta learning approach for open information extraction

Why does the president tweet this? Discovering reasons and contexts for politicians’ tweets from news articles

Politicians’ tweets can have important political and economic implications. However, limited context makes it hard for readers to instantly and precisely understand them, especially from a causal perspective. The triggers for these tweets may have been reported in news prior to the tweets, but simply finding similar news articles would not serve the purpose, given the following reasons. First, readers may only be interested in finding the reasons and contexts (we call causal backgrounds) for a certain part of a tweet. Intuitively, such content would be politically relevant and accord with public’s recent attention, which is not usually reflected within the context. Besides, the content should be human-readable, while the noisy and informal nature of tweets hinders regular Open Information Extraction systems. Second, similarity does not capture causality and the causality between tweet contents and news contents is beyond the scopes of causality extraction tools. Meanwhile, it will be non-trivial to construct a high-quality tweet-to-intent dataset.We propose the first end-to-end framework for discovering causal backgrounds of politicians’ tweets by: 1. Designing an Open IE system considering rule-free representations for tweets; 2. Introducing sources like Wikipedia linkage and edit history to identify focal contents; 3. Finding implicit causalities between different contexts using explicit causalities learned elsewhere. We curate a comprehensive dataset of interpretations from political journalists for 533 tweets from 5 US politicians. On average, we obtain the correct answers within top-2 recommendations. We make our dataset and framework code publicly available.