Large language models (LLMs) have majorly advanced NLP and AI, and next to their ability to perform a wide range of procedural tasks, a major success factor is their internalized factual knowledge. Since Petroni et al. (2019), analyzing this knowledge has gained attention. However, most approaches investigate one question at a time via modest-sized pre-defined samples, introducing an ``availability bias'' (Tversky&Kahnemann, 1973) that prevents the analysis of knowledge (or beliefs) of LLMs beyond the experimenter's predisposition. To address this challenge, we propose a novel methodology to comprehensively materialize an LLM's factual knowledge through recursive querying and result consolidation. Our approach is a milestone for LLM research, for the first time providing constructive insights into the scope and structure of LLM knowledge (or beliefs). As a prototype, we build GPTKB, a knowledge base (KB) comprising 101 million relational triples for over 2.9 million entities from GPT-4o-mini. We use GPTKB to exemplarily analyze GPT-4o-mini's factual knowledge in terms of scale, accuracy, bias, cutoff and consistency, at the same time. GPTKB is accessible at https://gptkb.org
We introduce SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, and measure its performance on a knowledge base construction task using Wikidata triple completion. We evaluate SHADOW on the LM-KBC 2024 challenge and show that it outperforms the baseline solution by 20% with a F1 score of 68.72%.
Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate "hallucinated" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they only evaluate the performance of the LLM component of the RAG pipeline in the experiments, and neglect the influence of the retrieval component and the external knowledge database. To address these issues, this paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios. Specifically, we have categorized the range of RAG applications into four distinct types-Create, Read, Update, and Delete (CRUD), each representing a unique use case. "Create" refers to scenarios requiring the generation of original, varied content. "Read" involves responding to intricate questions in knowledge-intensive situations. "Update" focuses on revising and rectifying inaccuracies or inconsistencies in pre-existing texts. "Delete" pertains to the task of summarizing extensive texts into more concise forms. For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems. We also analyze the effects of various components of the RAG system, such as the retriever, the context length, the knowledge base construction, and the LLM. Finally, we provide useful insights for optimizing the RAG technology for different scenarios.
Knowledge base construction entails acquiring structured information to create a knowledge base of factual and relational data, facilitating question answering, information retrieval, and semantic understanding. The challenge called "Knowledge Base Construction from Pretrained Language Models" at International Semantic Web Conference 2023 defines tasks focused on constructing knowledge base using language model. Our focus was on Track 1 of the challenge, where the parameters are constrained to a maximum of 1 billion, and the inclusion of entity descriptions within the prompt is prohibited. Although the masked language model offers sufficient flexibility to extend its vocabulary, it is not inherently designed for multi-token prediction. To address this, we present Vocabulary Expandable BERT for knowledge base construction, which expand the language model's vocabulary while preserving semantic embeddings for newly added words. We adopt task-specific re-pre-training on masked language model to further enhance the language model. Through experimentation, the results show the effectiveness of our approaches. Our framework achieves F1 score of 0.323 on the hidden test set and 0.362 on the validation set, both data set is provided by the challenge. Notably, our framework adopts a lightweight language model (BERT-base, 0.13 billion parameters) and surpasses the model using prompts directly on large language model (Chatgpt-3, 175 billion parameters). Besides, Token-Recode achieves comparable performances as Re-pretrain. This research advances language understanding models by enabling the direct embedding of multi-token entities, signifying a substantial step forward in link prediction task in knowledge graph and metadata completion in data management.
The ability to understand and generate similes is an imperative step to realize human-level AI. However, there is still a considerable gap between machine intelligence and human cognition in similes, since deep models based on statistical distribution tend to favour high-frequency similes. Hence, a large-scale symbolic knowledge base of similes is required, as it contributes to the modeling of diverse yet unpopular similes while facilitating additional evaluation and reasoning. To bridge the gap, we propose a novel framework for large-scale simile knowledge base construction, as well as two probabilistic metrics which enable an improved understanding of simile phenomena in natural language. Overall, we construct MAPS-KB, a million-scale probabilistic simile knowledge base, covering 4.3 million triplets over 0.4 million terms from 70 GB corpora. We conduct sufficient experiments to justify the effectiveness and necessity of the methods of our framework. We also apply MAPS-KB on three downstream tasks to achieve state-of-the-art performance, further demonstrating the value of MAPS-KB.
Corpora that contain tabular data such as WebTables are a vital resource for the academic community. Essentially, they are the backbone of any modern research in information management. They are used for various tasks of data extraction, knowledge base construction, question answering, column semantic type detection and many other. Such corpora are useful not only as a source of data, but also as a base for building test datasets. So far, there were no such corpora for the Russian language and this seriously hindered research in the aforementioned areas. In this paper, we present the first corpus of Web tables created specifically out of Russian language material. It was built via a special toolkit we have developed to crawl the Russian Wikipedia. Both the corpus and the toolkit are open-source and publicly available. Finally, we present a short study that describes Russian Wikipedia tables and their statistics.
We present a system for knowledge graph population with Language Models, evaluated on the Knowledge Base Construction from Pre-trained Language Models (LM-KBC) challenge at ISWC 2022. Our system involves task-specific pre-training to improve LM representation of the masked object tokens, prompt decomposition for progressive generation of candidate objects, among other methods for higher-quality retrieval. Our system is the winner of track 1 of the LM-KBC challenge, based on BERT LM; it achieves 55.0% F-1 score on the hidden test set of the challenge.
Language Models (LMs) have proven to be useful in various downstream applications, such as summarisation, translation, question answering and text classification. LMs are becoming increasingly important tools in Artificial Intelligence, because of the vast quantity of information they can store. In this work, we present ProP (Prompting as Probing), which utilizes GPT-3, a large Language Model originally proposed by OpenAI in 2020, to perform the task of Knowledge Base Construction (KBC). ProP implements a multi-step approach that combines a variety of prompting techniques to achieve this. Our results show that manual prompt curation is essential, that the LM must be encouraged to give answer sets of variable lengths, in particular including empty answer sets, that true/false questions are a useful device to increase precision on suggestions generated by the LM, that the size of the LM is a crucial factor, and that a dictionary of entity aliases improves the LM score. Our evaluation study indicates that these proposed techniques can substantially enhance the quality of the final predictions: ProP won track 2 of the LM-KBC competition, outperforming the baseline by 36.4 percentage points. Our implementation is available on https://github.com/HEmile/iswc-challenge.
In recent years, creating and managing knowledge bases have become crucial to the retail product and enterprise domains. We present an automatic knowledge base construction system that mines data from documents. This system can generate training data during the training process without human intervention. Therefore, it is domain-agnostic trainable using only the target domain text corpus and a pre-defined knowledge base. This system is called OASYS and is the first system built with the Korean language in mind. In addition, we also have constructed a new human-annotated benchmark dataset of the Korean Wikipedia corpus paired with a Korean DBpedia to aid system evaluation. The system performance results on human-annotated benchmark test dataset are meaningful and show that the generated knowledge base from OASYS trained on only auto-generated data is useful. We provide both a human-annotated test dataset and an auto-generated dataset.
Knowledge bases (KBs) contain plenty of structured world and commonsense knowledge. As such, they often complement distributional text-based information and facilitate various downstream tasks. Since their manual construction is resource- and time-intensive, recent efforts have tried leveraging large pretrained language models (PLMs) to generate additional monolingual knowledge facts for KBs. However, such methods have not been attempted for building and enriching multilingual KBs. Besides wider application, such multilingual KBs can provide richer combined knowledge than monolingual (e.g., English) KBs. Knowledge expressed in different languages may be complementary and unequally distributed: this implies that the knowledge available in high-resource languages can be transferred to low-resource ones. To achieve this, it is crucial to represent multilingual knowledge in a shared/unified space. To this end, we propose a unified representation model, Prix-LM, for multilingual KB construction and completion. We leverage two types of knowledge, monolingual triples and cross-lingual links, extracted from existing multilingual KBs, and tune a multilingual language encoder XLM-R via a causal language modeling objective. Prix-LM integrates useful multilingual and KB-based factual knowledge into a single model. Experiments on standard entity-related tasks, such as link prediction in multiple languages, cross-lingual entity linking and bilingual lexicon induction, demonstrate its effectiveness, with gains reported over strong task-specialised baselines.
There has been a steady need to precisely extract structured knowledge from the web (i.e. HTML documents). Given a web page, extracting a structured object along with various attributes of interest (e.g. price, publisher, author, and genre for a book) can facilitate a variety of downstream applications such as large-scale knowledge base construction, e-commerce product search, and personalized recommendation. Considering each web page is rendered from an HTML DOM tree, existing approaches formulate the problem as a DOM tree node tagging task. However, they either rely on computationally expensive visual feature engineering or are incapable of modeling the relationship among the tree nodes. In this paper, we propose a novel transferable method, Simplified DOM Trees for Attribute Extraction (SimpDOM), to tackle the problem by efficiently retrieving useful context for each node by leveraging the tree structure. We study two challenging experimental settings: (i) intra-vertical few-shot extraction, and (ii) cross-vertical fewshot extraction with out-of-domain knowledge, to evaluate our approach. Extensive experiments on the SWDE public dataset show that SimpDOM outperforms the state-of-the-art (SOTA) method by 1.44% on the F1 score. We also find that utilizing knowledge from a different vertical (cross-vertical extraction) is surprisingly useful and helps beat the SOTA by a further 1.37%.
Relation extraction (RE) has been extensively studied due to its importance in real-world applications such as knowledge base construction and question answering. Most of the existing works train the models on either distantly supervised data or human-annotated data. To take advantage of the high accuracy of human annotation and the cheap cost of distant supervision, we propose the dual supervision framework which effectively utilizes both types of data. However, simply combining the two types of data to train a RE model may decrease the prediction accuracy since distant supervision has labeling bias. We employ two separate prediction networks HA-Net and DS-Net to predict the labels by human annotation and distant supervision, respectively, to prevent the degradation of accuracy by the incorrect labeling of distant supervision. Furthermore, we propose an additional loss term called disagreement penalty to enable HA-Net to learn from distantly supervised labels. In addition, we exploit additional networks to adaptively assess the labeling bias by considering contextual information. Our performance study on sentence-level and document-level REs confirms the effectiveness of the dual supervision framework.
Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning, and it has been the subject of much research in recent works using KG embeddings. While existing KG embedding approaches mainly learn and predict facts within a single KG, a more plausible solution would benefit from the knowledge in multiple language-specific KGs, considering that different KGs have their own strengths and limitations on data quality and coverage. This is quite challenging, since the transfer of knowledge among multiple independently maintained KGs is often hindered by the insufficiency of alignment information and the inconsistency of described facts. In this paper, we propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs. KEnS embeds all KGs in a shared embedding space, where the association of entities is captured based on self-learning. Then, KEnS performs ensemble inference to combine prediction results from embeddings of multiple language-specific KGs, for which multiple ensemble techniques are investigated. Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion, via effectively identifying and leveraging complementary knowledge.
We describe a gold standard corpus of protest events that comprise of various local and international sources from various countries in English. The corpus contains document, sentence, and token level annotations. This corpus facilitates creating machine learning models that automatically classify news articles and extract protest event-related information, constructing knowledge bases which enable comparative social and political science studies. For each news source, the annotation starts on random samples of news articles and continues with samples that are drawn using active learning. Each batch of samples was annotated by two social and political scientists, adjudicated by an annotation supervisor, and was improved by identifying annotation errors semi-automatically. We found that the corpus has the variety and quality to develop and benchmark text classification and event extraction systems in a cross-context setting, which contributes to the generalizability and robustness of automated text processing systems. This corpus and the reported results will set the currently lacking common ground in automated protest event collection studies.
Identification of new concepts in scientific literature can help power faceted search, scientific trend analysis, knowledge-base construction, and more, but current methods are lacking. Manual identification cannot keep up with the torrent of new publications, while the precision of existing automatic techniques is too low for many applications. We present an unsupervised concept extraction method for scientific literature that achieves much higher precision than previous work. Our approach relies on a simple but novel intuition: each scientific concept is likely to be introduced or popularized by a single paper that is disproportionately cited by subsequent papers mentioning the concept. From a corpus of computer science papers on arXiv, we find that our method achieves a Precision@1000 of 99%, compared to 86% for prior work, and a substantially better precision-yield trade-off across the top 15,000 extractions. To stimulate research in this area, we release our code and data (https://github.com/allenai/ForeCite).
Open information extraction (OIE) systems extract relations and their arguments from natural language text in an unsupervised manner. The resulting extractions are a valuable resource for downstream tasks such as knowledge base construction, open question answering, or event schema induction. In this paper, we release, describe, and analyze an OIE corpus called OPIEC, which was extracted from the text of English Wikipedia. OPIEC complements the available OIE resources: It is the largest OIE corpus publicly available to date (over 340M triples) and contains valuable metadata such as provenance information, confidence scores, linguistic annotations, and semantic annotations including spatial and temporal information. We analyze the OPIEC corpus by comparing its content with knowledge bases such as DBpedia or YAGO, which are also based on Wikipedia. We found that most of the facts between entities present in OPIEC cannot be found in DBpedia and/or YAGO, that OIE facts often differ in the level of specificity compared to knowledge base facts, and that OIE open relations are generally highly polysemous. We believe that the OPIEC corpus is a valuable resource for future research on automated knowledge base construction.
Nowadays, editors tend to separate different subtopics of a long Wiki-pedia article into multiple sub-articles. This separation seeks to improve human readability. However, it also has a deleterious effect on many Wikipedia-based tasks that rely on the article-as-concept assumption, which requires each entity (or concept) to be described solely by one article. This underlying assumption significantly simplifies knowledge representation and extraction, and it is vital to many existing technologies such as automated knowledge base construction, cross-lingual knowledge alignment, semantic search and data lineage of Wikipedia entities. In this paper we provide an approach to match the scattered sub-articles back to their corresponding main-articles, with the intent of facilitating automated Wikipedia curation and processing. The proposed model adopts a hierarchical learning structure that combines multiple variants of neural document pair encoders with a comprehensive set of explicit features. A large crowdsourced dataset is created to support the evaluation and feature extraction for the task. Based on the large dataset, the proposed model achieves promising results of cross-validation and significantly outperforms previous approaches. Large-scale serving on the entire English Wikipedia also proves the practicability and scalability of the proposed model by effectively extracting a vast collection of newly paired main and sub-articles.
Universal schema builds a knowledge base (KB) of entities and relations by jointly embedding all relation types from input KBs as well as textual patterns expressing relations from raw text. In most previous applications of universal schema, each textual pattern is represented as a single embedding, preventing generalization to unseen patterns. Recent work employs a neural network to capture patterns' compositional semantics, providing generalization to all possible input text. In response, this paper introduces significant further improvements to the coverage and flexibility of universal schema relation extraction: predictions for entities unseen in training and multilingual transfer learning to domains with no annotation. We evaluate our model through extensive experiments on the English and Spanish TAC KBP benchmark, outperforming the top system from TAC 2013 slot-filling using no handwritten patterns or additional annotation. We also consider a multilingual setting in which English training data entities overlap with the seed KB, but Spanish text does not. Despite having no annotation for Spanish data, we train an accurate predictor, with additional improvements obtained by tying word embeddings across languages. Furthermore, we find that multilingual training improves English relation extraction accuracy. Our approach is thus suited to broad-coverage automated knowledge base construction in a variety of languages and domains.
Universal schema jointly embeds knowledge bases and textual patterns to reason about entities and relations for automatic knowledge base construction and information extraction. In the past, entity pairs and relations were represented as learned vectors with compatibility determined by a scoring function, limiting generalization to unseen text patterns and entities. Recently, 'column-less' versions of Universal Schema have used compositional pattern encoders to generalize to all text patterns. In this work we take the next step and propose a 'row-less' model of universal schema, removing explicit entity pair representations. Instead of learning vector representations for each entity pair in our training set, we treat an entity pair as a function of its relation types. In experimental results on the FB15k-237 benchmark we demonstrate that we can match the performance of a comparable model with explicit entity pair representations using a model of attention over relation types. We further demonstrate that the model per- forms with nearly the same accuracy on entity pairs never seen during training.
NLP tasks differ in the semantic information they require, and at this time no single se- mantic representation fulfills all requirements. Logic-based representations characterize sentence structure, but do not capture the graded aspect of meaning. Distributional models give graded similarity ratings for words and phrases, but do not capture sentence structure in the same detail as logic-based approaches. So it has been argued that the two are complementary. We adopt a hybrid approach that combines logic-based and distributional semantics through probabilistic logic inference in Markov Logic Networks (MLNs). In this paper, we focus on the three components of a practical system integrating logical and distributional models: 1) Parsing and task representation is the logic-based part where input problems are represented in probabilistic logic. This is quite different from representing them in standard first-order logic. 2) For knowledge base construction we form weighted inference rules. We integrate and compare distributional information with other sources, notably WordNet and an existing paraphrase collection. In particular, we use our system to evaluate distributional lexical entailment approaches. We use a variant of Robinson resolution to determine the necessary inference rules. More sources can easily be added by mapping them to logical rules; our system learns a resource-specific weight that corrects for scaling differences between resources. 3) In discussing probabilistic inference, we show how to solve the inference problems efficiently. To evaluate our approach, we use the task of textual entailment (RTE), which can utilize the strengths of both logic-based and distributional representations. In particular we focus on the SICK dataset, where we achieve state-of-the-art results.