Mining Meaning from Wikipedia

Entity Type Prediction in Knowledge Graphs using Embeddings

Open Knowledge Graphs (such as DBpedia, Wikidata, YAGO) have been recognized as the backbone of diverse applications in the field of data mining and information retrieval. Hence, the completeness and correctness of the Knowledge Graphs (KGs) are vital. Most of these KGs are mostly created either via an automated information extraction from Wikipedia snapshots or information accumulation provided by the users or using heuristics. However, it has been observed that the type information of these KGs is often noisy, incomplete, and incorrect. To deal with this problem a multi-label classification …

Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?

Question Answering for complex questions is often modeled as a graph construction or traversal task, where a solver must build or traverse a graph of facts that answer and explain a given question. This "multi-hop" inference has been shown to be extremely challenging, with few models able to aggregate more than two facts before being overwhelmed by "semantic drift", or the tendency for long chains of facts to quickly drift off topic. This is a major barrier to current inference models, as even elementary science questions require an average of 4 to 6 facts to answer and explain. In this work w…

Wikiometrics: A Wikipedia Based Ranking System

We present a new concept - Wikiometrics - the derivation of metrics and indicators from Wikipedia. Wikipedia provides an accurate representation of the real world due to its size, structure, editing policy and popularity. We demonstrate an innovative mining methodology, where different elements of Wikipedia - content, structure, editorial actions and reader reviews - are used to rank items in a manner which is by no means inferior to rankings produced by experts or other methods. We test our proposed method by applying it to two real-world ranking problems: top world universities and academic …

Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning

Word embeddings, i.e., low-dimensional vector representations such as GloVe and SGNS, encode word "meaning" in the sense that distances between words' vectors correspond to their semantic proximity. This enables transfer learning of semantics for a variety of natural language processing tasks. Word embeddings are typically trained on large public corpora such as Wikipedia or Twitter. We demonstrate that an attacker who can modify the corpus on which the embedding is trained can control the "meaning" of new and existing words by changing their locations in the embedding space. We develop an exp…

Scalable Text Mining with Sparse Generative Models

The information age has brought a deluge of data. Much of this is in text form, insurmountable in scope for humans and incomprehensible in structure for computers. Text mining is an expanding field of research that seeks to utilize the information contained in vast document collections. General data mining methods based on machine learning face challenges with the scale of text data, posing a need for scalable text mining methods. This thesis proposes a solution to scalable text mining: generative models combined with sparse computation. A unifying formalization for generative text models is d…

Towards Proactive Information Retrieval in Noisy Text with Wikipedia Concepts

Extracting useful information from the user history to clearly understand informational needs is a crucial feature of a proactive information retrieval system. Regarding understanding information and relevance, Wikipedia can provide the background knowledge that an intelligent system needs. This work explores how exploiting the context of a query using Wikipedia concepts can improve proactive information retrieval on noisy text. We formulate two models that use entity linking to associate Wikipedia topics with the relevance model. Our experiments around a podcast segment retrieval task demonst…

Transitive Text Mining for Information Extraction and Hypothesis Generation

Transitive text mining - also named Swanson Linking (SL) after its primary and principal researcher - tries to establish meaningful links between literature sets which are virtually disjoint in the sense that each does not mention the main concept of the other. If successful, SL may give rise to the development of new hypotheses. In this communication we describe our approach to transitive text mining which employs co-occurrence analysis of the medical subject headings (MeSH), the descriptors assigned to papers indexed in PubMed. In addition, we will outline the current state of our web-based …

WebBrain：通过基于大规模网络语料库的 grounding 学习为查询生成事实正确的文章

WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus

本文提出 WebBrain 任务，旨在基于网络证据为查询生成事实正确的短篇文章，构建了大规模数据集 WebBrain-Raw 及两个子数据集，并提出 ReGen 框架，通过改进检索与任务特定预训练提升生成事实性，实验证明其优于所有基线。

大型语言模型解决语义感知过程挖掘任务的潜力

On the Potential of Large Language Models to Solve Semantics-Aware Process Mining Tasks

本文系统探索LLMs解决语义感知过程挖掘任务的能力，通过上下文学习和监督微调评估五个任务，发现微调后模型在广泛过程类型和行业中表现优异。

文本理解提升WikiRace表现

Textual understanding boost in the WikiRace

针对WikiRace游戏的目标导向导航任务，系统评估结构、语义及混合策略，发现结合循环避免的纯贪心语义相似性引导策略成功率100%且效率远超其他方法，凸显大语言模型的语义导航潜力。