Microblogging is a model of content sharing in which the temporal locality of posts with respect to important events, either of foreseeable or unforeseeable nature, makes applica- tions of real-time filtering of great practical interest. We propose the use of Entity Linking (EL) in order to improve the retrieval effectiveness, by enriching the representation of microblog posts and filtering queries. EL is the process of recognizing in an unstructured text the mention of relevant entities described in a knowledge base. EL of short pieces of text is a difficult task, but it is also a scenario in which the information EL adds to the text can have a substantial impact on the retrieval process. We implement a start-of-the-art filtering method, based on the best systems from the TREC Microblog track realtime adhoc retrieval and filtering tasks , and extend it with a Wikipedia-based EL method. Results show that the use of EL significantly improves over non-EL based versions of the filtering methods.
Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result, retrieval performance is restricted by semantic discrepancies and vocabulary gaps. On the other hand, transformer-based dense retrievers introduce significant improvements in information retrieval tasks by exploiting low-dimensional contextualized representations of the corpus. While dense retrievers are known for their relative effectiveness, they suffer from low…
We propose a simple Named Entity Linking system that can be trained from Wikidata only. This demonstrates the strengths and weaknesses of this data source for this task and provides an easily reproducible baseline to compare other systems against. Our model is lightweight to train, to run and to keep synchronous with Wikidata in real time.
Radboud University（拉德堡德大学）；University of Stavanger（斯塔万格大学）
Machine understanding of user utterances in conversational systems is of utmost importance for enabling engaging and meaningful conversations with users. Entity Linking (EL) is one of the means of text understanding, with proven efficacy for various downstream tasks in information retrieval. In this paper, we study entity linking for conversational systems. To develop a better understanding of what EL in a conversational setting entails, we analyze a large number of dialogues from existing conversational datasets and annotate references to concepts, named entities, and personal entities using …
An Entity Linking system aligns the textual mentions of entities in a text to their corresponding entries in a knowledge base. However, deploying a neural entity linking system for efficient real-time inference in production environments is a challenging task. In this work, we present a neural entity linking system that connects the product and organization type entities in business conversations to their corresponding Wikipedia and Wikidata entries. The proposed system leverages Elasticsearch to ensure inference efficiency when deployed in a resource limited cloud machine, and obtains signifi…
We propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior work with improved feature representation, negative mining, and an auxiliary entity-pairing task, to obtain a single entity retrieval model that covers 100+ languages and 20 million entities. The model outperforms state-of-the-art results from a far more limited cross-lingual linking task. Rare entities and low-resource languages pose challenges at this large-scale, so we advocate for an incr…
A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions
Peking University（北京大学）；Harbin Institute of Technology（哈尔滨工业大学）
命名实体发现和链接是问答系统的基础和核心部分。在问句实体发现与链接（Question Entity Discovery and Linking，QEDL）问题中，由于短问句中的多个实体很难被完全发现，而短文本中的不完整信息又使得实体链接难以实现，从而对传统的方法提出了挑战。为了克服这些困难，我们提出了一个基于知识图谱的QEDL解决方案，并开发了一个系统，包括问题实体发现（QED）模块和实体链接（EL）模块。QED模块的方法是两种方法的折衷和集成。一种是基于知识图谱检索的方法，该方法能够提取更多的问题实体，保证召回率;另一种是基于条件随机场（CRF）的方法，该方法提高了查准率。将EL模块视为一个排序问题，利用学习排序（LTR）方法，结合语义相似度、文本相似度和实体流行度等特征，提取并充分利用短文本中的信息。在一个共享的QEDL评估任务的官方数据集上，我们的方法可以获得64.44%的QED和64.86%的EL的F1分数，排名第二，这表明它对QEDL问题的实际使用。
Universität des Saarlandes（萨尔大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
Entity Linking is the task of matching a mention to an entity in a given knowledge base (KB). It contributes to annotating a massive amount of documents existing on the Web to harness new facts about their matched entities. However, existing Entity Linking systems focus on developing models that are typically domain-dependent and robust only to a particular knowledge base on which they have been trained. The performance is not as adequate when being evaluated on documents and knowledge bases from different domains. Approaches based on pre-trained language models, such as Wu et al. (2020), atte…
In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base. In this paper, we address the task of multimodal entity linking (MEL), an emerging research field in which textual and visual information is used to map an ambiguous mention to an entity in a knowledge base (KB). First, we propose a method for building a fully annotated Twitter dataset for MEL, where entities are defined in a Twitter KB. Then, we propose a model for jointly learning a representation of both mentions and en…
We present an instance-based nearest neighbor approach to entity linking. In contrast to most prior entity retrieval systems which represent each entity with a single vector, we build a contextualized mention-encoder that learns to place similar mentions of the same entity closer in vector space than mentions of different entities. This approach allows all mentions of an entity to serve as "class prototypes" as inference involves retrieving from the full set of labeled entity mentions in the training set and applying the nearest mention neighbor's entity label. Our model is trained on a large …
University of Zagreb（萨格勒布大学）；University of Konstanz（康斯坦茨大学）；EPFL（洛桑联邦理工学院）
Named entity linking (NEL) in news is a challenging endeavour due to the frequency of unseen and emerging entities, which necessitates the use of unsupervised or zero-shot methods. However, such methods tend to come with caveats, such as no integration of suitable knowledge bases (like Wikidata) for emerging entities, a lack of scalability, and poor interpretability. Here, we consider person disambiguation in Quotebank, a massive corpus of speaker-attributed quotations from the news, and investigate the suitability of intuitive, lightweight, and scalable heuristics for NEL in web-scale corpora…
Graph Centrality Measures for Boosting Popularity-Based Entity Linking
Labex Observatoire de la vie littéraire (OBVIL)（文学生活观察实验室）；Laboratoire d’Informatique de Paris 6 (LIP6), Pierre and Marie Curie University（巴黎第六大学计算机实验室）
Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable entity linking method, Eigenthemes, that relies solely on the availability of entity names and a referent knowledge base. Eigenthemes exploits the fact that the entities that are truly mentioned in a document (the "gold entities") tend to form a semantically dense subset of the set of all candidate entities in the document. Geometrically speaking, …
Named Entity Recognition and Disambiguation (NERD) systems are foundational for information retrieval, question answering, event detection, and other natural language processing (NLP) applications. We introduce TweetNERD, a dataset of 340K+ Tweets across 2010-2021, for benchmarking NERD systems on Tweets. This is the largest and most temporally diverse open sourced dataset benchmark for NERD on Tweets and can be used to facilitate research in this area. We describe evaluation setup with TweetNERD for three NERD tasks: Named Entity Recognition (NER), Entity Linking with True Spans (EL), and End…
A recent advancement in the domain of biomedical Entity Linking is the development of powerful two-stage algorithms, an initial candidate retrieval stage that generates a shortlist of entities for each mention, followed by a candidate ranking stage. However, the effectiveness of both stages are inextricably dependent on computationally expensive components. Specifically, in candidate retrieval via dense representation retrieval it is important to have hard negative samples, which require repeated forward passes and nearest neighbour searches across the entire entity label set throughout traini…
Entity Linking (EL) is the task of detecting mentions of entities in text and disambiguating them to a reference knowledge base. Most prevalent EL approaches assume that the reference knowledge base is complete. In practice, however, it is necessary to deal with the case of linking to an entity that is not contained in the knowledge base (NIL entity). Recent works have shown that, instead of focusing only on affinities between mentions and entities, considering inter-mention affinities can be used to represent NIL entities by producing clusters of mentions. At the same time, inter-mention affi…
Entity Linking (EL) is the gateway into Knowledge Bases. Recent advances in EL utilize dense retrieval approaches for Candidate Generation, which addresses some of the shortcomings of the Lookup based approach of matching NER mentions against pre-computed dictionaries. In this work, we show that in the domain of Tweets, such methods suffer as users often include informal spelling, limited context, and lack of specificity, among other issues. We investigate these challenges on a large and recent Tweets benchmark for EL, empirically evaluate lookup and dense retrieval approaches, and demonstrate…
