Design Challenges for Entity Linking

By Xiao Ling, Sameer Singh, Daniel S. Weld. 2015

228 citations recorded by the source corpus.

Recent research on entity linking (EL) has introduced a plethora of promising techniques, ranging from deep neural networks to joint inference. But despite numerous papers there is surprisingly little understanding of the state of the art in EL. We attack this confusion by analyzing differences between several versions of the EL problem and presenting a simple yet effective, modular, unsupervised system, called Vinculum, for entity linking. We conduct an extensive evaluation on nine data sets, comparing Vinculum with two state-of-the-art systems, and elucidate key aspects of the system that include mention extraction, candidate generation, entity type prediction, entity coreference, and coherence.

Subfields: Artificial Intelligence, Management Science and Operations Research, Natural Language Processing, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Natural Language Processing

In Information Extraction

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, background): “These variations and the resulting fragmentation of evaluation is discussed at length by Ling et al. (2015) and Hachey et al. (2013), and partially addressed by attempts to consolidate datasets (Cornolti et al., 2013) and metrics (Usbeck et al., 2015).”
Knowledge Enhanced Contextual Word Representations (2019, background): “Ling et al. (2015) showed that incorporating candidate priors into entity linkers can be a powerful signal, so we optionally allow for the candidate selector to return an associated prior probability for each entity candidate.”
ERNIE: Enhanced Language Representation with Informative Entities (2019, methodology): “Following the same evaluation criteria used in the previous work, we compare NFGEC, BERT, ERNIE on FIGER, and adopt strict accuracy, loose macro, loose micro scores for evaluation.”
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2020, methodology): “For this task, we evaluate our models on Open Entity (Choi et al., 2018) and FIGER (Ling et al., 2015) following the same split setting as Zhang et al. (2019).”
QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships (2018, methodology): “This problem of mapping phrases to world identiﬁers is similar to the task of entity linking (Ling, Singh, and Weld 2015).”
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (2020, methodology): “We choose FIGER (Ling et al., 2015), which is a sentencelevel entity typing dataset labeled with distant supervision.”
DeepType: Multilingual Entity Linking by Neural Type System Evolution (2018, methodology): “…TAC KBP 2010) that our approach outperforms all existing solutions by a wide margin, including approaches that rely on a human-designed type system (Ling, Singh, and Weld 2015) and the more recent work by Yamada et al. for embedding words and entities (Yamada et al. 2016), or document and entities…”
Construction of the Literature Graph in Semantic Scholar (2018, methodology): “We use the Bag of Concepts F1 metric (Ling et al., 2015) for comparison.”
Entity Commonsense Representation for Neural Abstractive Summarization (2018, background): “Despite its usefulness, linked entities extracted from ELS’s have issues because of low precision rates (Hasibi et al., 2016) and design challenges in training datasets (Ling et al., 2015).”
Learning Text Representations for 500K Classification Tasks on Named Entity Disambiguation (2018, background): “Please see (Ling et al., 2015) for a more detailed review of past research.”
Entity Linking via Joint Encoding of Types, Descriptions, and Context (2017, methodology): “, 2011), an unsupervised linker that uses hand-crafted features to rank candidates, (3) Vinculum (Ling et al., 2015), a modular, unsupervised pipeline system, (4) AIDA (Hoffart et al.”
Towards a Seamless Integration of Word Senses into Downstream NLP Applications (2017, background): “Conventional knowledge-based disambiguation systems (Hoffart et al., 2012; Agirre et al., 2014; Moro et al., 2014; Ling et al., 2015; Pilehvar and Navigli, 2014) often rely on computationally expen-”
GERBIL - Benchmarking Named Entity Recognition and Linking consistently (2017, methodology): “[35] recently presented a good overview and comparison of NEL systems together with their VINCULUM system.”
Zero-Shot Entity Linking by Reading Entity Descriptions (2019, background): “Standard EL While there are numerous differences between EL datasets (Bunescu and Pasca, 2006; Ling et al., 2015), most focus on a standard setting where mentions from a comprehensive test entity dictionary (often Wikipedia) are seen during training, and rich statistics and meta-data can be utilized”
Character-Level Question Answering with Attention (2016, methodology): “However, we do incorporate additional information from Freebase such as entity descriptions for our linking system to improve overall precision, like previous work in this area (Ling et al., 2015), (Lin et al.”