Analysis of named entity recognition and linking for tweets

By Leon Derczynski, Diana Maynard, Giuseppe Rizzo, Marieke van Erp, G. Gorrell, Raphael Troncy, Johann Petrak, Kalina Bontcheva. 2014

377 citations recorded by the source corpus.

Applying natural language processing for mining and intelligent information access to tweets (a form of microblog) is a challenging, emerging research area. Unlike carefully authored news text and other longer content, tweets pose a number of new challenges, due to their short, noisy, context-dependent, and dynamic nature. Information extraction from tweets is typically performed in a pipeline, comprising consecutive stages of language identification, tokenisation, part-of-speech tagging, named entity recognition and entity disambiguation (e.g. with respect to DBpedia). In this work, we describe a new Twitter entity disambiguation dataset, and conduct an empirical analysis of named entity recognition and disambiguation, investigating how robust a number of state-of-the-art systems are on such noisy texts, what the main sources of error are, and which problems should be further investigated to improve the state of the art.

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

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

Citations in the corpus

Autoregressive Entity Retrieval (2020, methodology): “We evaluate on seven out-of-domain test sets: MSNBC, Derczynski (Der) (Derczynski et al., 2015), KORE 50 (K50) (Hoffart et al.”
CM3: A Causal Masked Multimodal Model of the Internet (2022, methodology): “For both setting we evaluate on seven test sets: MSNBC, Derczynski (Der) (Derczynski et al., 2015), KORE 50 (K50) (Hoffart et al., 2012), N3-Reuters-128 (R128), N3-RSS-500 (R500) (R¨oder et al., 2014), and OKE challenge 2015 and 2016 (OKE15 and OKE16) (Nuzzolese et al., 2015).”
Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition (2017, background): “This leaves them ill-equipped to handle NER in new environments (Derczynski et al., 2015).”
Implicit Entity Linking in Tweets (2016, background): “Mining tweets poses unique challenges due to their short, noisy, context-dependent, and dynamic nature [4].”
Domain-specific Knowledge Extraction from the Web of Data (2018, background): “This is challenging for NLP algorithms and hence has become a very active research area [Derczynski et al. 2015].”
Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer (2020, background): “As a crucial component of many information extraction tasks including entity linking (Derczynski et al., 2015), opinion mining (Maynard et al., 2012), and event detection (Ritter et al., 2012), named entity recognition (NER) has attracted much attention in the research community in the past two…”
Directions in Abusive Language Training Data: Garbage In, Garbage Out (2020, background): “Purposive sampling has been criticised for introducing various forms of bias into datasets [112], such as missing out on mis-spelled content [36] and only focusing on the linguistic patterns of an atypical subset of users.”
Directions in abusive language training data, a systematic review: Garbage in, garbage out (2020, background): “Purposive sampling has been criticised for introducing various forms of bias into datasets [96], such as missing mis-spelled content and only focusing on the linguistic patterns of an atypical subset of users [97].”
Interpretable Multi-dataset Evaluation for Named Entity Recognition (2020, positive): “To alleviate this problem, a few works (Ichihara et al., 2015; Derczynski et al., 2015) have attempted to perform ﬁne-grained error analysis of NER systems.”