Nested Named Entity Recognition

By Jenny Rose Finkel, Christopher D. Manning. Conference on Empirical Methods in Natural Language Processing, 2009

333 citations recorded by the source corpus.

Many named entities contain other named entities inside them. Despite this fact, the field of named entity recognition has almost entirely ignored nested named entity recognition, but due to technological, rather than ideological reasons. In this paper, we present a new technique for recognizing nested named entities, by using a discriminative constituency parser. To train the model, we transform each sentence into a tree, with constituents for each named entity (and no other syntactic structure). We present results on both newspaper and biomedical corpora which contain nested named entities. In three out of four sets of experiments, our model outperforms a standard semi-CRF on the more traditional top-level entities. At the same time, we improve the overall F-score by up to 30% over the flat model, which is unable to recover any nested entities.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/e38a53a5b43de50e8f9bfc2c4a2c8ece9c3be38f

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 Molecular Biology

Citations in the corpus

A Unified MRC Framework for Named Entity Recognition (2019, background): “Finkel and Manning (2009) built a model to extract nested entity mentions based on parse trees.”
Named Entity Recognition as Dependency Parsing (2020, unknown): “We preprocess the dataset following the same settings of Finkel and Manning (2009) and Lu and Roth (2015) and use 90%/10% train/test split.”
An annotated dataset of literary entities (2019, background): “While classic NER models typically presume a flat entity structure (Finkel and Manning, 2009), relevant characters and places (and other entities) in literature need not be flat, and need not be named: The cook’s sister ate lunch contains two PER entities ([The cook] and [The cook’s sister]).”
Structured Prediction as Translation between Augmented Natural Languages (2021, methodology): “As in previous work, we use the processing and splits of Finkel & Manning (2009) resulting in 14,824 sentences for training, 1,855 for and 1,854 for testing.”
Low Resource Multi-Task Sequence Tagging - Revisiting Dynamic Conditional Random Fields (2020, methodology): “In summary, existing work focuses on task specific solutions that either model a specific hierarchy in NNER (Alex et al., 2007; Finkel and Manning, 2009; Ju et al., 2018; Lin et al., 2019; Luan et al., 2019; Li et al., 2019), assume independence between tasks given the shared data representation (Sø”
Recognizing Named Entities in Tweets (2011, background): “Proposed solutions to NER fall into three categories: 1) The rule-based (Krupka and Hausman, 1998); 2) the machine learning based (Finkel and Manning, 2009; Singh et al., 2010) ; and 3) hybrid methods (Jansche and Abney, 2002).”