---
title: "Named entity recognition — definition and key papers"
description: "Named entity recognition locates stretches of text that refer to specific real-world things, such as people, organizations, places, products or dates…"
canonical: "https://research.elamur.ai/free/en/concepts/named-entity-recognition/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/concepts/named-entity-recognition/)

[home](https://md.research.elamur.ai/free/en/) / [concepts](https://md.research.elamur.ai/free/en/concepts/) / Named entity recognition

# 🏷️ Named entity recognition

Concept · 30 key papers · [all concepts](https://md.research.elamur.ai/free/en/concepts/)

Named entity recognition locates stretches of text that refer to specific real-world things, such as people, organizations, places, products or dates, and gives each one a category drawn from a fixed or open inventory of entity types.

Also: NER, named entity recognition and classification (NERC), entity extraction, entity identification, entity chunking

## What it is

Named entity recognition (NER) turns unstructured text into a list of typed mentions. In "Andrew Little met Microsoft executives in Bonn", a system should mark "Andrew Little" as a person, "Microsoft" as an organization and "Bonn" as a location. The task has two parts. Segmentation finds where a name begins and ends. Classification decides what kind of thing the name denotes.

Inventories vary by benchmark. The CoNLL-2003 news data uses four labels: person, location, organization and miscellaneous ([Sang & Meulder 2003](https://md.research.elamur.ai/free/en/papers/sang-2003-introduction-conll-2003-shared-task/); [McCallum & Li 2003](https://md.research.elamur.ai/free/en/papers/mccallum-2003-early-results-named-entity-recognition/)). The MUC evaluations also covered times, dates, percentages and monetary amounts ([Zhou & Su 2002](https://md.research.elamur.ai/free/en/papers/zhou-2002-named-entity-recognition-hmm-based/)). Biomedical NER targets proteins, DNA, RNA, cell types and cell lines ([Collier et al. 2004](https://md.research.elamur.ai/free/en/papers/collier-2004-introduction-bio-entity-recognition-task/)).

A further distinction separates two settings. In flat NER, mentions never overlap. In nested NER, one mention sits inside another, as with a country inside an organization name ([Finkel & Manning 2009](https://md.research.elamur.ai/free/en/papers/finkel-2009-nested-named-entity-recognition/); [Li et al. 2020](https://md.research.elamur.ai/free/en/papers/li-2020-unified-mrc-framework-named-entity/)).

NER is often the first stage of a larger pipeline. Entity linking maps each recognized mention to a knowledge-base entry ([Bunescu & Paşca 2006](https://md.research.elamur.ai/free/en/papers/bunescu-2006-encyclopedic-knowledge-named-entity-disambiguation/); [Yamada et al. 2016](https://md.research.elamur.ai/free/en/papers/yamada-2016-joint-learning-embedding-words-entities/); [Wu et al. 2020](https://md.research.elamur.ai/free/en/papers/wu-2020-scalable-zero-shot-entity-linking/)). Relation discovery then looks for links between pairs of tagged entities ([Hasegawa et al. 2004](https://md.research.elamur.ai/free/en/papers/hasegawa-2004-discovering-relations-among-named-entities/)).

## The key idea

The dominant formulation treats NER as sequence labeling. Each token receives a tag that encodes both its position inside an entity and the entity type. The resulting tag sequence can then be decoded back into spans.

| Token | Andrew | Little | visited | New | York |
| --- | --- | --- | --- | --- | --- |
| BIO | B-PER | I-PER | O | B-LOC | I-LOC |
| BILOU | B-PER | L-PER | O | B-LOC | L-LOC |

In BIO, B marks the beginning of a span, I marks a token inside it, and O marks a token outside any entity. BILOU (also called BIOES) adds L for the last token of a span and U for a single-token entity. On CoNLL-2003 test data, BILOU outperformed BIO, at 90.57 versus 89.15 F1 ([Ratinov & Roth 2009](https://md.research.elamur.ai/free/en/papers/ratinov-2009-design-challenges-misconceptions-named-entity/)).

A classic model for scoring tag sequences is the linear-chain conditional random field:

```
P(y | x) = (1 / Z(x)) · exp( Σₜ Σₖ λₖ · fₖ(yₜ₋₁, yₜ, x, t) )
```

Here x is the input sentence and y = y₁ … yₙ is a candidate tag sequence. The index t runs over token positions, and y₀ is a fixed start symbol. Each fₖ is a feature function. It looks at the previous tag yₜ₋₁, the current tag yₜ and any part of the sentence around position t. Typical features include capitalization, affixes or a gazetteer match. Each λₖ is a learned weight. Z(x) is a normalizing sum over all possible tag sequences, so the probabilities add to one. The best sequence is found with Viterbi dynamic programming.

McCallum and Li used this model, and so did Settles, each with a different feature set ([McCallum & Li 2003](https://md.research.elamur.ai/free/en/papers/mccallum-2003-early-results-named-entity-recognition/); [Settles 2004](https://md.research.elamur.ai/free/en/papers/settles-2004-biomedical-named-entity-recognition-conditional/)). In neural systems, the hand-built fₖ are replaced by scores computed from learned token representations. One example is a character CNN combined with a bidirectional LSTM ([Chiu & Nichols 2015](https://md.research.elamur.ai/free/en/papers/chiu-2015-named-entity-recognition-bidirectional-lstm/)). Another is a bidirectional LSTM topped by a CRF output layer ([Lample et al. 2016](https://md.research.elamur.ai/free/en/papers/lample-2016-neural-architectures-named-entity-recognition/)).

Exact structured decoding is not always essential. For a model trained on CoNLL-2003 with baseline features, greedy left-to-right decoding scored nearly the same as Viterbi (83.29 vs 83.71 F1) and ran over 100 times faster ([Ratinov & Roth 2009](https://md.research.elamur.ai/free/en/papers/ratinov-2009-design-challenges-misconceptions-named-entity/)).

Several alternatives to per-token tagging now exist:

- Span classification scores every start–end pair directly, as in a biaffine parser-style model ([Yu et al. 2020](https://md.research.elamur.ai/free/en/papers/yu-2020-named-entity-recognition-as-dependency/)).
- Question answering phrases each entity type as a query and extracts the answer spans ([Li et al. 2020](https://md.research.elamur.ai/free/en/papers/li-2020-unified-mrc-framework-named-entity/)).
- Generation produces marked-up text or filled templates. It uses either a sequence-to-sequence (seq2seq) model, which maps an input text to an output text, or a large language model, a very large pretrained text generator steered by prompts ([Cui et al. 2021](https://md.research.elamur.ai/free/en/papers/cui-2021-template-based-named-entity-recognition/); [Wang et al. 2025](https://md.research.elamur.ai/free/en/papers/wang-2025-gpt-ner-named-entity-recognition/)).

## History and founding papers

The task took its modern shape in the named entity evaluations of the Message Understanding Conferences, notably MUC-6 and MUC-7. Systems in those evaluations often relied on hand-written rules and name lists ([Zhou & Su 2002](https://md.research.elamur.ai/free/en/papers/zhou-2002-named-entity-recognition-hmm-based/); [Mikheev et al. 1999](https://md.research.elamur.ai/free/en/papers/mikheev-1999-named-entity-recognition-without-gazetteers/)). Mikheev, Moens and Grover questioned how much those lists mattered. On MUC-7 data, their system recognized persons and organizations in the high-80s F-range with no gazetteers at all. A small list of well-known place names recovered most of the location performance ([Mikheev et al. 1999](https://md.research.elamur.ai/free/en/papers/mikheev-1999-named-entity-recognition-without-gazetteers/)).

In the same year, Collins and Singer showed that names could be classified from just seven seed rules plus unlabeled text. Their method exploited two redundant views of each example, spelling and context. It exceeded 91% accuracy on a hand-labelled test set drawn from 1,000 random examples ([Collins & Singer 1999](https://md.research.elamur.ai/free/en/papers/collins-1999-unsupervised-models-named-entity-classification/)).

Statistical learning soon matched rule-based systems. Zhou and Su's HMM chunk tagger reported F-measures of 96.6 on MUC-6 and 94.1 on MUC-7 ([Zhou & Su 2002](https://md.research.elamur.ai/free/en/papers/zhou-2002-named-entity-recognition-hmm-based/)).

The CoNLL-2003 shared task gave the field a lasting multilingual benchmark in English and German ([Sang & Meulder 2003](https://md.research.elamur.ai/free/en/papers/sang-2003-introduction-conll-2003-shared-task/)). One entry was a CRF with automatic feature induction and web-harvested lexicons. It reached 84.04 F1 on English test data with about 6.4 thousand features ([McCallum & Li 2003](https://md.research.elamur.ai/free/en/papers/mccallum-2003-early-results-named-entity-recognition/)). Another entry combined several diverse classifiers and reached 88.76 F1 on English test data ([Florian et al. 2003](https://md.research.elamur.ai/free/en/papers/florian-2003-named-entity-recognition-through-classifier/)).

Biomedical NER gained its reference benchmark with JNLPBA 2004. There the best total F-score was 72.6 ([Collier et al. 2004](https://md.research.elamur.ai/free/en/papers/collier-2004-introduction-bio-entity-recognition-task/)), and a CRF with mainly orthographic features scored 69.8 ([Settles 2004](https://md.research.elamur.ai/free/en/papers/settles-2004-biomedical-named-entity-recognition-conditional/)).

Ratinov and Roth then examined the main design choices in a systematic study: chunk encoding, decoding, non-local features and external knowledge. Their system reached 90.8 F1 on CoNLL-2003 ([Ratinov & Roth 2009](https://md.research.elamur.ai/free/en/papers/ratinov-2009-design-challenges-misconceptions-named-entity/)). Finkel and Manning recast nested NER as constituency parsing ([Finkel & Manning 2009](https://md.research.elamur.ai/free/en/papers/finkel-2009-nested-named-entity-recognition/)).

The neural turn came around 2015–2016. Chiu and Nichols combined a character-level CNN with a stacked bidirectional LSTM. They reported 91.62 F1 on CoNLL-2003 and 86.28 on OntoNotes 5.0 ([Chiu & Nichols 2015](https://md.research.elamur.ai/free/en/papers/chiu-2015-named-entity-recognition-bidirectional-lstm/)). Lample and colleagues proposed two taggers: a bidirectional LSTM with a CRF output layer and a transition-based stack-LSTM model ([Lample et al. 2016](https://md.research.elamur.ai/free/en/papers/lample-2016-neural-architectures-named-entity-recognition/)). A survey of this period built on the first of these by adding affix features. It found that neural models learning their own features outperformed feature-engineered systems on CoNLL-2002 and CoNLL-2003 news data in all four languages: Spanish, Dutch, English and German ([Yadav & Bethard 2018](https://md.research.elamur.ai/free/en/papers/yadav-2018-survey-recent-advances-named-entity/)).

## How it is used today

Pretrained transformer encoders now underlie most high-scoring systems. A biaffine span model using BERT reached 93.5 F1 on English CoNLL-2003. At its publication in 2020, it also reported the best results on the nested corpora ACE 2004, ACE 2005 and GENIA ([Yu et al. 2020](https://md.research.elamur.ai/free/en/papers/yu-2020-named-entity-recognition-as-dependency/)).

Nested labels can also be linearized into per-token label sequences instead of explicit trees, hypergraphs or stacked recognizers. In one study using this encoding, a multilabel LSTM-CRF suited flat or lightly nested data. A seq2seq decoder, even without contextual embeddings, beat the previous best results on ACE-2004, ACE-2005, GENIA and the Czech CNEC corpus ([Straková et al. 2019](https://md.research.elamur.ai/free/en/papers/strakova-2019-neural-architectures-nested-ner-through/)).

Efficiency remains a practical concern for large-scale tagging. Iterated dilated convolutions came close to Bi-LSTM-CRF accuracy while being 14–20 times faster at test time ([Strubell et al. 2017](https://md.research.elamur.ai/free/en/papers/strubell-2017-fast-accurate-entity-recognition-iterated/)).

Language-specific issues shape model design. Chinese has no explicit word boundaries. This has motivated lattice models that inject lexicon words without committing to one segmentation ([Zhang & Yang 2018](https://md.research.elamur.ai/free/en/papers/zhang-2018-chinese-ner-lattice-lstm/)). A later transformer variant, FLAT, encodes the lattice through relative positions. It beats lattice LSTM in average F1 and runs faster at inference. Batching speeds FLAT up 4.97 times, against 2.1 times for lattice LSTM ([Li et al. 2020](https://md.research.elamur.ai/free/en/papers/li-2020-flat-chinese-ner-flat-lattice/)).

Social-media text required separate work:

- English tweets: tweet-adapted tagging pipelines with distant supervision from Freebase ([Ritter et al. 2011](https://md.research.elamur.ai/free/en/papers/ritter-2011-named-entity-recognition-tweets-experimental/)), and KNN-plus-CRF bootstrapping ([Liu et al. 2011](https://md.research.elamur.ai/free/en/papers/liu-2011-recognizing-named-entities-tweets/)).
- Chinese Weibo posts: embeddings trained jointly with the tagger. Test F1 still stayed around 44 for name mentions and around 40 for name plus nominal mentions ([Peng & Dredze 2015](https://md.research.elamur.ai/free/en/papers/peng-2015-named-entity-recognition-chinese-social/)).

Coverage of more languages is expanding through community datasets such as MasakhaNER for ten African languages ([Adelani et al. 2021](https://md.research.elamur.ai/free/en/papers/adelani-2021-masakhaner-named-entity-recognition-african/)).

In low-resource settings, prompting and generation are increasingly common. One approach uses BART, a pretrained seq2seq model, to score filled natural-language templates for each candidate span. It beat fine-tuned BERT by 10.88 to 15.34 F1 in low-resource transfer to the MIT Movie, MIT Restaurant and ATIS (flight) datasets ([Cui et al. 2021](https://md.research.elamur.ai/free/en/papers/cui-2021-template-based-named-entity-recognition/)). GPT-NER reported roughly 60 F1 with just 8 training sentences, where supervised models scored near zero ([Wang et al. 2025](https://md.research.elamur.ai/free/en/papers/wang-2025-gpt-ner-named-entity-recognition/)).

## Open questions

Generalization beyond memorized names is the central unresolved issue. The WNUT 2017 task removed test texts whose entity surface forms already appeared in training. The best system then reached only about 42 entity F1 ([Derczynski et al. 2017](https://md.research.elamur.ai/free/en/papers/derczynski-2017-results-wnut2017-shared-task-novel/)). Similar weaknesses appear elsewhere. In MasakhaNER, entities unseen in training lost about 5 F1 points, and entities of four or more words lost about 20 ([Adelani et al. 2021](https://md.research.elamur.ai/free/en/papers/adelani-2021-masakhaner-named-entity-recognition-african/)).

Domain shift remains severe. Stanford NER, trained on CoNLL-2003 news, fell from 90.8 F1 on news to 45.8 F1 on tweets ([Liu et al. 2011](https://md.research.elamur.ai/free/en/papers/liu-2011-recognizing-named-entities-tweets/)). This is a different tagger from LBJ-NER, despite the identical news figure. Transfer from Wikipedia-based data to African-language news stayed below 40 F1 ([Adelani et al. 2021](https://md.research.elamur.ai/free/en/papers/adelani-2021-masakhaner-named-entity-recognition-african/)). How best to transfer across domains, languages and label sets is still open. Query-based and template-based models are promising candidates ([Li et al. 2020](https://md.research.elamur.ai/free/en/papers/li-2020-unified-mrc-framework-named-entity/); [Cui et al. 2021](https://md.research.elamur.ai/free/en/papers/cui-2021-template-based-named-entity-recognition/)).

Other questions concern resources and evaluation:

- The value of external knowledge such as gazetteers is inconsistent across settings ([Mikheev et al. 1999](https://md.research.elamur.ai/free/en/papers/mikheev-1999-named-entity-recognition-without-gazetteers/); [Settles 2004](https://md.research.elamur.ai/free/en/papers/settles-2004-biomedical-named-entity-recognition-conditional/)).
- Annotation quality limits measured progress. In one Weibo error analysis, about 43% of sampled errors were annotation mistakes ([Peng & Dredze 2015](https://md.research.elamur.ai/free/en/papers/peng-2015-named-entity-recognition-chinese-social/)).
- It is unclear when large language models can reliably replace supervised taggers, given their tendency to overpredict entities ([Wang et al. 2025](https://md.research.elamur.ai/free/en/papers/wang-2025-gpt-ner-named-entity-recognition/)).
- Whether nested structure should be kept in corpora and modeled by default is still debated ([Finkel & Manning 2009](https://md.research.elamur.ai/free/en/papers/finkel-2009-nested-named-entity-recognition/)).

## Key papers

The works this page cites, the most cited first; citations as counted by OpenAlex plus the papers of this library that cite the work, read 2026-10-23.

- [Named Entity Recognition with Bidirectional LSTM-CNNs](https://md.research.elamur.ai/free/en/papers/chiu-2015-named-entity-recognition-bidirectional-lstm/) — Jason P. C. Chiu, Eric Nichols · 2015 · 2,276 citations
- [Design Challenges and Misconceptions in Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/ratinov-2009-design-challenges-misconceptions-named-entity/) — Lev Ratinov, Dan Roth · 2009 · 1,836 citations
- [Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/sang-2003-introduction-conll-2003-shared-task/) — Erik F. Tjong Kim Sang, Fien De Meulder · 2003 · 1,479 citations
- [Named Entity Recognition in Tweets: An Experimental Study](https://md.research.elamur.ai/free/en/papers/ritter-2011-named-entity-recognition-tweets-experimental/) — Alan Ritter, Sam Clark, Mausam et al. · 2011 · 1,451 citations
- [Early results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-Enhanced Lexicons](https://md.research.elamur.ai/free/en/papers/mccallum-2003-early-results-named-entity-recognition/) — Andrew McCallum, Wei Li · 2003 · 1,335 citations
- [Neural Architectures for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/lample-2016-neural-architectures-named-entity-recognition/) — Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian et al. · 2016 · 1,021 citations
- [Unsupervised Models for Named Entity Classification](https://md.research.elamur.ai/free/en/papers/collins-1999-unsupervised-models-named-entity-classification/) — Michael Collins, Yoram Singer · 1999 · 991 citations
- [Chinese NER Using Lattice LSTM](https://md.research.elamur.ai/free/en/papers/zhang-2018-chinese-ner-lattice-lstm/) — Yue Zhang, Jie Yang · 2018 · 990 citations
- [Using Encyclopedic Knowledge for Named entity Disambiguation](https://md.research.elamur.ai/free/en/papers/bunescu-2006-encyclopedic-knowledge-named-entity-disambiguation/) — Razvan Bunescu, Marius Paşca · 2006 · 978 citations
- [A Unified MRC Framework for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/li-2020-unified-mrc-framework-named-entity/) — Xiaoya Li, Jingrong Feng, Yuxian Meng et al. · 2020 · 833 citations
- [Named Entity Recognition using an HMM-based Chunk Tagger](https://md.research.elamur.ai/free/en/papers/zhou-2002-named-entity-recognition-hmm-based/) — GuoDong Zhou, Jian Su · 2002 · 794 citations
- [Introduction to the Bio-entity Recognition Task at JNLPBA](https://md.research.elamur.ai/free/en/papers/collier-2004-introduction-bio-entity-recognition-task/) — Nigel Collier, Tomoko Ohta, Yoshimasa Tsuruoka et al. · 2004 · 731 citations
- [Scalable Zero-shot Entity Linking with Dense Entity Retrieval](https://md.research.elamur.ai/free/en/papers/wu-2020-scalable-zero-shot-entity-linking/) — Ledell Wu, Fabio Petroni, Martin Josifoski et al. · 2020 · 618 citations
- [Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets](https://md.research.elamur.ai/free/en/papers/settles-2004-biomedical-named-entity-recognition-conditional/) — Burr Settles · 2004 · 600 citations
- [Named Entity Recognition as Dependency Parsing](https://md.research.elamur.ai/free/en/papers/yu-2020-named-entity-recognition-as-dependency/) — Juntao Yu, Bernd Bohnet, Massimo Poesio · 2020 · 594 citations
- [A Survey on Recent Advances in Named Entity Recognition from Deep Learning models](https://md.research.elamur.ai/free/en/papers/yadav-2018-survey-recent-advances-named-entity/) — Vikas Yadav, Steven Bethard · 2018 · 565 citations
- [Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://md.research.elamur.ai/free/en/papers/strubell-2017-fast-accurate-entity-recognition-iterated/) — Emma Strubell, Patrick Verga, David Belanger et al. · 2017 · 544 citations
- [Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition](https://md.research.elamur.ai/free/en/papers/derczynski-2017-results-wnut2017-shared-task-novel/) — Leon Derczynski, Eric Nichols, Marieke van Erp et al. · 2017 · 534 citations
- [FLAT: Chinese NER Using Flat-Lattice Transformer](https://md.research.elamur.ai/free/en/papers/li-2020-flat-chinese-ner-flat-lattice/) — Xiaonan Li, Hang Yan, Xipeng Qiu et al. · 2020 · 503 citations
- [Named Entity Recognition without Gazetteers](https://md.research.elamur.ai/free/en/papers/mikheev-1999-named-entity-recognition-without-gazetteers/) — Andrei Mikheev, Marc Moens, Claire Grover · 1999 · 502 citations
- [Discovering Relations among Named Entities from Large Corpora](https://md.research.elamur.ai/free/en/papers/hasegawa-2004-discovering-relations-among-named-entities/) — Takaaki Hasegawa, Satoshi Sekine, Ralph Grishman · 2004 · 486 citations
- [Named Entity Recognition through Classifier Combination](https://md.research.elamur.ai/free/en/papers/florian-2003-named-entity-recognition-through-classifier/) — Radu Florian, Abe Ittycheriah, Hongyan Jing et al. · 2003 · 484 citations
- [Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings](https://md.research.elamur.ai/free/en/papers/peng-2015-named-entity-recognition-chinese-social/) — Nanyun Peng, Mark Dredze · 2015 · 481 citations
- [GPT-NER: Named Entity Recognition via Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2025-gpt-ner-named-entity-recognition/) — Shuhe Wang, Xiaofei Sun, Xiaoya Li et al. · 2025 · 436 citations
- [Recognizing Named Entities in Tweets](https://md.research.elamur.ai/free/en/papers/liu-2011-recognizing-named-entities-tweets/) — Xiaohua Liu, Shaodian Zhang, Furu Wei et al. · 2011 · 435 citations
- [MasakhaNER: Named Entity Recognition for African Languages](https://md.research.elamur.ai/free/en/papers/adelani-2021-masakhaner-named-entity-recognition-african/) — David Ifeoluwa Adelani, Jade Abbott, Graham Neubig et al. · 2021 · 429 citations
- [Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://md.research.elamur.ai/free/en/papers/yamada-2016-joint-learning-embedding-words-entities/) — Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda et al. · 2016 · 427 citations
- [Template-Based Named Entity Recognition Using BART](https://md.research.elamur.ai/free/en/papers/cui-2021-template-based-named-entity-recognition/) — Leyang Cui, Yu Wu, Jian Liu et al. · 2021 · 420 citations
- [Nested Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/finkel-2009-nested-named-entity-recognition/) — Jenny Rose Finkel, Christopher D. Manning · 2009 · 403 citations
- [Neural Architectures for Nested NER through Linearization](https://md.research.elamur.ai/free/en/papers/strakova-2019-neural-architectures-nested-ner-through/) — Jana Straková, Milan Straka, Jan Hajic · 2019 · 400 citations

## Related concepts

- [Coreference resolution](https://md.research.elamur.ai/free/en/concepts/coreference-resolution/) — Coreference resolution is the task of finding the expressions in a text that refer to the same entity as one another, such as names…
- [Part-of-speech tagging](https://md.research.elamur.ai/free/en/concepts/part-of-speech-tagging/) — Part-of-speech tagging is the task of assigning each token in a text a grammatical category, such as noun, verb, adjective or determiner…
- [Word embeddings](https://md.research.elamur.ai/free/en/concepts/word-embeddings/) — Word embeddings are dense, real-valued vectors that represent the words of a vocabulary as points in a shared geometric space. They are…
- [Knowledge representation and reasoning](https://md.research.elamur.ai/free/en/concepts/knowledge-representation/) — Knowledge representation and reasoning is the area of artificial intelligence that studies how facts, concepts and rules about a domain can…

## More papers

Topics: [🏷️ Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · [🔎 Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/)

Shelves: [💬 Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

- [← previous concept Minimum description length](https://md.research.elamur.ai/free/en/concepts/minimum-description-length/)
- [next concept → Ontology engineering](https://md.research.elamur.ai/free/en/concepts/ontology-engineering/)
- [↑ back to concepts](https://md.research.elamur.ai/free/en/concepts/)