Meta tags:

Headings (most frequently used words):

named, entity, recognition, contents, problem, approaches, history, see, also, references, definition, difficulties, formal, evaluation, current, challenges,

Text of the page (most frequently used words):
the (123), and (72), #entity (64), for (49), named (46), #recognition (30), language (27), text (26), ner (26), that (21), processing (18), name (18), learning (17), such (17), wikipedia (16), from (16), example (16), extraction (16), entities (15), pdf (15), systems (15), this (14), natural (14), been (14), with (13), computational (13), edit (13), can (13), are (13), names (13), linguistics (12), information (12), types (12), based (12), speech (11), word (11), model (10), semantic (10), statistical (10), have (10), many (10), 2013 (9), evaluation (9), also (9), some (9), token (9), refer (9), search (8), analysis (8), user (8), system (8), proceedings (8), association (8), task (8), has (8), one (8), not (8), person (8), may (7), organization (7), retrieved (7), data (7), models (7), isbn (7), workshop (7), noisy (7), june (7), but (7), well (7), used (7), was (6), categories (6), segmentation (6), machine (6), part (6), 978 (6), 2016 (6), supervised (6), definition (6), see (6), approaches (6), problem (6), which (6), precision (6), defined (6), using (5), non (5), page (5), all (5), july (5), linguistic (5), simple (5), lexical (5), words (5), james (5), generated (5), twitter (5), doi (5), semi (5), random (5), vol (5), two (5), domain (5), rigid (5), other (5), proposed (5), typically (5), history (5), case (5), tokens (5), type (5), first (5), ford (5), toggle (4), contents (4), about (4), terms (4), articles (4), tasks (4), org (4), related (4), automatic (4), computer (4), classification (4), english (4), knowledge (4), term (4), resolution (4), general (4), 2nd (4), prentice (4), hall (4), 2015 (4), linking (4), archived (4), original (4), conditional (4), fields (4), conference (4), high (4), standard (4), 2006 (4), grained (4), challenges (4), muc (4), 2001 (4), state (4), art (4), into (4), conll (4), designators (4), new (4), references (4), identifying (4), expressions (4), there (4), different (4), main (4), context (4), features (4), they (4), often (4), etc (4), recall (4), might (4), same (4), predicted (4), when (4), year (4), hide (4), move (4), sidebar (4), topic (3), languages (3), view (3), last (3), errors (3), short (3), wikidata (3), https (3), formal (3), annotation (3), interface (3), question (3), answering (3), grammar (3), document (3), identification (3), bank (3), corpus (3), open (3), rule (3), chunking (3), disambiguation (3), mining (3), coreference (3), jurafsky (3), martin (3), upper (3), saddle (3), river (3), coling (3), bidirectional (3), han (3), kim (3), ritter (3), tweets (3), pages (3), sam (3), chinese (3), ijcnlp (3), eds (3), quality (3), gold (3), fine (3), 2010 (3), 2009 (3), annual (3), meeting (3), cite (3), help (3), artificial (3), intelligence (3), gazetteers (3), sekine (3), hierarchy (3), 2003 (3), york (3), university (3), research (3), url (3), recently (3), important (3), being (3), domains (3), recent (3), human (3), current (3), scored (3), perform (3), work (3), then (3), several (3), interest (3), article (3), more (3), uppercase (3), given (3), over (3), follows (3), correct (3), score (3), these (3), exactly (3), location (3), spans (3), accuracy (3), what (3), real (3), second (3), finding (3), personal (3), cases (3), measures (3), account (3), company (3), tools (3), table (2), contact (2), privacy (2), policy (2), available (2), use (2), hidden (2), deprecated (2), need (2), updating (2), 2021 (2), description (2), matches (2), spacy (2), semantics (2), vision (2), character (2), sentiment (2), checker (2), assisted (2), allocation (2), latent (2), retrieval (2), large (2), translation (2), sentence (2), summarization (2), compound (2), sense (2), detection (2), parsing (2), ontology (2), reading (2), deep (2), complete (2), daniel (2), 2008 (2), 0131873216 (2), partial (2), nut (2), december (2), osaka (2), japan (2), organizing (2), committee (2), wnut (2), 135 (2), s2cid (2), shared (2), normalization (2), 2014 (2), local (2), 2019 (2), link (2), feng (2), aaron (2), wong (2), fai (2), chao (2), lidia (2), graph (2), acl (2), proceeding (2), international (2), queries (2), web (2), crowdsourcing (2), lee (2), lecture (2), notes (2), science (2), 540 (2), 1007 (2), technology (2), 2012 (2), ratinov (2), method (2), overview (2), april (2), 1998 (2), proper (2), journalistic (2), texts (2), citeseerx (2), chemical (2), drug (2), chemdner (2), wolf (2), julien (2), 2020 (2), empirical (2), methods (2), transformers (2), nadeau (2), david (2), henry (2), introduction (2), press (2), cross (2), 2011 (2), extended (2), lluís (2), 2007 (2), encyclopedia (2), kripke (2), saul (2), identity (2), another (2), seen (2), challenging (2), considered (2), communities (2), performances (2), wiki (2), instance (2), where (2), output (2), researchers (2), did (2), specific (2), performance (2), across (2), projects (2), turned (2), obtain (2), deal (2), while (2), measure (2), were (2), considerable (2), effort (2), included (2), medical (2), most (2), common (2), content (2), events (2), list (2), any (2), era (2), surrounding (2), target (2), items (2), itself (2), include (2), annotated (2), includes (2), out (2), created (2), single (2), wrong (2), error (2), contribute (2), always (2), titles (2), ground (2), every (2), issues (2), kinds (2), how (2), number (2), hans (2), blick (2), correctly (2), problems (2), full (2), his (2), madison (2), assigning (2), completely (2), smith (2), than (2), desired (2), missing (2), however (2), those (2), values (2), jfk (2), difficulties (2), certain (2), 2002 (2), subtypes (2), percentages (2), month (2), temporal (2), phase (2), america (2), things (2), expression (2), referent (2), although (2), jim (2), bought (2), 300 (2), shares (2), acme (2), corp (2), time (2), block (2), pre (2), unstructured (2), here (2), html (2), xml (2), appearance (2), upload (2), file (2), changes (2), links (2), read (2), subsection (2), log (2), create (2), donate (2), menu (2), add, mobile, cookie, statement, statistics, developers, code, conduct, legal, safety, contacts, disclaimers, under, additional, apply, site, you, agree, registered, trademark, profit, wikimedia, foundation, inc, creative, commons, attribution, sharealike, license, rendered, parsoid, edited, august, 2026, utc, cs1, parameters, index, php, title, entity_recognition, oldid, 1368156295, gnd, authority, control, databases, toolkit, benchmark, hallucination, gensim, action, optical, multimodal, clip, image, visual, voice, virtual, assistant, prompt, engineering, interactive, fiction, chatbot, spell, pronunciation, assessment, predictive, concordancer, automated, essay, scoring, reviewing, pachinko, dirichlet, dynamic, generation, synthesis, capture, wordnet, uby, google, ngram, viewer, framenet, dbpedia, babelnet, universal, dependencies, treebank, thesaurus, network, propbank, parallel, readable, dictionary, linked, resource, standards, datasets, corpora, resources, word2vec, embedding, transformer, seq2seq, long, memory, small, glove, fasttext, explicit, matrix, bert, distributional, neural, transfer, simplification, multi, stemming, lemmatization, induction, truecasing, textual, entailment, terminology, adversarial, stylometry, stance, similarity, decomposition, role, labeling, tagging, syntactic, logic, distant, concept, collocation, argument, stop, understanding, trigram, bigram, gram, bag, limsopatham, collier, nigel, 152, 145, lstm, messages, partalas, ioannis, lopez, cédric, derbas, nadia, kalitvianski, ruslan, 177, 171, recognizing, 2022, github, baldwin, timothy, marneffe, marie, catherine, young, bum, alan, wei, beijing, china, 14500933, 2078, 284718, hdl, 18653, w15, 4319, 126, derczynski, leon, giuseppe, rizzo, marieke, van, erp, genevieve, gorrell, raphael, troncy, johann, petrak, kalian, botcheva, management, diana, maynard, global, algorithms, documents, encyclopedic, zeng, xiaodong, derek, sighan, light, characteristics, intelligent, klopotek, iis, lncs, 7912, eiselt, andreas, figueroa, alejandro, 833, 829, step, recognizer, development, clinical, changki, hwang, gyu, hyo, jung, lim, soojong, heo, jeong, chung, hee, hyeon, jin, wang, hyun, jang, myung, gil, 4182, 587, 45780, 11880592_49, 581, frustratingly, easy, adaptation, roth, 147, 155, thirteenth, design, misconceptions, turian, bengio, representations, 48th, 384, 394, elaine, marsh, dennis, perzanowski, results, poibeau, thierry, kosseim, leila, computers, 157, 12591786, 33390, 1163, 9789004333901_011, 144, netherlands, 2000, uses, parameter, book, krallinger, leitner, rabal, vazquez, oyarzabal, valencia, 684, 4118, fourth, biocreative, challenge, debut, lysandre, sanh, victor, chaumond, delangue, clement, moi, anthony, cistac, pierric, rault, tim, louf, remi, funtowicz, morgan, davison, joe, shleifer, von, platen, patrick, clara, jernite, yacine, plu, canwen, scao, teven, gugger, sylvain, drame, mariama, lhoest, quentin, thomas, rush, alexander, demonstrations, jenny, rose, finkel, trond, grenager, christopher, manning, 2005, 43rd, 370, 363, incorporating, gibbs, sampling, turney, peter, matwin, stan, lamontagne, luc, marchand, mario, 3060, berlin, heidelberg, springer, 277, 34630, 11766247_23, 266, advances, unsupervised, generating, resolving, ambiguity, mikheev, andrei, moens, marc, grover, claire, 1999, thompson, lascarides, alex, bergen, norway, ninth, european, chapter, without, dan, series, pearson, 213375806, oclc, 187321, nothman, joel, 175, 1016, artint, 006, 151, 194, multilingual, lin, dekang, xiaoyun, 1038, 1030, phrase, clustering, discriminative, kapetanios, epaminondas, tatar, doina, sacarea, christian, crc, 298, 9781466584969, aspects, esuli, andrea, sebastiani, fabrizio, forum, clef, 111, 100, evaluating, clark, mausam, etzioni, proc, experimental, study, nlp, nyu, edu, brunstein, ada, consortium, ldc, catalog, guidelines, answer, webknox, com, tjong, sang, erik, meulder, fien, independent, carreras, xavier, màrquez, padró, extractor, adaboost, satoshi, lingvisticae, investigationes, survey, laporte, joseph, 2018, stanford, philosophy, 1971, necessity, munitz, city, individuation, smart, tag, microsoft, record, linkage, onomastics, aka, controlled, vocabulary, field, progress, remains, application, microblogs, due, orthography, shortness, informality, organized, compare, various, crfs, lstms, michael, jordan, professor, berkeley, university_of_california, _berkeley, michael_i, _jordan, emerging, extremely, actual, describing, potentially, ambiguous, concepts, below, wikification, them, who, comparisons, hmm, crf, feature, sets, maximum, entropy, markov, despite, numbers, reported, dataset, far, solved, efforts, directed, reducing, annotations, labor, employing, robust, scaling, years, promising, solution, aggregate, judgments, devising, linguistically, complex, contexts, produce, near, best, entering, annotators, indicated, even, brittle, meaning, developed, involved, tuning, true, both, trainable, early, 1990s, aimed, primarily, attention, military, dispatches, reports, later, stages, ace, informal, styles, conversational, telephone, conversations, since, great, gene, products, drugs, competition, teams, participating, genes, bioinformatics, molecular, biology, transcripts, weblogs, section, needs, please, update, reflect, newly, updated, classifier, learned, typical, choice, their, electric, augment, had, gazetteer, occurring, grams, whether, appears, lists, affixes, shape, lowercase, initial, mixed, followed, period, indicating, middle, contains, hyphen, orthographic, pattern, stemmed, labeled, usually, performed, linear, regression, decoded, commonly, viterbi, algorithm, engineered, require, amount, manually, training, suggested, avoid, semisupervised, hand, crafted, better, cost, lower, months, experienced, linguists, fast, source, visualizer, opennlp, supports, box, usable, via, api, java, graphical, gate, techniques, incorporate, multiple, matching, credit, overlapping, criterion, allow, finer, comparison, intersection, union, above, prediction, misses, spurious, class, hard, does, positively, either, thus, said, pessimistic, close, adequate, purpose, omit, compared, truth, expects, treated, because, actually, examine, decide, goals, requirements, harmonic, mean, similarly, appear, predictions, line, required, zero, averaged, academic, conferences, variant, overly, measuring, merely, count, fraction, incorrectly, identified, suffers, least, vast, majority, world, baseline, predict, extravagantly, mispredicting, span, properly, penalized, only, wanted, smaller, larger, scope, impose, restriction, never, overlap, nest, means, must, make, arbitrary, choices, inexact, substance, school, calling, partitioning, adjacent, differently, treating, jones, robinson, including, fewer, john, reasonably, obvious, fail, ways, arguably, partially, should, counted, success, failures, evaluate, usual, called, remain, just, calculate, caused, white, house, instead, metonymy, ira, irish, republican, army, individual, retirement, airport, ambiguities, united, states, son, former, president, reference, literature, consists, made, 200, breaking, experiments, social, media, freebase, bbn, hierarchies, numerical, money, instances, good, examples, invalid, ones, take, vacations, refers, undefined, arguable, loosened, practical, reasons, therefore, strict, explained, next, past, 2001st, gregorian, calendar, broken, down, conceptually, possibly, implementations, distinct, simplified, contiguous, nesting, disregarding, fact, inside, substring, formally, similar, requires, choosing, organize, restricts, strings, phrases, stand, fairly, consistently, closely, practice, deals, referents, philosophically, referred, biological, species, substances, exclude, pronouns, descriptions, pick, its, properties, opposed, individuals, dicto, motor, automotive, 1903, consisting, detected, classified, highlights, nee, structured, taking, unannotated, transducing, known, subtask, seeks, locate, classify, mentioned, per, loc, gpe, veh, quantities, monetary, codes, vehicles, geopolitical, locations, organizations, redirects, sgml, mentions, redirected, free, item, printable, version, download, print, export, switch, legacy, parser, get, shortened, permanent, actions, talk, tiếng, việt, українська, română, português, മലയാളം, 한국어, 日本語, עברית, gaeilge, français, فارسی, euskara, español, deutsch, čeština, català, العربية, top, special, community, portal, learn, navigation, jump,

Text of the page (random words):
nd de re and names for kinds of things as opposed to individuals for example bank full named entity recognition is often broken down conceptually and possibly also in implementations 4 as two distinct problems detection of names and classification of the names by the type of entity they refer to e g person organization or location 5 the first phase is typically simplified to a segmentation problem names are defined to be contiguous spans of tokens with no nesting so that bank of america is a single name disregarding the fact that inside this name the substring america is itself a name this segmentation problem is formally similar to chunking the second phase requires choosing an ontology by which to organize categories of things temporal expressions and some numerical expressions e g money percentages etc may also be considered as named entities in the context of the ner task while some instances of these types are good examples of rigid designators e g the year 2001 there are also many invalid ones e g i take my vacations in june in the first case the year 2001 refers to the 2001st year of the gregorian calendar in the second case the month june may refer to the month of an undefined year past june next june every june etc it is arguable that the definition of named entity is loosened in such cases for practical reasons the definition of the term named entity is therefore not strict and often has to be explained in the context in which it is used 6 certain hierarchies of named entity types have been proposed in the literature bbn categories proposed in 2002 are used for question answering and consists of 29 types and 64 subtypes 7 sekine s extended hierarchy proposed in 2002 is made of 200 subtypes 8 more recently in 2011 ritter used a hierarchy based on common freebase entity types in ground breaking experiments on ner over social media text 9 difficulties edit ner can have reference resolution ambiguities where the same name can refer to different entities of the same type for example jfk can refer to the former president of the united states or his son the same name can refer to completely different types jfk might refer to the airport in new york ira can refer to individual retirement account international reading association or irish republican army this can be caused by metonymy for example the white house can refer to an organization instead of a location formal evaluation edit to evaluate the quality of an ner system s output several measures have been defined the usual measures are called precision recall and f1 score however several issues remain in just how to calculate those values these statistical measures work reasonably well for the obvious cases of finding or missing a real entity exactly and for finding a non entity however ner can fail in many other ways many of which are arguably partially correct and should not be counted as complete success or failures for example identifying a real entity but with fewer tokens than desired for example missing the last token of john smith m d with more tokens than desired for example including the first word of the university of md partitioning adjacent entities differently for example treating smith jones robinson as 2 vs 3 entities assigning it a completely wrong type for example calling a personal name an organization assigning it a related but inexact type for example substance vs drug or school vs organization correctly identifying an entity when what the user wanted was a smaller or larger scope entity for example identifying james madison as a personal name when it s part of james madison university some ner systems impose the restriction that entities may never overlap or nest which means that in some cases one must make arbitrary or task specific choices one overly simple method of measuring accuracy is merely to count what fraction of all tokens in the text were correctly or incorrectly identified as part of entity references or as being entities of the correct type this suffers from at least two problems first the vast majority of tokens in real world text are not part of entity names so the baseline accuracy always predict not an entity is extravagantly high typically 90 and second mispredicting the full span of an entity name is not properly penalized finding only a person s first name when his last name follows might be scored as ½ accuracy in academic conferences such as conll a variant of the f1 score has been defined as follows 5 precision is the number of predicted entity name spans that line up exactly with spans in the gold standard evaluation data i e when person hans person blick is predicted but person hans blick was required precision for the predicted name is zero precision is then averaged over all predicted entity names recall is similarly the number of names in the gold standard that appear at exactly the same location in the predictions f1 score is the harmonic mean of these two it follows from the above definition that any prediction that misses a single token includes a spurious token or has the wrong class is a hard error and does not contribute positively to either precision or recall thus this measure may be said to be pessimistic it can be the case that many errors are close to correct and might be adequate for a given purpose for example one system might always omit titles such as ms or ph d but be compared to a system or ground truth data that expects titles to be included in that case every such name is treated as an error because of such issues it is important actually to examine the kinds of errors and decide how important they are given one s goals and requirements evaluation models based on a token by token matching have been proposed 10 such models may be given partial credit for overlapping matches such as using the intersection over union criterion they allow a finer grained evaluation and comparison of extraction systems approaches edit ner systems have been created that use linguistic grammar based techniques as well as statistical models such as machine learning state of the art systems may incorporate multiple approaches gate supports ner across many languages and domains out of the box usable via a graphical interface and a java api opennlp includes rule based and statistical named entity recognition spacy features fast statistical ner as well as an open source named entity visualizer hand crafted grammar based systems typically obtain better precision but at the cost of lower recall and months of work by experienced computational linguists 11 statistical ner systems typically require a large amount of manually annotated training data semisupervised approaches have been suggested to avoid part of the annotation effort 12 13 in the statistical learning era ner was usually performed by learning a simple linear regression model on engineered features then decoded by a bidirectional viterbi algorithm some commonly used features include 14 lexical items the token itself be labeled stemmed lexical items shape the orthographic pattern of the target word for example all lowercase all uppercase initial uppercase mixed case uppercase followed by a period often indicating a middle name contains hyphen etc affixes of the target word and surrounding words part of speech of the word whether the word appears in one or more named entity lists gazetteers words and or n grams occurring in the surrounding context a gazetteer is a list of names and their types such as general electric it can be used to augment any system for ner they had been often used in the era of statistical machine learning 15 16 many different classifier types have been used to perform machine learned ner with conditional random fields being a typical choice 17 transformers features token classification using deep learning models 18 history edit this section needs to be updated please help update this article to reflect recent events or newly available information july 2021 early work in ner systems in the 1990s was aimed primarily at extraction from journalistic articles attention then turned to processing of military dispatches and reports later stages of the automatic content extraction ace evaluation also included several types of informal text styles such as weblogs and text transcripts from conversational telephone speech conversations since about 1998 there has been a great deal of interest in entity identification in the molecular biology bioinformatics and medical natural language processing communities the most common entity of interest in that domain has been names of genes and gene products there has been also considerable interest in the recognition of chemical entities and drugs in the context of the chemdner competition with 27 teams participating in this task 19 in 2001 research indicated that even state of the art ner systems were brittle meaning that ner systems developed for one domain did not typically perform well on other domains 20 considerable effort is involved in tuning ner systems to perform well in a new domain this is true for both rule based and trainable statistical systems as of 2007 state of the art ner systems for english produce near human performance for example the best system entering muc 7 scored 93 39 of f measure while human annotators scored 97 60 and 96 95 21 22 current challenges edit despite high f1 numbers reported on the muc 7 dataset the problem of named entity recognition is far from being solved the main efforts are directed to reducing the annotations labor by employing semi supervised learning 12 23 robust performance across domains 24 25 and scaling up to fine grained entity types 8 26 in recent years many projects have turned to crowdsourcing which is a promising solution to obtain high quality aggregate human judgments for supervised and semi supervised machine learning approaches to ner 27 another challenging task is devising models to deal with linguistically complex contexts such as twitter and search queries 28 there are some researchers who did some comparisons about the ner performances from different statistical models such as hmm hidden markov model me maximum entropy and crf conditional random fields and feature sets 29 and some researchers recently proposed graph based semi supervised learning model for language specific ner tasks 30 a recently emerging task of identifying important expressions in text and cross linking them to wikipedia 31 32 33 can be seen as an instance of extremely fine grained named entity recognition where the types are the actual wikipedia pages describing the potentially ambiguous concepts below is an example output of a wikification system entity url https en wikipedia org wiki michael_i _jordan michael jordan entity is a professor at entity url https en wikipedia org wiki university_of_california _berkeley berkeley entity another field that has seen progress but remains challenging is the application of ner to twitter and other microblogs considered noisy due to non standard orthography shortness and informality of texts 34 35 ner challenges in english tweets have been organized by research communities to compare performances of various approaches such as bidirectional lstms learning to search or crfs 36 37 38 see also edit controlled vocabulary coreference resolution entity linking aka named entity normalization entity disambiguation information extraction knowledge extraction onomastics record linkage semantic web smart tag microsoft references edit kripke saul 1971 identity and necessity in m k munitz ed identity and individuation new york city new york university press pp 135 64 laporte joseph 2018 rigid designators the stanford encyclopedia of philosophy nadeau david sekine satoshi 2007 a survey of named entity recognition and classification pdf lingvisticae investigationes carreras xavier màrquez lluís padró lluís 2003 a simple named entity extractor using adaboost pdf conll 1 2 tjong kim sang erik f de meulder fien 2003 introduction to the conll 2003 shared task language independent named entity recognition conll named entity definition webknox com retrieved on 2013 07 21 brunstein ada annotation guidelines for answer types ldc catalog linguistic data consortium archived from the original on 16 april 2016 retrieved 21 july 2013 1 2 sekine s extended named entity hierarchy nlp cs nyu edu retrieved on 2013 07 21 ritter a clark s mausam etzioni o 2011 named entity recognition in tweets an experimental study pdf proc empirical methods in natural language processing esuli andrea sebastiani fabrizio 2010 evaluating information extraction pdf cross language evaluation forum clef pp 100 111 kapetanios epaminondas tatar doina sacarea christian 2013 11 14 natural language processing semantic aspects crc press p 298 isbn 9781466584969 1 2 lin dekang wu xiaoyun 2009 phrase clustering for discriminative learning pdf annual meeting of the acl and ijcnlp pp 1030 1038 nothman joel et al 2013 learning multilingual named entity recognition from wikipedia artificial intelligence 194 151 175 doi 10 1016 j artint 2012 03 006 jurafsky dan martin james h 2009 22 1 named entity recognition speech and language processing an introduction to natural language processing computational linguistics and speech recognition prentice hall series in artificial intelligence 2 ed upper saddle river n j pearson prentice hall isbn 978 0 13 187321 6 oclc 213375806 mikheev andrei moens marc grover claire june 1999 thompson henry s lascarides alex eds named entity recognition without gazetteers ninth conference of the european chapter of the association for computational linguistics bergen norway association for computational linguistics 1 8 nadeau david turney peter d matwin stan 2006 unsupervised named entity recognition generating gazetteers and resolving ambiguity in lamontagne luc marchand mario eds advances in artificial intelligence lecture notes in computer science vol 3060 berlin heidelberg springer pp 266 277 doi 10 1007 11766247_23 isbn 978 3 540 34630 2 jenny rose finkel trond grenager christopher manning 2005 incorporating non local information into information extraction systems by gibbs sampling pdf 43rd annual meeting of the association for computational linguistics pp 363 370 wolf debut lysandre sanh victor chaumond julien delangue clement moi anthony cistac pierric rault tim louf remi funtowicz morgan davison joe shleifer sam von platen patrick ma clara jernite yacine plu julien xu canwen le scao teven gugger sylvain drame mariama lhoest quentin wolf thomas rush alexander 2020 transformers state of the art natural language processing proceedings of the 2020 conference on empirical methods in natural language processing system demonstrations pp 38 45 krallinger m leitner f rabal o vazquez m oyarzabal j valencia a 2013 overview of the chemical compound and drug name recognition chemdner task proceedings of the fourth biocreative challenge evaluation workshop vol 2 pp 6 37 citeseerx ...