For disaster preparedness, a key aspect of the work is the identi cation, ahead of time, of potentially implicated locations (LOC), organizations (ORG), and persons (PER). Here we describe how static repositories of traditional news reports can be rapidly exploited to yield disaster- or accident-implicated named entities.
In the normal course of events, emergencies like natural disasters, military escalation, epidemic outbreaks etc. are almost immediately followed by some response, such as containment and mitigation e orts, counterattack, quarantine, etc., often within minutes or hours, and much of the work on emergency response is concerned with exploiting this short-term dynamics. Yet for preparedness, a key aspect of the work is the identi cation, ahead of time, of potentially implicated locations (LOC), organizations (ORG), and persons (PER). Here we describe how static repositories of traditional news reports, operating on a much slower (typically, daily) news cycle can be exploited to yield disaster- or accident-implicated named entities. Most of our results are on English data, but the bootstrap method proposed here works for any language, and to show this we evaluate our method on Hungarian as well.
Section 2 describes the current state of the Basic Emergency Vocabulary (BEV) that can be used as the basis of the classi ers we use to select emergencyrelated material in English and other languages. Section 3 outlines the main method of collecting emergency-implicated NERs, Section 4 describes an ad hoc evaluation, and Section 5 o ers some conclusions.
The idea that there is a basic vocabulary composed of a few hundred or at most
a few thousand elements goes back to the Renaissance { for a more detailed
history see [
In terms of applications, the basic concept list promises a strategy of
gradually extending the vocabulary from the simple to the more complex and
conversely, reducing the complex to the more simple. Thus, to de ne asphyxiant3 as
`chemical causing su ocation', we need to de ne su ocation, but not chemical
as this item is already listed in the basic set. Since su ocate is de ned as `to
lose one's life because of lack of air', by substitution we will obtain for
asphyxiant the de nition `chemical causing loss of life because of lack of air' where all
the key items chemical, lose, life, because, lack, air are part of the basic set.
Proper nouns like Jesus are discussed further in [
At 1,200 items, the basic list was small enough to permit manual selection of a seed emergency list, about 1/10th of the basic list, by the following principles. First, we included from the basic list every word that is, in and of itself, suggestive of emergency, such as danger, harm, or pain. Second, we selected all concepts that are likely causes of emergency, such as accident, attack, volcano, or war. Third, we selected all concepts that are concomitant with emergencies, such as damage, Dr, or treatment. Fourth, because of semantic decomposition, we added those concepts that signal emergencies only in the negative, such as breathe or safe (can't breathe, not safe, unsafe). Fifth, and nal, we added those words that will, on our judgment, appear commonly in situation reports, news articles, or even tweets related to emergencies such as calm, e ort, equipment, or situation. The full list of these manually selected entries is given in Appendix A.
It is evident that many emergency words are not basic: examples include
jettisoning and typhoon. To obtain a good sample, we analyzed the the glossary [
Of the 260 words found in the Glossary, only 41 appear on the basic list, and of these, only half (22) were found on the rst manual pass over the basic list. In hindsight it is clear that the remaining 19, area authority care develop event exercise eld general heat measure o cer plan protection range search skin smoke team waste, should also have been selected based on the above principles, especially the last ( fth) one.
The lesson from this is clear: the list has to be built from emergency materials, rather than by human expertise. But there is something of a chicken and egg problem here: to have a good list, we need to have a good corpus of emergency materials, to have a good corpus, we need to build a good classi er, and to build a good classi er, we need a good list. In the next Section we describe a method of jointly bootstrapping the list and the emergency corpus. 3
Using the BEV as positive evidence [
This is a noisy sample, only about 80% of the documents in it are actually emergency related, and we estimate recall also to be only about 80%, so there may still be about 400 further emergency-related articles in the corpus. An Fmeasure of .8 will not be impressive if our goal was detecting emergency-related articles in a live stream, but here it does not unduly a ect the logic of our enterprise: since a random document in the corpus C will be emergency related with probability p = 0:0025, but in the subset E with probability p = 0:8, words in the subsample are far more likely to be emergency-prone. To quantify this, we computed log text frequency ratio = log(T F (w; E)=T F (w; C)) for each word, and looked at those 1,700 words where this exceed the expected zero log ratio by at least two natural orders of magnitude. Of these, the ratio is greater than 3 for about a quarter (472 items), and greater than 4 for about one in 12 (135).
Since we have only 2k relatively short documents to consider, we ran the NER system from Stanford CoreNLP on these, and collected the results for all 1,700 words. Typically, words are classi ed unambiguously (label entropy is below 0.1 Two-thirds of the words in the list are emergency-related common nouns (e.g. levee, oodwater, mudslide). This number is so signi cant that we could in fact dispense with the BEV, and bootstrap the classi er starting with only two words: emergency and urgent.
Looking at the documents that contain at least one of these two words we can obtain an emergency-related corpus of documents E'. While the top of the list of words that are signi cantly more frequent in E' than in the background are not quite as good as the actual BEV listed in Appendix B (e.g. it has outright false positives like nirmala), it is good enough for further iteration. The emergency sets obtained from the BEV and from this skeletal list are practically identical, a matter we shall investigate more formally in Section 4 for Hungarian, and so are the lists of NERs.
To summarize what we have so far, we propose to identify emergency-implicated NERs by searching for those NERs that occur in an emergency-related subcorpus considerably more frequently than in the corpus as a whole. Certainly, among the hundreds of thousands of locations in NewReuters, the method puts at the top Hohenwutzen, Slibice, and Oderbruch, still very much exposed to oods of the river Oder, and Popocatepetl, a volcano that has been implicated in half a dozen new eruptions since the corpus was collected. Among persons, the top choices are `Matthias Platzeck, environment minister in the German state of Brandenburg' and `government crisis committee spokesman Krzysztof Pomes'. 4
It is clear that the precision of the system is reasonably high, even at the bottom of the range we get locations like Key Biscayne and good classi er words like around-the-clock. To measure recall is much harder, and it would take manual analysis of larger samples to obtain signi cant gures. Therefore, we decided to validate the basic idea of iteratively bootstrapping the keyword- and the document-set on a di erent language, Hungarian. We use the MagyarHirlap collection of some 44,000 newspaper articles, and start with only three words, katasztrofa `catastrophy', veszhelyzet `emergency situation', and aldozat `victim, sacri ce'. (Hungarian doesn't have a word that could be used both as a noun and an adjective to denote emergency.) word TF word TF word TF goma 5.19 13 richter-skala 3.91 34 megaradt 3.68 16 lavafolyam 4.95 15 tu}zhanyo 3.91 17 elelmiszercsomag 3.65 11 ruanda 4.81 12 foldcsuszamlas 3.90 30 aknamez}o 3.65 11 vulkankitores 4.53 16 foldrenges 3.85 148 lava 3.63 39 33-as 4.44 10 monszun 3.81 14 el}orejelz}o 3.62 17 ruandai 4.40 26 karokozo 3.77 34 epicentrum 3.56 24 l}oszerraktar 4.25 12 teletid}o 3.74 25 renges 3.48 52 evakual 4.10 21 megrongalodik 3.74 20 vegigsopr}o 3.48 13 segelyszall tmany 4.10 14 bozottu}z 3.71 36 csernobil 3.48 13 kongoi 4.07 36 nino 3.71 31 es}ozes 3.47 132 horeteg 4.05 11 hurrikan 3.69 42 vulkanikus 3.41 14 segelyszervezet 4.02 57 tornado 3.68 16 Based on these words, we found a small document set (170 documents) from which we repeated the process. The resulting wordlist required manual editing, primarily to take care of tokenization artifacts, but the top 35 words already show the same tendency, with several emergency-implicated locations (Goma, Rwanda, Chernobyl) and excellent keywords for a second pass such as vulkankitores `volcanic eruption', evakual `evacuate', or segelyszall tmany `relief supplies'. There are also entries such as 33-as `#33' which require local knowledge to understand (there was ooding along route 33 in Hungary at the time) and morphology is a much more serious issue: we see e.g. the locative adjectival form ruandai `of or pertaining to Rwanda' along with the country name.
Although the TF values are really too small for this, we performed another iteration, obtaining a slightly longer document list, and a much longer wordlist, containing many excellent keywords that could not be obtained by translating the BEV to Hungarian, supporting the observation we already made in regards to English, that manual word selection has low recall. In fact, the wordlist we obtained by a dictionary-based translation of BEV had too many elements (over 2,200) and was dominated by false positives (valid Hungarian translations that corresponded to some sense of English keywords that were not emergencyrelated). 5
Faced with the problem of building a two-way classi er selecting a small class of emergency reports from a much larger set of other (non-emergency) texts, it is tempting to put the emphasis on non-textual features such as the snowballing of reports from the same area. Here we considered `emergency' to be a topic on a par with `sports' or `computer science' or any other topic in a well-established topic hierarchy, and assumed that reports coming in later will often have reference not just to the event, but to the response as well.
This assumption is clearly borne out by the vocabularies, not so much by the BEV (which was built by knowledge engineering, with the response assumption already built in), as by the lists built iteratively based on very small seeds (in English, two words, in Hungarian, three words). The rst iteration already yields words like English evacuee or Hungarian segelyszervezet `aid organization' that only makes sense in the context of some organized response.
In the near future we plan to use the method for a systematic selection
of a far larger emergency corpus (since we build linear classi ers, the time to
do it is linear in the size of the corpus), with the expectation that not more
than a quarter of a percent of the material in a static news corpus will be
selected. Once the corpus is at hand, we can use standard NER techniques
to designate persons, organizations, and locations as emergency-implicated. We
plan to investigate whether in the context of iterated keyword-weight bootstrap
the simple recall-based ranking of selecting and weighing keywords advocated in
[
The key bene t of our proposal is that it only requires a collection of
documents, typically easily obtained by web crawl even in less well resourced
languages { everything else can be bootstrapped from minimal seeds of 2-3 words.
In better resourced languages, the iterative keyword selection method used here
can be compared to one based on word vectors [
We thank referee #2 for calling [
Dr able accident against alone angry arms army attack bad bite blood blow body bone break breathe burn calm can catch chemical cloud cold concern condition could crime crush damage danger dead destroy die dig drug e ort end energy enough equipment escape explode extreme fail fall fault ght re esh food force frighten gas grain harm hospital hot hurt ice ill injure level lightning limit mass meal medical necessary o ensive organization pain people police powerful problem protect public quick radio rain react report request risk rule safe sea serious shock shoot sick sink situation snow social soldier special speed stop strong surprise temperature tent thick thin travel treatment trouble vehicle violent volcano war weapon weather wind worry wound
Becquerel Bq Ci Curie Dr able absorb accident acute adverse a ect against agency airborne alarm alert alone angry anomaly area arms army asphyxiant assistance assurance atomic attack authority avoid bad barrier bite blast blood blow body bomb bone boundary break breathe bu er burn burning calm can cancer carcinogen care catastrophy catch chemical civilian cloud cold combat combustible compromised concentrated concern condition consequence containment contaminate cooling coordinate corrective could counterterrorism crime crisis critical crush damage danger dangerous dead debris decay declaration decontaminate defective defense degrade demolition department designated destroy destruction deteriorate develop device diarrhea die dig disaster discharge disease disperse dose dosimeter downgrade drill drug earthquake e ort embargo emergency emission end energy enough environment equipment error escape escort evacuate event exceed exclusion exercise explode explosion explosive expose exposure extreme facility fail failure fall fallout fatality fatigue fault eld ght lter re re ghter ssion ssionable ammable ashpoint esh food force frighten fuel fuse gas general grain grenade half-life harm hazard hazmat headquarters health heat hemorrhage herbicide hospital hot hotline hurricane hurt ice ignition ill illness impact inadequate inadvertent incident infect in ammation ingest inhale injure installation ionization issue jettison launch leak lethal level liason lifethreatening lightning limit loss lost malevolent malfunction management mass meal measure medical microorganism mine missile mitigate mobilize monitoring mortality nausea necessary notify nuclear o ensive o cer o site operation organization pain parameter people perimeter pesticde plan plume plutonium poison police pollute pose powerful preparedness prevent problem procedure protect public quarantine quick rad radiation radio radioactive radiology rain range react reactor recovery reentry release rem report request resolution respiration responder response restoration risk rocket rod rule sabotage safe safeguard safety scenario sea search secure security serious severe shelter shield shock shoot sick sickness sink site situation skin smoke snow social soldier spark special speed spill stabilization staging stolen stop strike strong su ocation supply surprise symptom tank target team temperature tent terrorism thermal thermonuclear thick thin threat tornado toxic toxin travel treatment tritium trouble typhoon unconscious uncontrolled unexpected unintended unintentional unstable uranium urgent vehicle victim violation violent vital volatile volcano vomiting vulnerability vulnerable war warhead waste weakness weapon weather wind worry wound zone