<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0501">
  <Title>WordNet 2 - A Morphologically and Semantically Enhanced Resource</Title>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 Word sense disambiguation of
</SectionTitle>
    <Paragraph position="0"> gloss concepts There are se~e, al dlffe~ences bet~een gloss dlsamblguauon and text dlsamb~guatmn A n-la\]oi difference is that m our project we know the meaning of each gloss, namely the synset to whmh a gloss apphes Second, the glosses contain a defimUon, comments, and one or more examples We address the word sense dmamblguaUon problem by using three complementary methods (a) heunstms, (b) conceptual dens,ty, and (c) staustins on large corpora The first two methods rely enurely on the mfolmaUon contained m WordNet, while the th,rd one uses other corpora Specffically, the sources of knowledge available to us me (1) lexlcal mformauon that includes part of speech, posluon of ~ords (1 e head word), and lexmal lelauons (2) collocauons and s)ntacuc patterns, (3) s}nset to which a gloss belongs, (4) hypernyms of s)nset and their glosses (5) synsets of pobsemouns x~o2ds and their glosses, (6) hypernyms of synsets of polysemous words, and their glosses, and so on Method 1 Classes of heur,st,cs for word sense dmarnblguatmn A statable techmque for dmamblguatmg dmuonarms is to rely on heu!mucs able to cope with d~ffe2ent sources of mformauon Work m tins alea w~ doue by Ravin (Rax m 1990) in a similar project at IBM, (Klavans et al 1990), and others We present no~ some of the heunsUcs used by us  1. Class- Hypernyms  A way of explaining a concept m to speclahze a more general concept (, e a hypernym) It m hkely that an explanatmn begins with a phrase whose head is one of ~ts hypernyms, and the features are expressed either as attributes m the same phrase o2 as phrases attached to the first phrase Example The gloss of synset {xntrusxon} is (entrance by force or without permxsslon or welcome) * entrance#3, the head of the fiist phrase, is a hype~n)m of zntruszon, thus we pick sense 3 of noun entrance (The senses in Wo2dNet a2e ,anked acco, dmg to then frequency ot occmrence m the Brown corpus, entrance#3 means sense 3 of wo, d entrance )</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Class Lmgmstlc Parallehsm
</SectionTitle>
    <Paragraph position="0"> It 2s hkel? that the s} ntacuc pal allehsm of t~ o xx ord~ uanslates into semantic parallelmm and the ~xo2ds may have a common hypernym, or one m a hypernym of the other Fo~ adjectives, the hypein) m) is replaced by the similarity relation Other heuristics in this class check ~hether or not two pol)semous words belong to the same synset, or one is a hypern} m of the other, or if they belong to the same the2 arch:y Example The gloss of {interaction} is (a mutual or. reczprocal actlon) * Adjective reciprocal has only one sense ,n Word-Net 1 6, whereas mutual has two senses But we find that between sense 2 of mutual and reciprocal there is a szmdar link m WordNet 1 6, thus pick  3. Class. Gloss Comments.</Paragraph>
    <Paragraph position="1">  In glosses, comments and examples are meant to provide supplemental information It ts possible to find the specmhzatlon o, typical relation hnkmg the comment to the preceding head phrase m one of the synsets (or gloss) of the head phrase E~ample The gloss of the synset {scuff, scuffing} IS (the act of scufflng (scraplng or dragging the feet)) * In %Y=ordNet 1 6 there is a synset {scuff#l, drag}, thus verb scuff Is dlsamblguated</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 Class. Gloss Examples
</SectionTitle>
    <Paragraph position="0"> Examples in WordNet prov,de collocatmnal reformation of the words m synsets The intrinsic semanuc tag of the word from the synset which is used in the example can occur in the same lexical relation in some other gloss, carrymg the semantic tag w,th ~t Example Synset {penetration} has the gloss (the act of forcing a way Into something) * \[wlrw2\] ---- \[force way\] The gloss of {way#9} contains the example (2 'I had xt my way' '), provldmg the lexlcal relation \[w3rw2\] = \[have way\] * Noun way is dxsamblguated (sense 9), and verbs have#7 and force#9 have a common hypernym, therefore verb force ~s also dlsambiguated</Paragraph>
  </Section>
  <Section position="8" start_page="0" end_page="0" type="metho">
    <SectionTitle>
5 Class Collocations
</SectionTitle>
    <Paragraph position="0"> Nouns representing actions ate nommahzatmns of some verbs If a verbal collocation contains a noun, and is also a s~ nonym of some mo, phologmally related verb, then ,t is likely to be the nommahzatlon source The verb from the gloss of a synonym describing an actmn, ff not the source of the nomlnahzaUon is hkely to belong to the same hmtarchy as the true nommahzatlon source, since they must share some properties Ezample Let s = {escape, flight}, with the gloss (the act of escaping physically) * The ~erb escape Is morphologically identical to the noun escape from synset s  * Sense 1 of verb escape has a hypernym collocation usmg noun flxght from s, thus is selected 6 Class Lex~cal Relat,ons %. lexlcal relatmn using a ~ ord w both in the gloss of  a s} nsct s and m some other gloss s~gnals a prope~D, of w associated u~th s In other cases x~hen ~wo ielatmns \[w,r w~\] and \[w,~ w~.\] are ~ound m txvo glosses of %%bldNet, and the~e are senses of w~ and w~ that have a common hypernym, it is hkely that the correlatmn between w, and the common hypeInym is  thus sense 4 of noun ald IS picked Method 2 Conceptual dens,ty method We have ,mplemented a WSD system for free text that disamb,guates multiple wolds mmultaneousl3 (Mlhalcea and Moldovan, 1999) The method is based on measuring the number of common nouns shared by the verb and noun hmrarchms, and thus gets around the lack of connections problem As an example, consider a verb - noun pair of uotds Denote w~th &lt; vl,v2, ,Vh &gt; and &lt; nl,n2, ,nt &gt; the senses of the verb and the noun m WoidNet Fo~ each possible pelt v, - n j, the conceptual density m computed as follows 1 Extract all the glosses from the sub-hmrmch~ of v, and determine the nouns from these glosses This constitutes the noun-context of verb v, Each such noun is stored together with a weight w that indicates the level m the sub-hmrarchy of the velb concept m whose gloss the noun was found</Paragraph>
  </Section>
  <Section position="9" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Determine the glosses of the noun sub-hmtatchy
</SectionTitle>
    <Paragraph position="0"> of nj and determine the nouns m them</Paragraph>
  </Section>
  <Section position="10" start_page="0" end_page="3" type="metho">
    <SectionTitle>
3 Compute the conceptual denszty C u of the com-
</SectionTitle>
    <Paragraph position="0"> mon concepts between the nouns obtained at (1) and the nouns obtained at (2) using the metllc</Paragraph>
    <Paragraph position="2"> where * \[~d,~l is the number of common concepts be- null tween the tnelarch,es of v~ attd nj * w~ are the levels of the nouus m the lueiaich~ of verb v, * descendentsj *s the total number of uotd~ w,thm the hmra, chy of noun nj 4 C u tanks each pa,r v, - nj, fol all ~ and j Van null ants of th,s method work for other parts of speech pairs such as noun-noun, noun-verb, verb-verb, verb-noun, adje.cUve-noun and verb-adverb Th,s ,s a powerful method that v, orks surprisingly x~ell even for free text We ha~e tested the method on SemCor, the pint of the Brown coipus tagged x~ltlt WotdNet seltses \V,th tlns technique it is possible to ,ank the senses and \[o keep not only the h~st lanked sense, but the second ol th,td ~anked senses  especmlly when the tankmg is sufficiently close and there ~s another wa~ to check the vahd,ty of the d~samb~guaUon null Method 3 Statistics on large corpora As a last resort, we can use a staustmal approach to d,samblguate those words that can not be done with any of the methods described so fal Consider a collocating word-word pmr wl - w2 m whmh we conslde, that Wl has been dtsambtguated already The dlsambtguatmn of w2 proceeds as follows  (1) Foi each sense w~, form a slmdanty hst with w) and all other words that may be m that synset {w.~, w', (1) &amp;quot; ,(2)~ ' _ , w 2 ) } (2) Form pans of wz and all the %xords m each ~Izmlarzty hst foI all z (3) Search a lalge empus for the occurrences o\[ any of the pans m the hst above ,.</Paragraph>
    <Paragraph position="3"> , KI). . K2)~,, { wtw~&amp;quot; OR ~1~ OR wzw 2 ) }  We have searched the Internet using the AltaV~sta search engine The number of hits for each similarity hst measmes the ,elatedness of w~ wtth each sense w~ and thus provtdes a ranking of the senses  The followmg procedure was used to dlsamb~guate 12,762 words from 1000 randomly selected glosses Step 1 Identify and separate the monosemous words - that have only one sense m WordNet (m out experiment 6468 words were found) Step 2 Apply Method 1 - HeurlsUcs - to the reroaming 6294 polysemous words Method 1 provides correct d~samblguatmn for 5475 words, thus an accmac~ of 87% Out of the remammg 13% of the words, 3% were dlsamb~guated erroneously and 10% could not be done with the heuristics used The correct sense for each word was determined manually by a team of three students We ha~e found a fe~ s) n~ets such as {commemorate, remember} that have no hnks to an~ other synsets, m no h3 pern3 ms and no hypom}ms Step 3 Apply Method 2 - Conceptual Denszty - to the 6294 polysemous words, staitmg hesh Step 4 Apply Method 3 - StaUstlcs - to the 6294 words using AltaY=~sta on the Internet Step 5 The results obtained wtth Method 1 and Method 2 are combined, that is, take all the wo, ds that were d~sambzguated, and m the case of conflict g~ve prmnty to Method 1 Step 6 The results from Step 5 are combmed wtth the results g~ven by Method 3 and m the case of conflmt gtve priority to results obtained m Step 5 Table 1 indicates the accuracy obtamed at each step An overall accmacy of 94% x~as achmved Out goal ,s to improve the techmque to be able to dlsamb~guate all words automatmally These results must be seen agamst the background average rate of 59 39% correct sense asstgnment achmved when the first WordNet sense is assigned to each polysemous word This is considered the basehne performance level for word-sense dlsamblguat,on programs (Gale et al 1992) and is consistent ~uth out  the d,scnmmatlon of any conceptual defimtlons into a genus and the dzfferentza Our LFTs Implement the same dlstlncUon by always plaong the genus predicate on the first position of the LFT, and the rest of the LFT viewed as the definition differentia (2) A predmate is generated for every noun, verb, adjective or adverb encountered In any gloss The name of the predicate is a concatenatmn of the morpheme's base form, the pat t-of-speech and the Word-Net semanuc sense, thus capturing the full lemcal and semantm disamblguaUon For example, the LFT of the gloss of {student, pupzl, educatee} contains the predmates learner n#l, enroll v#l and  educabonaIJnstJtutlon n#l (3) In the sprat of the Davidsoman tzeatment oi  the acUon predicates, all verb predmates (as ~ell as the nommahzaUons zeptesentmg acuons, e~ents or states) haxe thlee arguments actlon/state/eventpredlcate(e,,~\[,x~), where  In the case when the subject or the object are present m the gloss, they share the correspondmg arguments wtth the actmn/state/event predmate For example, the LFT of (a person who backs a polltlclan) the gloss of {supporter, protagonlst, champion, admlrer, booster, friend} zs  (4) The role of complements wmthm a phrase ~s  rephcated m the LFTs Predicates generated from modffiers share the same arguments w~th the predicates corresponding to the phrase heads Adjective p~ed~cates share the same argument as the predicate corresponding to the noun they modify An exemphficatlon ~s the LFT of the gloss of {art~fact, artefact}, whmh maps (a man-made object) into</Paragraph>
    <Paragraph position="5"> the argument of adverbml predmate ~s the argument marking the eventuahty of the event/state/actmn they modify For example, the gloss of the verb synset {hare} is (run quickly), producing the</Paragraph>
    <Paragraph position="7"> (5) Conflunctmns a~e transformed m predicates,  whmh enable the aggregatmn of several predicates under the same syntactic role (e g subject, object or preposmonal object) By conventmn, conjunctionpredmates have a variable number of arguments, since they cover a varmble number of predicates The first argument represents the &amp;quot;result&amp;quot; of the logmal operation induced by the conjunctmn (e g a logical and m the case of the and conjunctmn, or a loggcal or m the case of the or con\]unctmn) The rest of the a~guments mdmate the predicates covered by the conjunctmn, as they are a~guments of those predmates as well (6) We also generate p~edmates for every preposition encountered ,n the gloss The prepos~tmn predicates always have two arguments the first argument corresponding to the predicate of the head of the phrase to which prepos~tmnal phlase ~s attached, whereas the second argument corresponds to the prepos~tmnal object Sources of mformatmn. The ~mplementatlon of LFTs rehes on mformatmn provided b3  (a) Lexmal and semantm d~samb~guatmn p~oduced m the p~eprocessmg and semantm d~samb~guatmn phases Th,s mformatmn contributes to the creatmn of predicate names (b) Phrasal parsing, enabl,ng the recogmtmn of basic and complex phrases Th~s determines all complements to share the same predmate argument w~th the phrase head (c) Syntactm t~ansformatmn rules, d~scnmmatmg the syntactm subject and object of every verb (m nommahzatmn) based on the local syntactic context (d) Preposlt,onal attachment resolutmn, indicating  the arguments of the prepos~tmn p~ed~cates Table 2 lllustiates the tlansfolmatlons fo~ the gloss of {tennis, lawn tennis}</Paragraph>
  </Section>
  <Section position="11" start_page="3" end_page="3" type="metho">
    <SectionTitle>
5 Semantic form transformation
</SectionTitle>
    <Paragraph position="0"> Many NLP problems lely on the recogmuon of the tyDcal lexmo-semantm I elatlonshlps between hngulstm concepts The LFT codfficatlon meiely acknowledges the foUowmg syntax-based relatlonsh~ps</Paragraph>
    <Paragraph position="2"> prepositional attachments (4) complex nominals and (5) adjecuval/adverblal adjuncts Semanuc mterpretat,ons of utterances, as ~ell as d~scou~e p~ocessmg require knowledge about the semantic or themat~c relatmnsh~ps between concepts The ~emant~c form trans.formatwns prov,de with constraint-based mappings of the syntax-based relatmns covered m the LFTs into binary thematic relatmns or semantLc relations (We dlstmgmsh between thematic ~elatmns such as agent, expenencer, etc, and semantic relatmns such as a-kind-of, part-of, etc )  LFTs by the predmatlve formula subjeCt(xl )&amp;:verb(e, ~ l, ~.~) can be mapped into a x a-Ilet:y of thematic relations The defimtlon of the thematm relations is enurely based on mfo~matmn internal to the WordNet database, explessed as constraints Fol example, all the subjects of verbs that are hyponyms of the verb cause or have thts concept as the genus of then glosses are defined to represent the Iole of agents (2) The syntactzc obTect ~elatmns a~e tecogmzed m the LFTs b) the predmauve founula verb(em,xi,x2) &amp; aoua(~2) The defimtmn of tim thematic relatmns m whmh syntactm objects can be mapped is expressed m terms of verb synsets The constraining verb synsets ~epresent the upper-most hypernyms of all verbs that (z) have syntactic objects m the WordNet glosses and (~z) belong to the same hmrarchy or a~e defined by gloss gem from the same h~el arch:y (3) The preposztzonal predzcates ale tlansfolmed into thematm ol semantm relations When a IVo~d- null wxth rackets by two or four players who h~t a ball back and forth over a net that d~v~des a tennis court) Net semantm relauon holds between the arguments of a pteposmonal p~edmate, that specffic ~elatmn becomes the semantic transformauon of the predicate Fol example, the PP attachment \[sacrament of penance\] derived from the gloss of {confession} indicates a semantic kind-o\[ relauon due to the fact that m WordNet penance is a hyponym of sacrament (4) The transformation of complex nominal predzcates into thematic or semanUc constraints m done by first seeking a WordNet relatmn (or a combma-Uon of such relatmns) between the components of the predicate If such a (chain of) relation(s) m found, predicate nn is transformed into the dominant WordNet semantic relation Otherwise, the no predicate is transformed into a thematic relation (5) The Uansformatlon of ad3ectwal and adverbzal adjuncts, lepresented m the LFTs as p~edmates sharing the same argument with the concepts they modify shall be connected to their modifiers through attribute lelauons</Paragraph>
  </Section>
class="xml-element"></Paper>