<?xml version="1.0" standalone="yes"?>
<Paper uid="P85-1002">
  <Title>TEMPORAL I\]~'RRI~C~S IN HEDICAL TEXTS</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
l.O INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> This paper describes the development of a NiPS for analyzing domain-specific as well as temporal information in a well-defined text type. The analysis, i.e. output, of the NLPS is a data structure which serves as the input to an expert system. The ultimate Real is to allow the user of the expert system to enter data into the system by means of NL text which follows the linguistic conventions of English.</Paragraph>
    <Paragraph position="1"> The particular domain chosen to illustrate the underlying theory of such a system ts that of medical descriptive rexis which deal with patients' case histories of Liver diseases.</Paragraph>
    <Paragraph position="2"> The texts are taken unedtted from the Jourmal of the Amerzcan Medical As~ocPSation. The information contained in those texts serves as input to PATREC, an intelligent database assistant for MDX, the medical expert system \[Chandrasekaran 831. The objectives of this research are twofold, whereby the sy~;tem described above is meant to be a particular implementation of a genera\[ NLP which could be used for a variety of domains.</Paragraph>
    <Paragraph position="3"> The first objective is to provide a theory for processing temporal information contained in a given text. The second objective is to argue for a knowledge-based approach to NL processing in which the parsing procedure is driven by extra Linguistic knowledge.</Paragraph>
    <Paragraph position="4"> My NLPS, called GROK, \[Gran~nattcal Representation of Obiective Knowledge\] is a functioning program which is implemented in EL\[SP and EFRL on a DEC20/60. The full documentation, including source code is available IObermeier 8A\]. The program performs the following tasks: (L) parse a text from a medical iournaL while using Linguistic and extra Linguistic knowledge; (2) map the parsed Linguistic structure into an event-representation; (3) draw temporal and factual inferences within the domain of Liver diseases; (4) create and update a database containing the pertinent information about a patient.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="10" type="metho">
    <SectionTitle>
2.0 OVERVI RW
2. l A SampLe Text:
</SectionTitle>
    <Paragraph position="0"> The user of my NLPS can enter a text of the format given in FiRure L L The texts which the NLPS accepts are descriptive for a particular domain. The information-processing task consists of the analysis of Linguistic information into datastructures which are chronologically ordered by the NLPS.</Paragraph>
    <Paragraph position="1"> L This 80-year-old Cau=aslan female complained of nau.s~, vomlclnL abciommal  swelhnl~ and jaundice.</Paragraph>
    <Paragraph position="2"> ~. She h~\[ dlal~ melhtus, credlL~'l wllh iosuiln for slx years ~fora aclm,~on. 3. She ~ad ~lacl fll-~efmes~ p.sl~romcmuna\[ complamu for many ye..lrs ancl occaalonai em~me.s of nau.s~ ancl vomum$ chr~ years ~'evlousiy -~ Four w~ics ~forc aclmlsslon snc dcveloo~l ptm across the u~&amp;quot; aO~lomen. radmunll to the rlanlcs.</Paragraph>
    <Paragraph position="3"> 5. She also compiamed of shoal.in E ~ecordlai ~ma anti ~im~{ion wlm shl~lt ,-'xer t|o~l d~ s~n~.</Paragraph>
    <Paragraph position="4">  F~.~ure I.: SampLe Text Eor Case So. 17~.556 lThe numbering on the sentences is only for ease of references in the following discussion and does not appear in the actual text,  The first module of the program analyzes each word by accessing a \[exical component which assigns syntactic, semantic, and conceptual features to it. The second module consists of a bottom-up parser which matches the output from the lexical component to a set of augmented phrase structure rules 2. The third module consists of a knowledge base which contains the domain-specific information as well as temporal knowledge. The knowledge base is accessed during the processing of the text in conjunction with the augmented phrase structure rules.</Paragraph>
    <Paragraph position="5"> The output of the program includes a lexical feature assignment as given in Figure 2, a phrase-structure representation as given in Figure 3, and a knowledge representation as provided in Figure 4. The resulting knowledge representation of mv NLPS consists of a series of events which are extracted from the text and chronologically ordered by the NLPS based on the stored knowledge the system has about the domain and ~enera \[ temporal re\[at ions. The final knowledge representation (see Figure 5) which my NLPS ~enerates is the input to the expert system or its database specialist.</Paragraph>
    <Paragraph position="6"> The final output o\[ the expert system is a diagnosis of the patient.</Paragraph>
    <Section position="1" start_page="9" end_page="10" type="sub_section">
      <SectionTitle>
2.2 Scenario
</SectionTitle>
      <Paragraph position="0"> The comprehension of a descriptive text requires various types of knowledge: linguistic knowledge for analyzing the structure of words and sentences; &amp;quot;world knowledge&amp;quot; for relating the text to our experience; and, in the case ,)f tech:~ica\[ texts, expert knowledge for dealing with information ~eared toward the domain expert.</Paragraph>
      <Paragraph position="1"> =or the purpose o\[ mv r(.search, \[ contend that the comprehension of technical, descriptive te&gt;:t is ~implv a conversion of information from one representation i~to another based on the knowledge oF the NLI'E.</Paragraph>
      <Paragraph position="3"> * %'~. the ~-suffix ms ~parated: the trigger on compl~m chan~d the following of from a prep~it\]ou \[o a panicle:  contain know\[edze about morphology, syntax, and the particular domain in which the NLPS is operatzng. These rules are used for interpreting the text, Ln particular, embiguities, as well as for generating the final output ~f the NLFS.</Paragraph>
      <Paragraph position="4">  If a doctor were given a patient's case history (see Figure l), he would read the text and try to extract the salient pieces of information which are necessary for his diagnosis. In this particular text type, he would be interested in the sign, symptoms, and laboratory data, as well as the medical history of the patient. The crucial point hereby is the temporal information associated with the occurrences of these data. In general, he would try to cluster certain abnormal manifestations to form hypotheses which would result in a coherent diagnosis. The clustering would be based on the temporal succession of the information in the text. Each manifestation of abnormalities \[ will refer to as an &amp;quot;event&amp;quot;. Each event is defined and related to other events by means of temporal information explicitly or implicitly provided in the text. An important notion which \[ use in my program is chat of a key event 4. &amp;quot;Events are or~anize~ around key events (which are domain-specific in the medical domain, some of the important ones are 'admission', 'surgery', 'accident', etc.), so that ocher events are typically stated or ordered with respect to these key events&amp;quot; \[Micra\[ 82\].</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="10" end_page="12" type="metho">
    <SectionTitle>
3.0 KNi~IrLF.DCE-BASED PARSING
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="10" end_page="11" type="sub_section">
      <SectionTitle>
3.1 Selection and OwganizaCion for the Knowledge
Base
</SectionTitle>
      <Paragraph position="0"> \[ have characterized the task of a doctor reading a patient's case history as finding key domain concepts (e.g., sign, symptom, laboratory data), relating them to temporal indicators (e.g, seven veers a~o), and ordering the events resulting from assignin R temporal indicators co key concepts with respect to a &amp;quot;key event&amp;quot; (e.g., at admission, at surgery). (\[) This 80-year-old Caucasian female complained of nausea, vomiting, abdominal swe\[\[in~ ~nd iaundice.</Paragraph>
      <Paragraph position="1"> In the sample text in Figure l, the first sentence, given in (l) requires the following domain concepts: Patient: person identified by age, sex, and profession, whose signs, symptoms, and laboratory data will be given.</Paragraph>
      <Paragraph position="2"> Symptoms: manifestations of abnormalities repor\[ed by the patient. Certain symptoms have to be further defined: swellin~ needs a characterization as to where it occurs. Pain can be characterized by its location, intensity. and nature (e.g., &amp;quot;shooting&amp;quot;).</Paragraph>
      <Paragraph position="3"> Signs: abnormalities found by the physician such as fever, jaundice, or swelling.</Paragraph>
      <Paragraph position="4"> 4The notion of &amp;quot;key event&amp;quot; is further discussed in 4.3 &amp;quot;Key Events&amp;quot;.</Paragraph>
      <Paragraph position="5"> Whether &amp;quot;fever&amp;quot; is a sign or a symptom is indicated by the verb. Therefore, the verbs have features which indicate if the following is a sign or a symptom. There are no explicit temporal indicators in (1), except the tense marker on the verb. The doctor, however, knows chat case histories ordinarily use &amp;quot;admission&amp;quot; as a reference point.</Paragraph>
      <Paragraph position="7"> (2) She had diabetes mellitus, treated with insulin for six veers before admission.</Paragraph>
      <Paragraph position="8"> The sentence in (2) requires a temporal concept &amp;quot;year&amp;quot; in conjunction with the numerical value &amp;quot;six&amp;quot;, it also requires the concept &amp;quot;duration&amp;quot; to represent the meaning of for. The &amp;quot;key event&amp;quot; at admission is mentioned explicitly and must be recognized as a concept by the system.</Paragraph>
      <Paragraph position="9"> After selecting the facts on the basis of about 35 case descriptions as well as previous research of the medical sublanguage \[Hirschman 83\] 5 , \[ organized them into schemas based on what is known&amp;quot; about the particular text type. \[n \]Bonnet 79\], a medical summary is characterized as &amp;quot;a sequence of episodes that correspond Co phrases, sentences, or groups of sentences dealing with a single topic. These constitute the model and are represented bv schemas&amp;quot; \[Bonnet 79, 80\]. Schemas for the medical domain in Bonnet's system are $PATIENTiNFORMATION (e.g., sex, job), SSICNS (e.g., \[ever, jaundice). \[n GROK, l use the schemas SREPORT-SICN, SREPORT-SYMPTOM, SREPORT-LAB-DATA, SPATIENT-\[NFO. Each of my schemas indicates &amp;quot;who reports, what co whom, and when&amp;quot;. The $REPORT-SYMPTOM schema has the following elements: verb(unknown), subject(patient), object(symptom), indirect object(medic), time(default is admission).</Paragraph>
      <Paragraph position="10"> After selecting the facts on the basis of the domain, and organizing them on the basis of the text-type, \[ add one fact for putting the information into the target representation.</Paragraph>
      <Paragraph position="11"> The target representation consists of a temporal indicator attached to a domain-specific fact what \[ had referred to in as &amp;quot;event&amp;quot;. The event structure contains the following elements: name of domain-specific concept, reference point, duration (known or unknown), and relation to reference point (e.g., before, after).</Paragraph>
      <Paragraph position="12"> 51 use ten types of domain-specific facts: sign, symptom, lab data, body-part, etc., I use six temporal facts: month, year, day, week, duration, period, i.e., &amp;quot;for how long&amp;quot;.</Paragraph>
    </Section>
    <Section position="2" start_page="11" end_page="12" type="sub_section">
      <SectionTitle>
3.2 The Flow of Control
</SectionTitle>
      <Paragraph position="0"> In addition to domain-specific knowledge, a person reading a text also uses his linguistic knowledge of the English grammar. The problem for a NLPS is how to integrate linguistic and extra linguistic knowledge. The dominant paradigm in computational linguistics uses syntactic and morphological information before considering extra linguistic knowledge; if extra linguistic knowledge is used at all.</Paragraph>
      <Paragraph position="1"> Considering syntactic knowledge before any other type of knowledge has the following problems which are avoided if enough contextual information can be detected by the knowledge base of the NIPS:</Paragraph>
      <Paragraph position="3"> bank) and structural ambiguities cause multiple parses (e.g. , \[ saw the man on the hill with the telescope).</Paragraph>
      <Paragraph position="4"> Moreover, psycholinguistic experiments have shown \[Marslen-Wilson 75, Marslen-Wilson 78, Marsten-Wilson 801 that the syntactic .,nalvsis of a sentence does not precede higher level processing bu~ interacts with seman=ic and pragmatic information. These findings are, to some extent, controversial, and not accepted by all psvcholinRuists.</Paragraph>
      <Paragraph position="5"> In my system, knowledge about the domain, the text-type, and the tarRet representation is used before and together with syntactic information. The syntactic information helps to select the interpretation of the sentence. Syntax functions as a filter for processing information. \[t selects the constituents of a sentence, and groups them into larger &amp;quot;chunks&amp;quot;, called phrases. The phrase types noun phrases \[NP\] and verb phrase \[VPI contain procedures to form concepts (e.g., &amp;quot;abdominal pain&amp;quot;). These concepts are combined by function specialists. Function specialists consists of procedures attached to function words (e.~., prepositions, determiners), fnflectional morphemes, and boundary markers (e.g., comma, period).</Paragraph>
      <Paragraph position="6"> Technically, \[ distinguish between phrase ~pecialists and function specialists. The phrase ~pecialists interact with extra\[tnguistic knowledge to determine which concepts are eypressed in a text, the function specialists de~ermine locally what relation these concepts have to each other. So in general, the phrase specialists are activated before the function specialists.</Paragraph>
      <Paragraph position="7"> To illustrate this process, consider the sentence: (3) The patient complained of shoottn~ pain across the flanks for three days before admission.</Paragraph>
      <Paragraph position="8"> The NP-specialist combines the and patient into a phrase. The central processing component in the sentence ls the VP-specialist. Its task is to find the verb-particle construction (complain of), and the object (e.g., shootin~ pain). The VP-specialist also looks at the syntactic and semantic characteristics of complain o__f_f. It notes that complain of expects a symptom in its object position. The expectation of a symptom invokes the schema &amp;quot;report-symptom&amp;quot;. At this point, the schema could fill in missing information, e.~., if no subject had been mentioned, it could indicate that the patient is the subject. The schema identifies the current topic of the sentence, vlz., &amp;quot;symptom&amp;quot;.</Paragraph>
      <Paragraph position="9"> CROK next encounters the word shootin~.</Paragraph>
      <Paragraph position="10"> This word has no further specification besides that of bein~ used as an adjective. The head noun pain points to a more complex entity &amp;quot;pain&amp;quot; which expects further specifications (e.~., location, type). It first tries to find any further specifications within the :malvzed part of the NP. \[t finds shootin~ and adds this characteristic to the entity &amp;quot;pain&amp;quot;. Since &amp;quot;pain&amp;quot; is usually specified in terms of its location, a place adverbial is expected. Upon the eqtry of across, the entity &amp;quot;pain&amp;quot; includes &amp;quot;acro~s&amp;quot; as a local ion marker, expect in~ as the next word a body-part. The next word, flank is a body-part, and the &amp;quot;pain&amp;quot; entity is completed. Note here, that the attachment of the preposition was ~uided by the information contained in the knowledge base.</Paragraph>
      <Paragraph position="11"> The next word for is a function word which can indicate duration. To determine which adverbial for Lntroduces, the system has to wait for the information from the following Nl'-specialist. After the numeric value &amp;quot;three&amp;quot;, the temporal indicator &amp;quot;dav&amp;quot; identifies for as a duration marker.</Paragraph>
      <Paragraph position="12"> Explicit ~emporal indicators such as day, week, or month, under certain conditions introduce new events. As soon as GROK verifies that a temporal indicator started an event, it fills in the information from the &amp;quot;report:&lt;xx&amp;quot; ,~chema. The new event representation includes the sign, symptom, or laboratory data, and the temporal indicator. The last two words in the sample sentence before admPSssion, provide Khe missing information as to what &amp;quot;key event&amp;quot; the ~ewly created event \[s related to. Once a new event frame or domain-specific frame is instnntiated) GROK can use the information associated with each event frame (e.g.) duration, key-event), together with the information from the domain-specific frame (e.g., the pain frame contains slots for specifying the location, intensity, and type of pain) to interpret the text.</Paragraph>
    </Section>
  </Section>
  <Section position="7" start_page="12" end_page="14" type="metho">
    <SectionTitle>
4.0 TEMPORAL \[NFO\[~ATION PROCESSINC
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="12" end_page="12" type="sub_section">
      <SectionTitle>
4.1 Problems
</SectionTitle>
      <Paragraph position="0"> The inherent problems of text comprehension from an information processing viewpoint are how to deal with the foremost problems in computational NLP (e.g., ambiguity, anaphora, ellipsis, conjunction), including the foremost problems in temporal information processing (e.g., implicit time reference, imprecision of reference).</Paragraph>
      <Paragraph position="1"> Within A\[ and computational linguistics, only a few theories have been proposed for the processing of temporal information \[Kahn 77, Hirschman 8\[, Kamp 7g, Allen 83l. in particular, a theory of how a NLP can comprehend temporal relations in a written text is still missing. \[n my research, \[ present a theory for processing temporal information in a NLPS for a well-defined class of technical descriptive texts. The texts deal with a specific domain and tasks which require the processing of linguistic information into a chronological order of events. The problems for processing the temporal information contained in the text include: * a NLPS has to work with implicit temporal information.</Paragraph>
      <Paragraph position="2"> ALthough in (I), no explicit temporal reference is present, the NLPS has to detect the implied information from the context and the extra Linguistic knowledge available.</Paragraph>
      <Paragraph position="3"> * a NLPS has to work with fuzzy information. The reference tO for many years in (}) is fuzzy, and yet a NiPS has to relate it to the chronology of the case.</Paragraph>
      <Paragraph position="4"> * a NLPS has to order the events in their chronology although they are not temporally ordered in the text.</Paragraph>
    </Section>
    <Section position="2" start_page="12" end_page="12" type="sub_section">
      <SectionTitle>
4.2 Solutions
</SectionTitle>
      <Paragraph position="0"> Hv solution to the problems discussed in the previous section lies within the computational paradigm as opposed co the Chomskyan generative paradi~m. The comFutationaL paradigm focuses nn how the comprehension processes are organized whereas within the generative paradiRm, linguistic performance is of less importance for a Linguistic theory than Linguistic competence. Within the computational paradigm, the representation and use of extra-Linguistic knowledge is a maior part of studying Linguistic phenomena, whereas generative linguists separate linguistic phenomena which fall within the realm of syntax from other cognitive aspects \[W~nograd 83, 21\].</Paragraph>
      <Paragraph position="1"> Functionality is the central theoretical concept upon which the design of GROK rests.</Paragraph>
      <Paragraph position="2"> What is important for comprehending language is the function of an utterance in a given situation. Words are used for their meaning, and the meaning depends on the use in a given context. The meaning of a word is subject to change according to the context, which is based on the function of the words that make up the text. Therefore, my approach to building a NLPS focuses on modeling the context of a text in a particular domain. \[ am primarily concerned with the relationship between writertext-reader, rather than with the relationship between two sentences. The use of the context for parsing requLres a knowledge representation of the domain, and the type of text, in addition to linguistic and empirical knowledge.</Paragraph>
      <Paragraph position="3"> In contradistinction to NLPSs which use syntactic information first \[Thompson 8\[\], and which possibly generate unnecessary structural descriptions, mv system uses higher \[eve\[ information (e.~., domain, text-type) before and together with usuaLLv a smaller amount o\[ syntactic information, in GROK, the syntactic information selects between contextually interpretations o\[ the text ~untax acts as ~ ill=or for the N\[.IJS.</Paragraph>
      <Paragraph position="4"> in contradistinction to NLPSs which use conceptual information first \[Schank 75\], GROK, partially due to the limited information processinC/ task and the particular domain, starts out with a small knowledge base and builds up datastructures which are used subsequently in the processing of the text. The knowledge base of my system contains only the information it absolutely needs, whereas Schankian scripts have problems with when to activate scripts and when to exit them.</Paragraph>
    </Section>
    <Section position="3" start_page="12" end_page="13" type="sub_section">
      <SectionTitle>
4.3 Key Events
</SectionTitle>
      <Paragraph position="0"> Temporal information in a text is conveyed by explicit temporal indicators, implicit temporal relations based on what one knows about written texts (e.g., &amp;quot;time moves forward&amp;quot;), and &amp;quot;key events&amp;quot;. \[ define a key event as a domain-specific concept which is used ro order and group events around a particular key event. \[n my theorv, temporal processing is based on the identification of key events far a parti=uLar domain, and their subsequent reco~uition bv the NLPS in the text.</Paragraph>
      <Paragraph position="1"> Temporal indicators . in a sentence are not of equal importance. The tense markinPS on the verb has been the Least influential {'or filling in the event structure. For the program, the most important sources are adverbials.</Paragraph>
      <Paragraph position="2"> The linear sequence of sentences also contributes co the seE-up of the configurations of events. My program makes use of two generally known heuristics; time moves forward in a narrative if not explicitly stated otherwise;</Paragraph>
      <Paragraph position="4"> the temporal reference of the subordinate clause is ordinarily the same as that in the main clause.</Paragraph>
      <Paragraph position="5"> &amp;quot;Key events&amp;quot; are significant since they are used to relate events to one another. \[n my theory of text processing, key events build up the temporal structure of a text. \[f key events for other domains can be identified, they could be used to explain how a NLPS can &amp;quot;comprehend&amp;quot; the texts of the domain in question. The representation of temporal information is significant \[n my theory. \[ define an event as the result of the assignment of a temporal value to a domain-specific concept. The structure of an event is Reneralizable to other domains. An event consists of a domain-specific concept, a key event, a relation to ke~ event, and a duration. \[n the medical domain, the instantiated event contains information about how long, and when a symptom or sign occurred, and what the kev event of the instantiated event was.</Paragraph>
      <Paragraph position="6"> ,\part from the temporal issue, my research has shown that \[f the domain and the task of the NLPS are sufficiently constrained, the use of frames as a knowledge representation ~cheme is efficient in implementing CROK. in ,nv program, \[ flare used individual frames to represent single concepts (e.g., pain). These concepts help the NLPS to access the domain-specific knowledge base. ToPSether with the temporal indicators, the information from tne knowledge base is then transferred to the topmost event frame. Procedures are then used to relate various event frames to each other.</Paragraph>
      <Paragraph position="7"> The restrictions and checks on the instantiation of the individual frames preclude an erroneotls activation of a frame.</Paragraph>
      <Paragraph position="8"> The viability of this approach shows that the idea of stereotypical representdL\[on of information is useful for NLPS \[f properly constrained. Mv program checks for the accessability of the various levels of the knowledge representation whenever new information is coming in. This multilaver approach constrains the ~nstantiatton of the event frame sufficiently in order to prevent erroneous event tnstantiation.</Paragraph>
    </Section>
    <Section position="4" start_page="13" end_page="14" type="sub_section">
      <SectionTitle>
4.4 Comparison to Extant Theories on Temporal
ProcessinR
</SectionTitle>
      <Paragraph position="0"> The overall ideas of GROK .is they re\[are ~,r differ from ~he extant theories and svstems are introduced by looking at four major issues concerning temporal proces:~ing.</Paragraph>
      <Paragraph position="1"> * temporaiiry: how is an event defined in the system; ho~ is temporal information treated vis-a-. !.; =he whole system? What search algorithms or inference procedures are provided? null * organization: are events organized on a time line, by key events, calendar dates, before/after chains? * problems: how is imprecision, fuzziness, and incompleteness of data handled? * testing: how can the system be tested; by queries, proofs, etc.? Does it have a consistency checker? In GROK, \[ use an interval-based approach to temporal information processing. An event is defined as an entity of finite duration. As in IKamp 79, 3771, event structures are transformed into instants by the Russell-Wiener construction.</Paragraph>
      <Paragraph position="2"> \[n GROK, the NLPS processes temporal (nformat\[on by first associating a concept with a temporal reference, then evaluating the extension of this event. The evaluation considers syntactic (e.~., adverbials) and pragmatic information (current time focus). Each event is represented in the knowledge base with information about when, for how long, and what occurred.</Paragraph>
      <Paragraph position="3"> The parser while analyzing the sentences, orders these events according to a &amp;quot;key event&amp;quot;. The single events contain information about the temporal indicator which is attached to a domain-soec~fic fact. The single events are connected to the respective &amp;quot;key event&amp;quot;. &amp;quot;Key events&amp;quot; are domain-specific. \[n general, \[ qcipulate that everv domain has a limited number of such &amp;quot;key events&amp;quot; which provide the &amp;quot;hooks&amp;quot; for the temporal structure of a domain-speci fic text.</Paragraph>
      <Paragraph position="4"> CROK also differs from logical theories \[n that it deals with discourse structures and their conceptual representations, not with :solated sentences and their truth value. \[t is different from Kahn's rime specialist {Kahn 771 in that it uses domain knowledge and &amp;quot;knows&amp;quot; about temporal relations of a particular domain. Moreover, Kahn's program only accepts LiSP-like input and handled only explicit temporal information. The use of domain-specific temporal knowledKe also qet=; CROK apart from Allen's l,\\[len 83\] temporal inference engine approach. GROK differs from Kamp's discourse structures in that it uses the notion of reference intervals that are based on conventiGnal temporal units (e.g., day, week, month, year) to organize single events into chronological order.</Paragraph>
      <Paragraph position="5"> GROK is in many respects similar to research reported in \[Hirschman \[98l\]: both systems deal with temporal relations in the medical domain; both syatems deal with implicit and explicit temporal information. GROK differs  from Hirschman's system in that GROK uses domain-specific and other extra linguistic information for analyzing the text, whereas Hirschman relies primarily on available syntactic information. Therefore, Hirschman's system as presented in \[Hirschman 81\] can neither handle anaphoric references to continuous states nor represent imprecision in time specification.</Paragraph>
    </Section>
    <Section position="5" start_page="14" end_page="14" type="sub_section">
      <SectionTitle>
4.5 State of \[=q~tememtatiou
</SectionTitle>
      <Paragraph position="0"> GROK is a highly exploratory program.</Paragraph>
      <Paragraph position="1"> The limitations of the current implementation are in three areas: * The parser itself does not provide the capability of a chart parser since it will not give different interpretations of a structurally ambiguous sentences. This type of structural ambiguity, where one constituent can belong to two or more different constructions, would not be detected.</Paragraph>
      <Paragraph position="2"> * The knowledge base does not have a fully implemented frame structure. Each ~eneric frame has a certain number of slots that define the concept. A generic concept (e.g., sign) must have slots which contain possible attributes of the specific frame (e.g., where is the sign found; how severe is its manifestation). These slots have not yet been implemented. The number of frames is strictly i/mired to the temporal frames and a few exemplary ~eneric frames necessary to process the text. * The range of phenomena is limited. Only &amp;quot;before-admission&amp;quot; references are recognized by the system. Furthermore, slots that prevent the inheritance of events of limited durations are not yet in place.</Paragraph>
      <Paragraph position="3"> in general, GROK is still in a developmental stage at which a number of phenomena have vet to be accounted for =hrough an implementation.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>