<?xml version="1.0" standalone="yes"?>
<Paper uid="M91-1027">
  <Title>FORCED THE INDIVIDUALS, VHO 'ERE TAKEN TO AN UNKNOWN LOCATION, OUT OF</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
MCDONNELL DOUGLAS ELECTRONIC SYSTEMS COMPANY :
</SectionTitle>
    <Paragraph position="0"> Description of the INLET System Used for MUC- 3 David de Hilster and Amnon Meyers  During the past nine months, our language processing effort has focused on implementin g a new NLP system called INLET. INLET relies heavily on the methodology developed for th e preceding VOX system . The goal of this work is to produce an NLP shell that can be customized to a variety of tasks and domains .</Paragraph>
    <Paragraph position="1"> INLET provides user-friendly graphics-oriented tools for knowledge addition an d perusal, to support customization to a variety of domains and tasks . INLET is implemented in C on Sun SPARCstations, in order to support faster analysis than Lisp-based systems and t o provide a more widely usable end-product .</Paragraph>
    <Paragraph position="2"> At the present time, the basic knowledge addition system is in place, includin g vocabulary addition interfaces (e .g ., Figure 1), a dictionary book tool (Figure 2), a hierarch y editor (Figure 3), and a grammar rule editor (Figure 4) . A new Conceptual Grammar has been implemented for INLET, supporting concept hierarchies, a 'conceptual' dictionary, and othe r knowledge types (such as lexical interrelationships) .</Paragraph>
    <Paragraph position="3"> A conceptual analyzer, called the skimmer (Figure 5), has been implemented to provid e robust top-down language analysis capabilities. The skimmer will augment a bottom-u p analyzer currently under construction . A skimmer trace is shown in Figure 6 .</Paragraph>
  </Section>
  <Section position="2" start_page="0" end_page="178" type="metho">
    <SectionTitle>
DESCRIPTION OF THE SKIMME R
</SectionTitle>
    <Paragraph position="0"> The skimmer, implemented in 2 months time, is the only operational component of the INLET analyzer (called LASS, for Language Analysis Support System) . Six major processes comprise the skimmer, and are described in turn . The first process performs a pass throug h the input message to replace all fixed phrases with their atomic representation . Fo r example, the literal phrase &amp;quot;farabundo marti national liberation front&amp;quot; is replaced by a concep t that represents that phrase . The second process, called the pre-processor, locates and parse s specialized constructs in the text, such as proper names, number words, temporal and locative phrases, as well as some domain-specific phrases dealing with perpetrators, physical, and human targets . Phrases like &amp;quot;thirty-three&amp;quot;, &amp;quot;Ricardo Alfonso Castellar&amp;quot;, &amp;quot;three months ago&amp;quot; , &amp;quot;San Miguel department&amp;quot;, and &amp;quot;member of the FMLN&amp;quot;, are all detected and parsed by the pre processor. Next, a pass through the text detects key words and phrases . Words like &amp;quot;attack&amp;quot;, &amp;quot;murder&amp;quot;, and &amp;quot;bomb&amp;quot;, as well as phrases like &amp;quot;set fire to object&amp;quot;, &amp;quot;bomb damage d object&amp;quot; are located in the text . Incidents found in this pass are merged or segmented by th e grouping process. Groups of sentences associated with a single incident are then examined by the actor/object separation process to determine perpetrators and targets . The subsequent  slot filling process further examines groups of sentences to fill remaining slots of the MUC 3 template. In order to assure self-consistency in a single template, a semantic trimming and rejection process trims the templates prior to output . This last process is ad hoc, bu t substitutes for our current lack of script-based processing .</Paragraph>
  </Section>
  <Section position="3" start_page="178" end_page="179" type="metho">
    <SectionTitle>
3. TYPE OF INCIDENT
MURDER
4. CATEGORY OF INCIDENT
TERRORIST ACT
</SectionTitle>
    <Paragraph position="0"> 5. PERPETRATOR : ID OF INDIV(S) &amp;quot;GUERRILLAS&amp;quot; 6. PERPETRATOR : ID OF ORG(S)  7. PERPETRATOR: CONFIDENCE  8. PHYSICAL TARGET: ID(S) 9. PHYSICAL TARGET: TOTAL NUM ' 10. PHYSICAL TARGET: TYPE(S) &amp;quot; 11. HUMAN TARGET: ID(S) &amp;quot;ROBERTO GARCIA ALVARADO&amp;quot; (&amp;quot;ATTORNEY GENERAL&amp;quot; ) 12. HUMAN TARGET : TOTAL NUM 1 13. HUMAN TARGET : TYPE(S) CIVILIAN: &amp;quot;ROBERTO GARCIA ALVARADO&amp;quot; 14. TARGET : FOREIGN NATION(S) 15. INSTRUMENT: TYPE(S) 16. LOCATION OF INCIDENT EL SALVADOR: SAN SALVADOR (CITY) 17. EFFECT ON PHYSICAL TARGET(S) 18. EFFECT ON HUMAN TARGET(S) &amp;quot;  A sample of the system's output for message 48 from TST2 is shown above . The system did fairly well, successfully applying an apposition rule in slot 11, for example . However, even though it found the appositive, it incorrectly assigned civilian type to the attorney general , due to an undiagnosed bug . The system often sloughs adjectives, e .g ., condensing &amp;quot;urban guerrillas&amp;quot; to &amp;quot;guerrillas&amp;quot; in the perpetrator id slot . Even though the first sentence of messag e 48 says &amp;quot;. . .accused the farabundo marti national liberation front (fmln) of the crime&amp;quot;, th e skimmer failed to fill the organization slot. In this case, failure was due to lack of patterns fo r accusations. Failure to find the instrument in &amp;quot;.. .was killed when a bomb placed by urba n guerrillas on his vehicle exploded&amp;quot; is due to the absence of a pattern like &amp;quot;bomb placed by actor&amp;quot;. Rather, the system knew the pattern &amp;quot;bomb BE placed by actor&amp;quot; where the verb 'to be' i s not optional.</Paragraph>
  </Section>
  <Section position="4" start_page="179" end_page="179" type="metho">
    <SectionTitle>
2. DATE OF INCIDENT 30 DEC 89
3. TYPE OF INCIDENT KIDNAPPING
4. CATEGORY OF INCIDENT TERRORIST ACT
5. PERPETRATOR: ID OF INDIV(S) &amp;quot;TERRORISTS'
6. PERPETRATOR: ID OF ORG(::) &amp;quot;FARABUNDO WARTI NATIONAL LIBERATION FRONT&amp;quot;
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="5" start_page="179" end_page="179" type="metho">
    <SectionTitle>
PEASANTS OF VARIOUS AGES HAVE BEEN KIDNAPPED BY TERRORISTS OF THE
FARABUNDO MARTI NATIONAL LIBERATION FRONT [FMLN) IN SAN MIGUEL
DEPARTMENT . ACCORDING TO THAT GARRISON, THE MASS KIDNAPPING TOOK PLACE ON
30 DECEMBER IN SAN LUIS DE LA REINA. THE SOURCE ADDED THAT THE TERRORISTS
FORCED THE INDIVIDUALS, VHO 'ERE TAKEN TO AN UNKNOWN LOCATION, OUT OF
THEIR RESIDENCES, PRESUMABLY TO INCORPORATE THEM AGAINST THEIR WILL INTO
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
class="xml-element"></Paper>