<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1043">
  <Title>Evaluating and comparing three text-production techniques</Title>
  <Section position="6" start_page="251" end_page="253" type="concl">
    <SectionTitle>
5. Examples
</SectionTitle>
    <Paragraph position="0"> Below are several examples o1' letters produced using the semi-automatic \['ill-in4hc-blmlks system and the automatic linguistic-and-template hybrid system.</Paragraph>
    <Section position="1" start_page="251" end_page="251" type="sub_section">
      <SectionTitle>
5.1 Semi-automatic letter
ChOre Madame,
</SectionTitle>
      <Paragraph position="0"> J'ai bien fe(~u votre courrier du 30tohre \[sic\] et je eomprends tout h fait votre mdcontentement.</Paragraph>
      <Paragraph position="1"> Nous faisons le maximum pour contenter nos clients, mais nous sommes ddpcndants des ddlais de liw'aison que nous imposent certains fournisseurs.</Paragraph>
      <Paragraph position="2"> Je suis ddsolde de no pouvoir vous donner une date prdcise de livraison, croyez bien clue je regrette vivcment ce retard.</Paragraph>
      <Paragraph position="3"> Restans 5 votre enti~re disposition, je vous prie de croire, Ch6rc Madame, h l'expression de rues sentiments ddvouds.</Paragraph>
      <Paragraph position="4"> /Dear Madam, In reply to your letter of 3rd Owber \[sicL 1 can completely undetwtand your d#sati,sfaction.</Paragraph>
      <Paragraph position="5"> W(-: do our ulmost to satisJS, our customer:v, but are dependent ott the delivery times imposed on us by certain suppliers.</Paragraph>
      <Paragraph position="6"> l ant q/kaid that 1 cannot give you an exact delivery date, and sincerely apologise for this dek(y.</Paragraph>
      <Paragraph position="7"> I remain at your entire dLvposal should you require any jitrther assistance.</Paragraph>
      <Paragraph position="8"> Yours sincerely, \]</Paragraph>
    </Section>
    <Section position="2" start_page="251" end_page="252" type="sub_section">
      <SectionTitle>
5.2 Linguistic and template example
ChOre Madame,
</SectionTitle>
      <Paragraph position="0"> Je suis ddsolde que vous n'ayez pas re(2u les chaussurcs de sport blanches.</Paragraph>
      <Paragraph position="1"> Comme vous en avez dtd informdc lots de I'enrcgistremcnt de votre commando, ellcs n'dtaient pas disponibles. La livraison dtait diffdrde de deux semaines.</Paragraph>
      <Paragraph position="2"> Cc ddlai sera un peu plus long que prdvu.</Paragraph>
      <Paragraph position="3"> I)?~s la rentrde en stock de ces ehaussurcs de sport, jc vous lcs envcrrai immddiatement, cn priorit,5.</Paragraph>
      <Paragraph position="4"> J'esp~re que vous nous pardonnerez celte attente et que vous voudrez bien patienter. Je vous prie d'agrdcr, Chbre Madame, l'expression de men entier ddvouement.</Paragraph>
      <Paragraph position="5">  /Dear Mac&amp;m, \] ant very sorry/hat you have 1tot received lhe white sports shoes.</Paragraph>
      <Paragraph position="6"> These items were not available when yottr order wax ivcor(led, as 3,oil were injbrmed at the time. The deliver was postponed by two weeks.</Paragraph>
      <Paragraph position="7"> The delivery will in Jact take a little longer than planned.</Paragraph>
      <Paragraph position="8"> As soo~ cts these .S'l)orts s'hoe.s' city in sleek 1 will send them to you ill i)rioriO '.</Paragraph>
      <Paragraph position="9"> 1 helle that you will forgive us ./or this delay, and are prel)ared to wait.fin your deliveo'. YoHI'S sill('ere\[),, /</Paragraph>
    </Section>
    <Section position="3" start_page="252" end_page="252" type="sub_section">
      <SectionTitle>
5.3 Comments
</SectionTitle>
      <Paragraph position="0"> a) Spelling errol&amp;quot; ill tile semi-automatic letter' due to the dale writlen by the r)perat(rr in a blank of a predefincd senlcnce b) Personalisation: the article and its colour me mentioned only in the automatic letter c) Precision of terminology (precision of the explanalion): clearly, tile autonnltic loller is much more precise</Paragraph>
    </Section>
    <Section position="4" start_page="252" end_page="252" type="sub_section">
      <SectionTitle>
5.4 Senti-automatic example
</SectionTitle>
      <Paragraph position="0"> The following example shows the typical problem o1' ~PS~)ctition in the semi-automatic letters.</Paragraph>
      <Paragraph position="1"> Cher Monsieur, J'ai bien regal w)tre lettre qui a lelenu toule rl\]()rl attention.</Paragraph>
      <Paragraph position="2"> Je r@onds h w)trc demande concernant la marchandise diffdrde suiwmte : cardigan 4566654 lai\[le 114.</Paragraph>
      <Paragraph position="3"> La marchandise a did enrcgistr@ sous le no 176 788956.</Paragraph>
      <Paragraph position="4"> Un envoi a dld fait le 23 juin.</Paragraph>
      <Paragraph position="5"> Norlnalement, wins dewiez ddjh awfir req;u la liwaison de ce paquet, veuillez m'adresser de prdfdrence un cheque pour rdgler la l/\]archandise que rlous VOtlS av(rllS ellVOy~e. Rcstant a w)lre enli,Sre disposition, je vous pric de or(tire, Chcr M(msieur, en rues sentiments ddvouds.</Paragraph>
      <Paragraph position="6"> /Dear Si~, I have received your lettel, which I have n'gd with great attention.</Paragraph>
      <Paragraph position="7"> I am writing in ~W~I 3, to your request concerning the ,/o/lowing postponed merchandise: ealzligan 4566654 size 114. 771e merchandise was recorded with the number 176 788956.</Paragraph>
      <Paragraph position="8"> ~&lt;Sending oeetued&gt;~ oil June 23rd.</Paragraph>
      <Paragraph position="9"> You shouhl ahvcMy have received this parcel, ther@n'e would you please send me a cheque iH paymeHt of the merchandise that we have ,vellt lo yell.</Paragraph>
    </Section>
    <Section position="5" start_page="252" end_page="253" type="sub_section">
      <SectionTitle>
6.1 Analysis of results
</SectionTitle>
      <Paragraph position="0"> The order of results for tile different techniques is always tile same for all tile criteria: first, truman writing; second, the automatic hybrid approach; trod third, tile senti-automatic system. Let us now examine the salient points of each type o1' technique.</Paragraph>
      <Paragraph position="1"> Senti-automatic system 'File principal weak points of the semi-automatic system are as follows, in decreasing order of variation in relation to the human averages.</Paragraph>
      <Paragraph position="2"> * l:,liminalory criteria not always reel due lo problems of comprehension and gramlnar.</Paragraph>
      <Paragraph position="3"> * Excessive repetition (a diflcrence of 6.4 out of 20 ill relalion Io human writing, and of 3.6 ira rehrtion to tire automatic system).</Paragraph>
      <Paragraph position="4"> deg l,ack of pcrsonalisation (5.6 and 3.2).</Paragraph>
      <Paragraph position="5"> * Lack of precision in the choice of vocabulary (4.4 and 2.4).</Paragraph>
      <Paragraph position="6"> Automatic hybrid system The principal strong points of the automatic linguistic-and-templates system based on AlethGen are as follows, in decreasing order of variation in relation to lhe semi-automatic averages.</Paragraph>
      <Paragraph position="7">  The main points for improvement for lhe automatic system are as follows, in decreasing order of variation in relation to the human averages.</Paragraph>
      <Paragraph position="8">  The best characteristics of the human letters were absence of repetition, and proximity / personalisation, which were both given scores of 17.6 out of 20.</Paragraph>
      <Paragraph position="9"> it can be seen that the jury considers the tone of the human letters as being not very good: only 14.4 out of 20. This would appear to be mainly \['or reasons related to commercial communication rather than computational linguistics.</Paragraph>
    </Section>
    <Section position="6" start_page="253" end_page="253" type="sub_section">
      <SectionTitle>
6.2 Conclusion
</SectionTitle>
      <Paragraph position="0"> The first conclusion is that semi-automatic systems (just as real-situation human writing) are subject to human mistakes, and that the texts they produce may be difficult to understand.</Paragraph>
      <Paragraph position="1"> The second conclusion is that the weak points of the semi-automatic systems are the strong points of the automatic hybrid systems, in the same order.</Paragraph>
      <Paragraph position="2"> We can conclude that, even if current automatic generation systems could do better (and we believe that this will soon be the case), one of the two main reasons for using linguistic-and-template hybrid systems such as that developed by La Redoute ~md GSI-Erli, rather than using semi-automatic systems, is the improvement in quality (the other being, of course, productivity).</Paragraph>
      <Paragraph position="3"> Although there are more research and industrial projects in Analysis than in Natural Language Generation, Generation has great potential, since the gains in terms of quality and productivity largely justify the investment.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>