<?xml version="1.0" standalone="yes"?>
<Paper uid="J03-2001">
  <Title>c(c) 2003 Association for Computational Linguistics A Model for Matching Semantic Maps between Languages (French/English, English/French)</Title>
  <Section position="5" start_page="167" end_page="169" type="metho">
    <SectionTitle>
3. Results
</SectionTitle>
    <Paragraph position="0"> The advantages of the model presented are (1) access to an extended lexicon and a broad semantic field and (2) coherence of the matching between the semantic values in each language. The results for insensible will be used again in this section to illustrate the second advantage.</Paragraph>
    <Section position="1" start_page="167" end_page="167" type="sub_section">
      <SectionTitle>
3.1 Access to an Extended Semantic Field and Lexicon
</SectionTitle>
      <Paragraph position="0"> The model fulfills two functions: It searches for a suitable lexicon and organizes the terms found. For each entry, the initial data provides a short list of terms representing certain prototypes of the word's translation. Table 1 lists the four English terms proposed as translations for the French word insensible. It can happen that certain semantic values in the source language are not represented in the translation database. For example, insensible has no corresponding French word in our database of English word translations. However, the model builds the appropriate values in French (Figure 3).</Paragraph>
      <Paragraph position="1"> The model builds a much larger vocabulary that includes the initial terms from the translation database and some semantic neighbors. Table 7 presents an overall evaluation of the results.</Paragraph>
      <Paragraph position="2">  Two-cluster separation of the French and English spaces for the French headword insensible.</Paragraph>
    </Section>
    <Section position="2" start_page="167" end_page="169" type="sub_section">
      <SectionTitle>
3.2 Coherence of the Semantic Matching
</SectionTitle>
      <Paragraph position="0"> The final step in the model consists of establishing a correspondence between the semantic values of the cliques and the terms in the two languages. By application of the above algorithm, the cliques and terms of the two languages are plotted on the same map. This map thus provides a summary of the semantic proximities in each language. In order to demonstrate the coherence of the semantic-value matching after projection onto the target language, the clusters obtained from the French and English cliques for the term insensible are superimposed on one another. Figures 4 and 5 present the division of the output into two and four clusters. (The French clusters in these figures are marked by a darker line and set in a darker typeface than the English ones.) As in the two-cluster semantic space for the French word insensible, Figure 4 separates the perceptual value from the other values.</Paragraph>
      <Paragraph position="1"> The three-cluster separation then differentiates the physical-moral value from the moral value. Figure 5 shows the division within the physical-moral value between what is more specifically physical and what pertains to emotional insensitivity (emotionless, r'efractaire, etc.) or to the inability to discern that sensitivity (imp'en'etrable, etc.). Note that although all values initially present in the monolingual space are represented, a reorganization process still takes place during pairing with the target language. In French, the terms (r'efractaire, inacessible, ...) were separated from the terms (inerte, engourdi, ...) by the group made up of the terms (dur, sans-coeur, ...), but now they are located close to the center. This layout probably results from (1) the effect of the greater number of terms like (inert, numb, sluggish, chilly, ...), which, in English, unlike in French, encompass emotional and physical insensitivity and therefore bring these two values closer together on the map, and (2) the prototypical, central nature of this value in English, as expressed by the terms (impassive, insensible, insensitive, ...).</Paragraph>
      <Paragraph position="2">  Ploux and Ji A Model for Matching Semantic Maps Figure 5 Four-cluster separation of the French and English spaces for the French headword insensible.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="169" end_page="171" type="metho">
    <SectionTitle>
4. Discussion
</SectionTitle>
    <Paragraph position="0"> We have presented a model for matching a semantic space in a source language and a semantic space in a target language. This model, currently built from lexical similarity relations (synonymy or near-synonymy and translations), uses several representation levels: cliques, which represent very precise units of meaning; terms, which are represented geometrically by a region in the space containing a set of cliques; and clusters, which are generated from the results of a spatialization process that singles out a term's main semantic values. (Again, this last representation level is merely mentioned in the present article; the method used to generate it and the rationale for its use in semantic classification will be described in detail in a forthcoming publication.) The matching between the French and English spaces is achieved by mapping the cliques of the two languages to each other. The model software allows a user to choose a candidate word in the target language according to its synonym neighborhood. A map showing each language's neighborhoods and separate clusters for each semantic value helps the user make the choice. This system and its interactive interface is a useful tool appreciated by researchers, translators, writers, and other users. Although this alone is enough to justify the model, it would be worthwhile to incorporate it into a more complete automatic language processing system. We are now working on enhancing the system by including context relations, and by bringing to bear a word's argument structure, qualia structure, and lexical inheritance.</Paragraph>
    <Paragraph position="1"> Within the past 10 years, original contributions have been made in the areas of compositional semantics and lexical context assignment (see Ide and Veronis [1998] for the state of the art on word sense disambiguation). Most studies have dealt with the sentence, but some have looked at the discourse and text levels. Based on a generative framework, Pustejovski (1995) proposed a computational model that adds a representation of a word's structures (event structure, argument structure, qualia structure, and  Computational Linguistics Volume 29, Number 2 lexical inheritance structure), along with transformation rules for combining units. In their study, Asher and Lascarides (1995) showed that lexical semantics and discourse structure may interfere with discourse structure and devised heuristics to disentangle the effects of these two interacting levels. Other authors (Foltz, Kintsch, and Landauer 1998; Kintsch 2001; Sch &amp;quot;utze 1998) have developed an approach based solely on automatic corpus analysis in which co-occurrences and their frequencies are used to generate the semantic space associated with a given word. Edmonds and Hirst (2002) proposed a model with two tiers: a fine-grained synonym tier and a coarse conceptual tier. Unlike Edmonds and Hirst's approach, which rests on an ontological model and conceptual representations, our model is capable of detecting semantic distinctions solely on the basis of similarity links. This feature is one of the model's assets, but it is also a limitation, which provides the incentive for the enhancements we are currently developing. Here is a brief preview of our ongoing projects: * Certain words are poorly represented in terms of synonymy. This is the case for words that are essentially nonpolysemous, like computer or daisy, and thus have very few synonyms. Such entities are better delineated by an ontological, hierarchical representation and by their qualia structure than by synonymy links. Grammatical words also have few synonyms, so they too need to be represented in a formalism more suited to their own features than the one proposed in this article.</Paragraph>
    <Paragraph position="2"> * Usage contexts or domains of application are not currently given for the different semantic values detected by the model. For example, the perceptual value of the word insensible is employed to modify external phenomena, whereas the moral and physical values apply to animate beings. It would thus be useful, as in a standard dictionary, to specify the different types of terms the values obtained can modify.</Paragraph>
    <Paragraph position="3"> * Our research should help improve map drawing. At the present time, map neighborhoods rely solely on semantic criteria, which sometimes leads to the map's including terms with similar meanings but different syntactic category memberships than the initial word.</Paragraph>
    <Paragraph position="4"> These projects should contribute to furthering research on language and automatic language processing. As stated in the article's introduction, we are also working on the cognitive relevance of our model. We have already conducted an initial study aimed at determining whether a spatial model is an appropriate way of representing the structure of the mental lexicon. Our work on this problem draws from a preliminary study (Rouibah, Ploux, and Ji 2001) which proposes a homomorphism between lexical distance (the organizing principal of our model) and reaction time (the parameter used in lexical access experiments). This idea is based on the finding that lexical distance is subject to the same effects as reaction time.</Paragraph>
    <Paragraph position="5">  Ploux and Ji A Model for Matching Semantic Maps 1. Qui n'a pas de sensibilit'e physique. inanim'e, mort. (Having no physical sensitivity. inanimate, dead.) 2. Qui n''eprouve pas les sensations habituelles, normales. (Not experiencing the usual, normal sensations) (insensible `ala douleur, au froid, `a la chaleur. (insensitive to pain, to cold, to heat.) 3. Qui n'a pas de sensibilit'e morale; qui n'a pas ou a peu  d''emotions. (Having no moral sensitivity; having few if any emotions.) apathique, calme, d'etach'e, froid, impassible, imperturbable, indiff'erent. cruel, dur, 'ego&amp;quot;iste, endurci, impitoyable, implacable, inexorable. imperm 'eable, indiff 'erent.</Paragraph>
    <Paragraph position="6"> sourd. 'etranger, ferm 'e, inaccessible; r 'efractaire. (apathetic, calm, detached, cold, impassible, imperturbable, indifferent. cruel, hard, egotistical, hardened, pitiless, implacable, inexorable.</Paragraph>
    <Paragraph position="7"> impervious, indifferent. deaf. foreign, closed, inaccessible; resistant.)</Paragraph>
  </Section>
  <Section position="7" start_page="171" end_page="173" type="metho">
    <SectionTitle>
* II
</SectionTitle>
    <Paragraph position="0"> 1. Qu'on ne sent pas, qu'on ne per,coit pas ou qui est `a peine  sensible, perceptible. imperceptible, l'eger. (Not being sensed, not being perceived or being just barely sensible, perceptible. imperceptible, slight.) 2. Graduel, progressif. (Gradual, progressive.) System output for a request to generate the semantic space associated with the French headword insensible.</Paragraph>
    <Paragraph position="1"> Your query was: insensible. There are 71 synonyms and 93 cliques. Table 8 Synonym list for the headword insensible (French lexical database). insensible: adamantin, anesth'esi'e, apathique, aride, assoupi, blas'e, calleux, calme, cruel, de marbre, dess'ech'e, dur, d'etach'e, endormi, endurci, engourdi, flegmatique, frigide, froid, f'eroce, glacial, glac'e, immobile, impassible, imperceptible, imperm'eable, imperturbable, impitoyable, implacable, imp'en'etrable, inabordable, inaccessible, inanim'e, inapparent, indiff'erent, indiscernable, indolent, indolore, inerte, inexorable, inflexible, inhumain, ininflammable, insaisissable, insignifiant, invisible, invuln'erable, l'eger, l'ethargique, mort, neutre, n'egligeable, obtus, paralys'e, progressif, rebelle, rigide, r'efractaire, sans coeur, sans entrailles, sans coeur, sec, sourd, sto&amp;quot;icien, sto&amp;quot;ique, suprasensible, s 'ev `ere, timide, 'ego&amp;quot;iste, 'etranger, 'etroit.</Paragraph>
    <Paragraph position="2">  77 cruel, heartless, inexorable, pitiless, relentless 78 cruel, heartless, inexorable, relentless, stern 79 cruel, heartless, inhuman, merciless, pitiless, ruthless 80 cruel, heartless, merciless, pitiless, relentless, ruthless, unfeeling 81 cruel, implacable, inexorable, pitiless, relentless 82 cruel, implacable, merciless, pitiless, relentless 83 cruel, inexorable, relentless, severe, stern 84 cruel, inhuman, merciless, pitiless, ruthless, savage 85 dead, extinct, inanimate, lifeless</Paragraph>
  </Section>
  <Section position="8" start_page="173" end_page="173" type="metho">
    <SectionTitle>
Acknowledgments We gratefully
</SectionTitle>
    <Paragraph position="0"> acknowledge support of the Agence Universitaire de la Francophonie and the FRANCIL network.</Paragraph>
  </Section>
class="xml-element"></Paper>