<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-2018">
  <Title>A Prototype Text to British Sign Language (BSL) Translation System</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 System Architecture
</SectionTitle>
    <Paragraph position="0"> The architecture of the English text to British Sign Langauge (BSL) system is essentially a pipeline of  four main translation stages 1. English syntactic parsing, 2. Discourse Representation Structure (DRS) generation, 3. Semantic transfer, 4. Generation of HamNoSys SL phonetic descriptions, as illustrated in Figure 1.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.1 Syntactic Parsing
</SectionTitle>
      <Paragraph position="0"> English text (Figure 2 top left) is parsed by the Carnegie Mellon University (CMU) link grammar parser (Sleator and Temperley, 1991) to produce an appropriate linkage which characterises syntactic dependencies (Figure 2 bottom left). In cases where multiple linkages are generated, the user intervenes to select an appropriate linkage.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.2 DRS Generation
</SectionTitle>
      <Paragraph position="0"> From a CMU parser generated linkage a Discourse Representation Structure DRS (Kamp and Reyle, 1993) is generated to capture the semantic content of the text (Figure 2 top middle). DRSs allow isolation of specific semantic content (nominal, verbal and adjectival based predicates, discourse referents and temporal relationships). Anaphora resolution is used to associate pronouns with discourse referents, and reuse of nouns is used to imply co-reference to the same linguistic referent. Currently, the most common 50% CMU links are transformed into DRS form.</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.3 Semantic Transfer
</SectionTitle>
      <Paragraph position="0"> An English oriented DRS is transformed into a SL oriented DRS. In particular, the number of arguments for some predicates is modified to a different number of arguments expected of a corresponding SL sign. For example, the English verb move obligatorily requires only one argument but is often accompanied by optional adjuncts for the source and destination locations. Its BSL equivalent (glossed as MOVE) requires three arguments - the start and end sign space positions and a (classifier or default) handshape consistent with the object being moved.</Paragraph>
      <Paragraph position="1"> Such transformations are effected on the DRS.</Paragraph>
      <Paragraph position="2"> The DRS is then transformed to an equivalent  HPSG semantic structure which is the starting point for SL generation.</Paragraph>
    </Section>
    <Section position="4" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.4 HamNoSys SL Generation
</SectionTitle>
      <Paragraph position="0"> A SL grammar and lexicon are used to drive derivation of a HamNoSys phonetic description of a sign sequence from the HPSG semantic structure (Figure 2 bottom middle). The BSL lexicon contains approximately 250 lexical items. Some lexical items are fully instantiated forms for fixed and bodyanchored signs, however others are only partially instantiated forms for directional verbs and forms of modulation of lexical items. For nominal oriented signs, classifiers are associated with signs, and for directional verbs the lexical entries require incorporation of specific forms of classifiers and sign space locations.</Paragraph>
      <Paragraph position="1"> The SL grammar constitutes a collection of simultaneous constraints which the phonology and syntax of selected signs must satisfy in order to constitute a valid sign sequence. These constraints enforce appropriate sign order, for example realising a topic comment ordering signs for the English sentence &amp;quot; I saw an exciting video.&amp;quot;</Paragraph>
    </Section>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
VIDEO EXCITING/INTERESTING SEE ME
</SectionTitle>
    <Paragraph position="0"> Sign space location agreement requires that nominals are assigned consistent positions in signing space and that directional verbs agree with these positions that reflects anaphoric relationships of the original text and use with directional verbs. In this example, the directional verb SEE must start at the location of ME and be directed towards the location of VIDEO. Subsequent references to the same object must respect its position by signing the sign at the same location or by anaphoric pointing at that location. This form of agreement is achieved by inclusion of a model of signing space within the HPSG feature structure in which nominals are allocated positions and from which verbal signs acquire positional information (Figure 2 top right).</Paragraph>
    <Paragraph position="1"> Number agreement between nominal and verbal signs is enforced distinguishing between collective and distributive interpretations of plurals. For example, the friends in &amp;quot;I invited four friends&amp;quot; may have been invited individually (in which case the directional verb INVITE is repeated three times) or they may have been invited as a group (with INVITE signed only once). The under-specification in the English input is resolved by requesting the user to volunteer the additional information of a distributive or collective reading.</Paragraph>
    <Paragraph position="2"> Conclusions The resulting HamNoSys sign sequence descriptions are realised visually as virtual human behaviour (Kennaway, 2001) (Figure 2 bottom right) 2. Currently, the SL generation sub-system incorporates a lexicon and grammar whose coverage are representative of a number of interesting SL phenomena and whose semantic, syntactic and phonological formalisation is one of the most advanced SL characterisations available. Such detail is essential to enable visualisation by a virtual human. The main omission in the system currently is the absence of non-manual components of signing, though the SL generation has been designed to be extended in this direction in the future. The functionality of the system is demonstrable on a laptop computer.</Paragraph>
  </Section>
class="xml-element"></Paper>