<?xml version="1.0" standalone="yes"?>
<Paper uid="N06-2027">
  <Title>Using Semantic Authoring for Blissymbols Communication Boards</Title>
  <Section position="3" start_page="105" end_page="105" type="metho">
    <SectionTitle>
2 Generating Messages via Translation
</SectionTitle>
    <Paragraph position="0"> A major difficulty when parsing a telegraphic sequence of words or symbols, is that many of the hints that are used to capture the structure of the text and, accordingly, the meaning of the utterance, are missing. Moreover, as an AAC device is usually used for real-time conversation, the interpretation of utterances relies heavily on pragmatics - time of mentioned events, reference to the immediate environment. null Previous works dealing with translating telegraphic text, such as (Grishman and Sterling, 1989), (Lee et al., 1997) requires to identify dependency relations among the tokens of the telegraphic input.</Paragraph>
    <Paragraph position="1"> Rich lexical knowledge is needed to identify possible dependencies in a given utterance, i.e., to find the predicate and to apply constraints, such as selectional restrictions to recognize its arguments.</Paragraph>
    <Paragraph position="2"> Similar methods were used for AAC applications, COMPANSION (McCoy, 1997) for example - where the telegraphic text is expanded to full sentences, using a word order parser, and a semantic parser to build the case frame structure of the verb in the utterance, filling the slots with the rest of the content words given. The system uses the semantic representation to re-generate fluent text, relying on lexical resources and NLG techniques.</Paragraph>
    <Paragraph position="3"> The main questions at stake in this approach are how good can a semantic parser be, in order to reconstruct the full structure of the sentence from telegraphic input and are pragmatic gaps in the given telegraphic utterances recoverable in general.</Paragraph>
  </Section>
  <Section position="4" start_page="105" end_page="106" type="metho">
    <SectionTitle>
3 Generating Messages via Semantic
Authoring
</SectionTitle>
    <Paragraph position="0"> Our approach differs from previous NLG-AAC systems in that, with the model of semantic authoring (Biller et al., 2005), we intervene during the process of composing the input sequence, and thus can provide early feedback (in the form of display composition and partial text feedback), while preventing the need for parsing a telegraphic sequence.</Paragraph>
    <Paragraph position="1"> Semantic parsing is avoided by constructing a semantic structure explicitly while the user inputs the sequence incrementally. It combines three aspects into an integrated approach for the design of an AAC system: * Semantic authoring drives a natural language realization system and provides rich semantic input.</Paragraph>
    <Paragraph position="2"> * A display is updated on the fly as the authoring system requires the user to select options.</Paragraph>
    <Paragraph position="3"> * Ready-made inputs, corresponding to predefined pragmatic contexts are made available to the user as semantic templates.</Paragraph>
    <Paragraph position="4"> In this method, each step of input insertion is controlled by a set of constraints and rules, which are drawn from an ontology. The system offers, at each step, only possible complements to a small set of concepts. For example, if the previous symbol denotes a verb which requires an instrumental theme, only symbols that can function as instruments are presented on the current display. Other symbols are accessible through navigation operations, which are interpreted in the context of the current partial semantic specification. The general context of each utterance or conversation can be determined by the user, therefore narrowing the number of symbols displayed in the board.</Paragraph>
    <Paragraph position="5"> The underlying process of message generation is based on layered lexical knowledge bases (LKB) and an ontology. The ontology serves as a basis for the semantic authoring process; it includes a hierarchy of concepts and relations, and the information it encodes interacts with the conceptual graphs processing performed as part of content determination and lexical choice. The ontology was acquired with a semi-automatic tool, which relies on WordNet (Miller, 1995) and VerbNet (Kipper et al., 2000).</Paragraph>
    <Paragraph position="6"> We designed and implemented the Bliss lexicon for both Hebrew and English. The lexicon can be used either as a stand-alone lexicon or as part of an application through an API. The design of the lexicon takes advantage of the unique properties of the language. The Bliss lexicon provides the list of symbols accessible to the user, along with their graphic representation, semantic information, and the mapping of symbols to English and Hebrew words. The lexicon can be searched by keyword (learn), or by semantic/graphic component: searching all words in the lexicon that contain both food and meat returns the symbols hamburger, hot-dog, meatball etc. (see  plication The core of the processing machinery of the AAC message generation system is based on SAUT (Biller et al., 2005) - an authoring system for logical forms encoded as conceptual graphs (CG). The system belongs to the family of WYSIWYM (What You See Is What You Mean) (Power and Scott, 1998) text generation systems: logical forms are entered interactively and the corresponding linguistic realization of the expressions is generated in several languages. The system maintains a model of the discourse context corresponding to the authored documents to enable reference planning in the generation process.</Paragraph>
    <Paragraph position="7"> Generating language from pictorial inputs, and specifically from Bliss symbols using semantic authoring in the WYSIWYM approach is not only a pictorial application of the textual version, but it also addresses specific needs of augmentative communication. null As was mentioned above, generating text from a telegraphic message for AAC usage must take the context of the conversation into account. We address this problem in two manners: (1) adding pre-defined inputs into the system (yet allowing accurate text generation that considers syntactic variations), and (2) enabling the assignment of default values to each conversation (such as participants, tense, mood). We also take advantage of the unique properties of the Bliss symbols; the set of symbols that are offered in each display can be filtered using their semantic/graphical connectivity; the reduction of the number of possible choices that are to be made by the user in each step of the message generation affects the cognitive load and can affect the rate of communication. null</Paragraph>
  </Section>
class="xml-element"></Paper>