<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-0503">
  <Title>Simple NLP Techniques for Expanding Telegraphic Sentences</Title>
  <Section position="3" start_page="18" end_page="18" type="metho">
    <SectionTitle>
2 The Need: Target Population
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="18" end_page="18" type="sub_section">
      <SectionTitle>
Description
</SectionTitle>
      <Paragraph position="0"> One population of AAC users that might greatly benefit from expanded telegraphic input are those who are young in age but who suffer from some cognitive impairments which affect their expressive language production. According to (Kumin, 1994) and (Roth and Casset-James, 1989), language production from a population that has such cognitive impairments includes: (1) short telegraphic utterances; (2) sentences consisting of concrete vocabulary (particularly nouns); (3) morphological and syntactical difficulties such as inappropriate use of verb tenses, plurals, and pronouns; (4) word additions, omissions, or substitutions; and (5) incorrect word order. While people exhibiting these kinds of production problems may be understandable, they will often be perceived negatively in both social and educational situations. Therapy is often geared toward developing strategies that overcome or compensate for these production problems. Children who use AAC and have these kinds of difficulties face additional problems over speaking children with the same impairments both because they have additional obstacles in accessing language elements (i.e., language elements must be accessed through a device) and because language and literacy acquisition are not well understood in children who use AAC.</Paragraph>
      <Paragraph position="1"> Because of this, it is not clear what kind of interventions will be effective with these children.</Paragraph>
      <Paragraph position="2"> Our aim is to provide an AAC device which will be useful to this population both by allowing their output to be more standard, and as a potential language intervention (therapy) tool.</Paragraph>
    </Section>
  </Section>
  <Section position="4" start_page="18" end_page="19" type="metho">
    <SectionTitle>
3 Challenges with This Population
</SectionTitle>
    <Paragraph position="0"> Before any intelligent device can be developed for this population, the problem of lexical access must be solved. That is, we must find a method that enables the user to select the lexical items that they wish to communicate. The speech output communication aids that PRC designs for commercial use incorporate an encoding technique called semantic compaction, commercially known as Minspeak R (a contraction of the phrase &amp;quot;minimum effort speech&amp;quot;) (Baker, 1982), (Baker, 1984). Minspeak R is ultimately an abbreviation expansion system, but it is designed to eliminate much of the cognitive load associated with abbreviation expansion. In using abbreviation expansion, users are required to memorize a set of abbreviations that, if typed, will be expanded into full words. For example, the user might type &amp;quot;t &amp;quot; for CCthe &amp;quot; and ~Csch &amp;quot; for ' 'school ' '. Of course, there is a tremendous amount of cognitive load associated with memorizing abbreviations (and with developing memorable abbreviations for a large number of words). Suffice it to say that regular abbreviation expansion is not a viable option for the population being considered here.</Paragraph>
    <Paragraph position="1"> Minspeak x deals with the cognitive load associated with standard abbreviation systems by forming abbreviations using multi-meaning icons rather than letters. Because the icons are rich in meaning and associations, a small number of icons (keys) can be used to represent a large vocabulary where each item can be selected using a memorable sequence of 2-3 icons. The success of the general Minspeak R paradigm of vocabulary access led PRC to start designing tailored prestored vocabulary programs known as Minspeak Application Programs (MAPs TM) for specific populations of users. These programs are concerned with providing both an appropriate vocabulary and a set of icons appropriately placed on the keyboard so as to allow communication in an &amp;quot;automatic&amp;quot; fashion.</Paragraph>
    <Paragraph position="2"> One of these MAPsTM(the Communic-Ease MAP TM) was developed for users chronologically  10 or more years of age with a language age of 56 years. This MAP provides access to a basic vocabulary and has proven to be an effective inter- null face for users in our target population. It provides access to approximately 580 single words divided into 38 general categories. Most of these words are coded as 2-icon sequences. The first icon in the sequence (the category icon) establishes the word category. For example, the &lt;SKULL&gt; icon indicates a body part word, the &lt;MASKS&gt; icon indicates a feeling word, and the &lt;APPLE&gt; icon indicates a food word. The second icon denotes the specific word.</Paragraph>
    <Paragraph position="3"> For example, &lt;MASK&gt; followed by &lt;SUN&gt; produces the word &amp;quot;happy&amp;quot;; &lt;APPLE&gt; followed by &lt;APPLE&gt;. produces the word &amp;quot;eat&amp;quot;. The learning and use of icon sequences is facilitated by the incorporation of &amp;quot;icon prediction&amp;quot;. In icon prediction the user is &amp;quot;prompted&amp;quot; for valid icon sequences using lights on keys. For example, once the first icon is hit (e.g., &lt;MASK&gt;) lights will appear on icons that lead to a word (e.g., all icons that complete a valid feeling word will be lit).</Paragraph>
    <Paragraph position="4"> In addition to the words which are accessed via the icon sequences, Communic-EaseTMcontains some morphology and allows the addition of endings to regular tense verbs and regular noun plurals. However, note that to accomplish this, additional keystrokes are required. Also, it is possible to spell words that are not included in the core vocabulary.</Paragraph>
    <Paragraph position="5">  In practice, however, users with either slow access methods or poor language ability tend to produce telegraphic messages consisting of sequences of core vocabulary items without embellishing morphology.</Paragraph>
    <Paragraph position="6"> Our project builds a processing method on top of the Communic-Ease MApTMwhich will expand the telegraphic/mis-ordered input on the part of the user into well formed sentences. Notice that developing a ~ystem for this particular population will overcome some of the difficulties faced with the general Compansion system built as a writing tool for people with sophisticated linguistic ability. First, this population will rely on a limited vocabulary. As was noted above, the users of this particular vocabulary access system generally use only the vocabulary items programmed into the Communic-Ease MAP TM. While the method allows them to spell any word, in actuality spelling is rather limited and the spelled vocabulary items may be easier to anticipate. Second, the output structures of the sentences will not require sophisticated syntactic constructions. This population requires limited output structures comprised primarily of fairly simple sentence structures. Finally, the system will not face the same sorts of input problems described in conjunction with the Compansion system. Again, this primarily follows from the language sophistication of the chosen population.</Paragraph>
    <Paragraph position="7"> On the other hand, this population of users does bring with it other difficulties. For example, it is likely that users may produce unusual sentence input. While we do not expect to see the same sorts of complications with the input described above with respect to Compansion, it is likely that the input will display unusual characteristics. For example, with linguistically sophisticated users we expect the input word order to mirror the desired surface form.</Paragraph>
    <Paragraph position="8"> This assumption does not hold for users with cognitive impairments. Thus we must carefully study this population to determine exactly what kind of input to expect.</Paragraph>
    <Paragraph position="9"> Other problems faced by this system have to do with the ability of the user to handle the decisions that are required of them. For instance, it may be the case that selecting from a set of expanded sentences may prove very difficult for this population who may become confused or may be unable to retain their desired sentence when given a list of sentences to choose from. Thus it becomes extremely important that the system present appropriate expansions and that these expansions be ordered using a heuristic that accurately predicts the most likely expansion.</Paragraph>
    <Paragraph position="10"> Because of the cognitive impairments, it is also likely that the user will have a great deal of difficulty if the system acts in unexpected ways. Thus, the system must be extremely robust and capable of handling any input given to it.</Paragraph>
    <Paragraph position="11"> Finally, the system's interface must be carefully designed so as to make it easy for users to learn and use. In addition, the system must be fast and runnable on relatively inexpensive and portable PC platforms so as to make it cost effective.</Paragraph>
  </Section>
  <Section position="5" start_page="19" end_page="19" type="metho">
    <SectionTitle>
4 Simple Techniques
</SectionTitle>
    <Paragraph position="0"> In this project we have decided to collapse the three levels of processing found in Compansion into one level. The system is implemented in C++ for economy of memory and for speed and compatibility considerations. null The major processing in the system takes place in an augmented transition network type of grammar.</Paragraph>
    <Paragraph position="1"> The network itself encodes a grammar of the telegraphic input expected from this population. The tests in the grammar may be made on the basis of syntactic or semantic features stored in the lexicon on each word. Some of the actions in the grammar are responsible for manipulating a particular register which encodes the &amp;quot;generated string&amp;quot; or expansion associated with each state in the network.</Paragraph>
    <Paragraph position="2"> Thus these actions are responsible for adding determiners etc. Sets of registers axe also maintained for recording semantic aspects of the partial sentence (e.g., information such as what word is the agent).</Paragraph>
    <Paragraph position="3"> This information is primarily used to reconstruct an appropriate expansion if later input indicates inappropriate decisions were made in earlier states of the parse.</Paragraph>
    <Paragraph position="4"> The augmented transition network formalism was chosen for this work mainly because it allowed parallel traversal of all possible parses and therefore the ability to predict next input words. This allowed us to extend the icon prediction mechanism described in the Communic-Ease MApTMto the word level.</Paragraph>
    <Paragraph position="5"> For instance, in a situation where the user has typed an adjective, only icons that begin valid next words (e.g., adjective, noun) will be highlighted thus facilitating learning. One can imagine this particular aspect of the system being expanded for therapy sessions. For example, it might be used to teach a user to use standard agent-verb-object sentences by highlighting only words that fit into that pattern.</Paragraph>
  </Section>
  <Section position="6" start_page="19" end_page="20" type="metho">
    <SectionTitle>
5 Methodological Issues
</SectionTitle>
    <Paragraph position="0"> Our system functionality has been determined by a collection of transcripts from Communic-EaseTMusers. We have collected both raw keystroke data (so that we can establish the range of input  we expect from the population) and keystroke data from videotaped sessions where interpretations of the keystroke data are provided by a communication partner. This data allows us to ensure the output from the system is in fact appropriate. In addition it has been used to validate expected sentence structures, validate the expectation that the core vocabulary will comprise most of the input, allow us to better anticipate the spelled vocabulary, and validate input expectations.</Paragraph>
    <Paragraph position="1"> Our methodology in using the data has been to partition it into several sets. First, some portion of each of the two kinds of data has been set aside for testing purposes. Thus it is not seen for purposes of system development. Because the videotaped sessions contain both input and its expansion, these are being used primarily as a means for tuning the expansion rules used in the grammar and the appropriateness heuristics that order the expansions produced by the system. We will attempt for the system to mimic the partner on the videotaped sessions.</Paragraph>
    <Paragraph position="2"> The raw keystroke data is being used in two ways.</Paragraph>
    <Paragraph position="3"> Most obviously it is being used to tune the grammar to the range of input. Secondly, some of the raw data is being associated with multiple interpretations deemed reasonable by one of the team members. These interpretations will be used to further tune the grammar expansions.</Paragraph>
    <Paragraph position="4"> Several evaluations of the completed prototype system are planned and made possible by the setaside collected data. Ffi:st, the robustness of the grammar can be tested by determining the number of completed input utterances found in the collected data that can be handled by the grammar.</Paragraph>
    <Paragraph position="5"> Second, the appropriateness of the grammar can be tested by determining how often the grammar's output matches the interpretation provided by the communication partner (in the video sessions containing interpretations by the partner) or by a human faced with the same sequence of words (for the raw data to which interpretations have been added).</Paragraph>
    <Paragraph position="6"> In addition to the theoretical grammar testing described above, we also plan an informal evaluation of the usability of the system. We plan to iteratively refine the interface by doing usability studies of our prototype with current users of the Communic-Ease MAP TM. We anticipate beginning this testing during the summer and fall of 1997.</Paragraph>
  </Section>
class="xml-element"></Paper>