<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1074">
  <Title>Computational Linguistics Research on Philippine Languages</Title>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
1 Philippine Languages
</SectionTitle>
    <Paragraph position="0"> Within the 7,200 islands of the Philippine archipelago, there are about one hundred and one (101) languages that are spoken. This is according to the nationwide 1995 census conducted by the National Statistics Office of the Philippine Government (NSO, 1997). The languages that are spoken by at least one percent of the total household population include Tagalog, Cebuano, Ilocano, Hiligaynon, Bikol, Waray, Pampanggo or Kapangpangan, Boholano, Pangasinan or Panggalatok, Maranao, Maguin-danao, and Tausug.</Paragraph>
    <Paragraph position="1"> Aside from these major languages, there are other Philippine dialects, which are variants of these major languages. Fortunato (1993) classified these dialects into the top nine major languages as above (except for Boholano which is similar to Cebuano).</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 Language Representations
</SectionTitle>
    <Paragraph position="0"> Linguistics information on Philippine languages are extensive on the languages mentioned above, except for Maranao, Maguindanao, and Tausug, which are some of the languages spoken in Southern Philippines. But as of yet, extensive research has already been done on theoretical linguistics and little is known for computational linguistics. In fact, the computational linguistics researches on Philippine languages are mainly focused on Tagalog. 1 There are also notable work done on Ilocano.</Paragraph>
    <Paragraph position="1"> Kroeger (1993) showed the importance of the grammatical relations in Tagalog, such as subject and object relations, and the insufficiency of a surface phrase structure paradigm to represent these relations. This issue was further discussed in the LFG98, which is on the problem of voice and grammatical functions in Western Austronesian Languages. Musgrave (1998) introduced the problem certain verbs in these languages that can head more than one transitive clause type. Foley (1998) and Kroeger (1998), in particular, discussed about long debated issues such as nouns in Tagalog that can be verbed, the voice system of Tagalog, and Tagalog as a symmetrical voice system.</Paragraph>
    <Paragraph position="2"> Latrouite (2000) argued that a level of semantic representation is still necessary to explicitly capture a word's meaning.</Paragraph>
    <Paragraph position="3"> Crawford (1999) contributed to an issue on interrogative sentences and suggested that the restriction on wh-movement reveals the syntactic structure of Tagalog.</Paragraph>
    <Paragraph position="4"> Potet (1995) and Trost (2000) provided general materials on computational morphology, though, both presented examples on Tagalog.</Paragraph>
    <Paragraph position="5"> Rubino (1997, 1996) provided an in-depth analysis of Ilocano. Among the major contributions of the work include an extensive treatment of the complex morphology in the language, a thorough treatment of the discourse 1 Tagalog (or Pilipino) has the most number of speakers in the country. This may be due to the fact that it was officially declared the national language of the Philippines in 1946.</Paragraph>
    <Paragraph position="6"> particles, and the reference grammar of the language.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 Applications in Machine Translation
</SectionTitle>
    <Paragraph position="0"> Currently, most of the empirical endeavours in computational linguistics are in machine translation.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.1 Filipino MT Software
</SectionTitle>
      <Paragraph position="0"> There are several commercially available translation software, which include Philippine language, but translation is done word-for-word.</Paragraph>
      <Paragraph position="1"> One such software is the Universal Translator 2000, which includes Tagalog among 40 other languages. Although omni-directional, translation involving Tagalog excludes morpho logical and syntactic aspects of the language Another software is the Filipino Language Software, which includes Tagalog, Visayan, Cebuano, and Ilocano languages.</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
3.2 Machine Translation Research
</SectionTitle>
      <Paragraph position="0"> IsaWika! is an English to Filipino machine translator that uses the augmented transition network as its computational architecture (Roxas, 1999). It translates simple and compound declarative statements as well as imperative English statements. To date, it is the most serious research undertaking in machine translation in the Philippines.</Paragraph>
      <Paragraph position="1"> Borra (1999) presented another translation software that translates simple declarative and imperative statements from English to Filipino. The computational architecture of the system is based on LFG, which differs from IsaWika's ATN implementation. Part of the research was describing a possible set of semantic information on every grammar category to establish a semantically-close translation.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>