Computational linguistics research on Philippine languages

Proceedings of the 7th Workshop on Asian Language Resources - ALR7, 2009

We present the diverse research activities on Philippine languages from all over the country, with focus on the Center for Language Technologies of the College of Computer Studies,

JURNAL ARBITRER, 2019

The purpose of this research is to describe computational linguistics as a study of science that should pay full attention to linguistics researches improvement. The type of research is a literature review and experimental research by designing a software model for Bahasa. The result of the research shows that computational linguistics is a field of linguistics that can be used as a solution to overcome a problem related to spelling correction and grammar for language users. This field of linguistics is related to software engineering designed to educate the public in producing languages; it can be Bahasa, regional language, and English language as the foreign language for Indonesian. The public can know the standardization of writing a language and equivalence translation between the target language and the source language that can also be precisely acquired. Also, the writer provides several practical examples of how computational linguistics can be applied to the development of w...

Journal of Research in Science, Computing and …, 2006

Morphological analyzers (MA) are automated systems that (1) derive the root word of a transformed word, (2) identify the affixes used and (3) identify the change in semantics after the word transformation. MAs are used in the field of natural language processing and information retrieval systems to reduce the size of its word dictionary or lexicon, while being able to efficiently analyze the syntax and semantics of a word. The MA presented here is part of a bi-directional English-Filipino machine translation system. It uses an example-based approach to address the limited lexical resources and incomplete morphology rules in Filipino. It improves the Wicentowski's Word Frame model by learning morphology rules from examples to handle the morphological phenomena of prefixation, suffixation, circumfixation, internal vowel changes, infixation, and partial and whole word reduplication.

This paper explores various problems in modeling the Philippine linguistic situation. Simple cladistic models are valuable in modeling proposed genetic relationships based on the results of the comparative-historical method, but are problematic when dealing with the languages of Negrito groups that adopted Austronesian languages. They are also problematic in dealing with networking as the result of dialect chaining, and widespread lexical borrowing from non-Austronesian languages, each of which creates special problems in modeling the Philippine linguistic situation. 93 An alternative model proposed by Sagart (2004) suggests a nested structure, based on proposed innovations in numerals. Note that although MP languages reflect PAN, none of them are spoken in (mainland) Taiwan. The evidence suggests that the changes that distinguish MP languages from their sister languages in Taiwan could have developed in the Batanic Islands of the northern Philippines (Ross 2005

Benjamins Translation Library, 2016

Computational linguistics is a science combined with not only computer science and linguistics, but also mathematics, cognitive science ,and so on. With the application of computer technology into language process ,it emerged and developed gradually into an independent system. Study on linguistics influence on the development of computational linguistics and translation platform construction from the perspective of computational linguistics, promotes deep understanding ,the further research explore and effective practice on translation. There seems a certain plausible division of labor between linguistics analysis methods and language process in computational linguistics, which are combined to form a hybrid system. The approach to design the hybrid system is explored from the application of translation platform construction from the perspective of computational linguistics. The paper aims to provide some new perspectives to the translation and the teaching of foreign languages, firstly, analyzes the basic theory of the hybrid model translation platform based on computational linguistics, and then designs the translation platform in detail from the system design idea, overall structure design, and function module design three aspects.

2013

The coming of the 21st century has brought forth a promise of advancement in various fields of studies including most technological science. While computers had been around since the 20th century, the flash flood of technological advancement only came in the early 21st century. Towards the end of the first decade of the century, computer and software companies produced a gazillion updates and probably earned billions and trillions of money. With the fast-paced way of life of the 21st century, advancement did not only come in the technological and natural science field, but also in the playgrounds of social sciences. People had been more curious about how they interact, what causes the interaction and how it affects the community. It is not confined within their communities but rather it expands to the whole world. As technology continues to update itself, linguistics had also continued to grow. Many people have now seen the importance of linguistics in their lives. As such, many devote themselves in the study of the languages of the world, including Philippine languages. This paper aims to see the development of Philippine linguistics in the early 21st century and to figure out the current trends in said field as evidenced by academic researches published and/or presented during the time range. This also aims to give a brief discussion on these trends and their possible motivations. And lastly, this paper intends to hypothesize some projections on the track that Philippine linguistics may take in the future.

2010

Linguist's Assistant (LA) is a practical computational paradigm for efficiently and thoroughly describing languages. LA has been used to describe and subsequently produce first draft translations into a wide variety of languages. We recently began a joint project with De La Salle University to explore the possible use of LA in the Philippines. This paper will give a brief introduction to LA and then describe how the complex verbal system of Tagalog can be described using LA.

The Philippines is a nation of 7107 islands located in Southeast Asia. The country is home to an estimated 99,809,100 people who thrive in a rich linguistic climate, which hosts 181 living languages (Lewis, Simons, & Fennig, 2014), an English variety (Philippine English) that has reached the fourth phase of Schneider’s dynamic model (Borlongan, 2011), and a rich tradition of applied linguistics (henceforth, AL) research that is aptly captured in Dita’s (2011) Issues and trends in applied linguistics in the Philippines: a decade in retrospect.

The 30th Pacific Asia Conference on Language, Information and Computation (PACLIC), 2016

The field of Natural Language Processing (NLP) in the country has been continually developing. However, the transition between Tagalog to the progressing Filipino language left tools and resources behind. This paper introduces a Statistical Machine Translation Part-of-Speech (POS) Tagger for Filipino (SMTPOST), with the purpose of reviving, updating and widening the scope of technologies in the POS`tagging domain, catering to the changes made by the Filipino language. Resources built are comprised mainly of a tagset (218 tags), parallel corpus (2,668 sentences), affix rules (59 rules) and word-tag dictionary (309 entries). SMTPOST was tested to different tagsets and domains, producing 84.75% as its highest accuracy score, at least 3.75% increase from the available Tagalog POS taggers. Despite SMTPOST's utilization of Filipino resources and good performance, there are room for improvements and opportunities. Recommendations include a better feature extractor (preferably a morphological analyzer), an increase in scope for all of the resources, implementation of pre-and/or post-processing, and the utilization of SMTPOST research to other NLP applications.