Program and Speakers

Conference Program

April 22, 2016

08:30–09:00

Registration

09:00–09:40

Doxology and National Anthem

Welcome Remarks
Madam Jane Annette Belarmino
Vice President for Development, Silliman University

Opening Remarks
Prof. Rachel Edita Roxas
Vice President for Academic Affairs, National University
Chair, Computing Society of the Philippines Special Interest Group on Natural Language Processing (CSP SIG-NLP)

09:40–10:00

Morning Break

10:00–11:00

Invited Talk
Session Chair: Prof. Rachel Edita Roxas, National University

Computational Linguistic Approaches to Non-literal Meaning and to Changes of Meaning in Context

Prof. Chu-Ren Huang
Chair Professor of Applied Language Studies, Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University

 

Oral Presentations
Session Chair: Mr. Allan Borra, De La Salle University

11:00–11:30

Meron o Mayroon: An Exploratory Study on Hiligaynon and Tagalog “Diphthongs”
Diane Manzano and Samantha Jade Sadural

11:30–12:00

Clustering Different Philippine Languages using Trigrams
Angelica Dela Cruz, Maria Cristina Co, Adrian Martin Sy and Nathaniel Oco

12:00–13:00

Lunch

 

Oral Presentations
Session Chair: Mr. Kurt Junshean Espinosa, University of the Philippines Cebu

13:00–13:30

A Sentiment Analysis of AlDub-related Tweets using a Model-Based Approach
Mari Hintay, Kenzo Sardea, Jenny Aducal, Mart Jacob and Rachel Edita Roxas

13:30–14:00

Classification of Disaster-Related Tweets Written in the Filipino Language
Kristine Ma. Dominique Kalaw, Ralph Vincent Regalado, Vilson Lu, Kyle Mc Hale Dela Cruz and John Paul Garcia

14:00–15:00

Invited Talk
Session Chair: Prof. Rachel Edita Roxas, National University

Linguist’s Assistant: Modifying a Tagalog Lexicon and Grammar to Accommodate Ayta Mag-Indi

Dr. Tod Allman
Graduate Institute of Applied Linguistics

15:00–15:20

Afternoon Break

15:20–15:50

Presentation
Session Chair: Mr. Jonathan Mark Te, Silliman University

Initiatives of the Philippine California Advanced Research Institutes (PCARI)

15:50–16:30

Workshop
Session Chair: Ms. Maria Art Antonette Clariño, University of the Philippines Los Baños

Developing Externally-Funded Projects

Prof. Rachel Edita Roxas
Vice President for Academic Affairs, National University
Chair, Computing Society of the Philippines Special Interest Group on Natural Language Processing (CSP SIG-NLP)

16:30–17:30

Presentation
Session Chair: Mr. Allan Borra, De La Salle University

Philippine Component of the ASEAN Machine Translation Project

Dr. Joel Ilao
Computer Technology Department, De La Salle University

Dr. Robert Roxas
Department of Computer Science, University of the Philippines Cebu

Dr. Raquel Sison-Buban
Filipino Department, De La Salle University

Ms. Charibeth Cheng
Software Technology Department, De La Salle University

Mr. Solomon See
Software Technology Department, De La Salle University

Mr. Ralph Vincent Regalado
Software Technology Department, De La Salle University

17:30–18:00

CSP SIG-NLP Meeting
(open only to registered members)


April 23, 2016

09:00–09:10

Announcements

09:10–10:10

Workshop
Session Chair: Mr. Ramon Rodriguez, National University

Linguist’s Assistant: Modifying a Tagalog Lexicon and Grammar to Accommodate Ayta Mag-Indi

Dr. Tod Allman
Graduate Institute of Applied Linguistics 

Venue: CC 11, College of Computer Studies Building
Note: Limited slots only

09:10–10:10

Poster Session
Session Chair: Dr. Rodolfo Raga, Jr., Jose Rizal University

An Analysis of Election-Related Tweets through Topic Modeling
Francis Apostol, Michelle Garingan, Abigail Villanueva, Cristina Santos and Rachel Roxas

Distributed representations for spatio-temporal modelling and sentiment analysis
Kurt Junshean Espinosa

Implementing a Bi-Directional English-Ilocano Translator for the Literature Domain
Ariel Neimond Lazaro, Janena Ragencia, Quinna Soler, John Michael Talingdan and Susan Caluya

Sociagraph: A Keyword Extractor and Sentiment Analyser Using Support Vector Machines
Jefferson Ferrera and Katrina Joy Magno

Twictionary: Normalizing Non-standard words on Twitter
Michelle Pairat, Princess Maelene Aquino, Jennifer Carreon, Inaj Alira Espinosa and Ramon Rodriguez

10:10–10:30

Morning Break

 

Oral Presentations
Session Chair: Mr. Ramon Rodriguez, National University

10:30–11:00

Automatic Text Summarization using ChainRank: A Hybrid Technique
Michael Angeles, Nathaniel Laxina, Maria Art Antonette Clariño and Rizza Mercado

11:00–11:30

Using Statistical Machine Translation for Style and Grammar Correction
Manolito Octaviano Jr, Nathaniel Oco and Allan Borra

11:30–12:00

Towards a Modified Hybrid N-gram Based Grammar Checker Applied in Filipino
Matthew Phillip Go and Allan Borra

12:15–12:30

Closing Remarks
Dr. Dave Marcial
OIC Dean, College of Computer Studies, Silliman University

12:30–13:30

Lunch


Speakers

Computational Linguistic Approaches to Non-literal Meaning and to Changes of Meaning in Context

Prof. Chu-Ren Huang, Hong Kong Polytechnic University

One of the most difficult challenges to NLP, in addition to emotion, is the processing of non-literal meaning. Different kinds of non-literal meanings include but are not limited to metaphor/synaesthesia, irony/sarcasm, metonymy, hyperbole, euphemism, and evening lying. The challenge of processing of nonliteral meaning lies in the incongruity between what is said and what is meant, or what is said and what the speaker believes. Yet, the contextual meaning of a nonliteral expression is often richer; and of course being able to obtain implicitly expressed meanings gives a knowledge system important advantage. In this talk, I will lay out the linguistic description of several important types of non-literal meanings especially metaphor (time is money), synaesthesia (sweet voice), irony/sarcasm (don’t we all LOVE Trump?), and metonymy (Malacañang defended the integrity of the Philippine financial system). I will also explicate the kind of challenge the pose to NLP. And lastly, I will conclude by introducing recent work done by my collaborators and myself on the processing of non-literal meanings.

Related papers can be downloaded @

https://www.researchgate.net/profile/Chu-Ren_Huang or

http://llt.cbs.polyu.edu.hk/

 

About the speaker

Chu-Ren Huang is a chair professor at the Hong Kong Polytechnic University. He received his PhD in linguistics from Cornell in 1987 and a Docteur Honoris Causa in the humanities from Aix-Marseille University in 2013. He is a Fellow as well as President of the Hong Kong Academy of the Humanities; and a permanent member of the International Committee on Computational Linguistics. Before joining the Hong Kong Polytechnic University to serve as Dean for the Faculty of Humanities for the past 6 years, he was with Academia Sinica in Taiwan for the past 22 years. In Taiwan, he spearheaded the development of corpus and computational linguistics and introduced several new linguistic theories such LFG, GPSG, and HPSG. He also lead the construction of language resources such as CKIP Lexicon, Sinica Corpus, Sinica Treebank, Sinica BOW,  Chinese WordNet, and Hantology. He is editor in chief of Lingua Sinica, Cambridge Studies in Natural Language Processing, and The Humanities in Asia.  He also serve as associate editor for Journal of Chinese Linguistics and Lexicography, as well as editorial board members for other journals in related areas.  His publication includes 23 book or edited volumes, 10 online and 12 licensable language resources, over 140 journal articles or book chapters, and over 400 refereed conference papers. His past co-edited books include Ontology and the Lexicon (Cambridge) and Computational Linguistics and Beyond (Academia Sinica). His upcoming books and edited volumes include A Reference Grammar of Chinese (Cambridge), Mandarin Chinese Words and Parts of Speech: A corpus-based study (Routledge), Chinese Language Processing (Cambridge),Digital Humanties: Bridging the Divide(Springer), Routledge Handbook in Chinese Applied Linguistics (Routledge), and Generative Lexicon Studies in Chinese (Commercial Press, in Chinese).


Linguist’s Assistant: Modifying a Tagalog Lexicon and Grammar to Accommodate Ayta Mag-Indi

Dr. Tod Allman, Graduate Institute of Applied Linguistics

Linguist’s Assistant (LA) is a large scale multilingual natural language generator designed and developed entirely from a linguist’s perspective.  The system incorporates extensive typological, semantic, syntactic, and discourse research into its semantic representational system and its transfer and synthesizing grammars.  LA has been tested with a variety of languages including English, Korean, Tagalog, Kewa (Papua New Guinea), Jula (Cote d’Ivoire), and North Tanna (Vanuatu).  In every case the system has generated initial draft translations that are of such high quality that they typically quadruple the productivity of experienced mother-tongue translators. 

A Tagalog lexicon and grammar were developed using LA, and initial draft translations of several short books were produced.  Those drafts were then edited by a mother-tongue speaker in order to make them presentable first drafts.  Questionnaires were used to compare the quality of LA’s edited drafts with the quality of professionally translated and published versions of the same books. The survey results indicate that LA’s edited drafts are of the same quality as the professionally translated and published texts.

Approximately one year was required to develop the Tagalog lexicon and grammar.  The Tagalog grammar is now fairly complete, so the project has shifted to focus on Ayta Mag-Indi, a Malayo-Polynesian language spoken by approximately 5,000 people in the Zambales and Pampanga provinces.  The goal of this project is to modify the Tagalog lexicon and grammar to accommodate Ayta Mag-Indi.  Because Tagalog and Ayta Mag-Indi are structurally very similar, modifying the Tagalog grammar to accommodate Ayta Mag-Indi should require much less time than was necessary for developing the Tagalog grammar. 

The ultimate goal of this project is to use LA to build lexicons and grammars for numerous languages spoken in the Philippine provinces.  After these lexicons and grammars are complete, LA will produce initial draft translations of many texts in these languages.

 

About the speaker

Dr. Tod Allman has been working in the field of Natural Language Generation for the past twenty years.  He and his colleagues have designed and developed a linguistically based natural language generator called Linguist’s Assistant (LA).  LA produces high quality draft translations in a wide variety of languages, particularly minority and endangered languages.  Linguists may use LA to simultaneously document a language, and also produce initial draft translations of significant texts in the language.  When experienced mother-tongue translators edit the translations produced by this system into publishable texts, their productivity is typically quadrupled without any loss of quality.  LA incorporates extensive typological, semantic, syntactic, and discourse research into its semantic representational system and its transfer and synthesizing grammars.  Tod has worked with linguists and mother-tongue speakers in order to develop lexicons and grammars for a variety of languages including Korean, Kewa (Papua New Guinea), Jula (Cote d’Ivoire), Angas (Nigeria), Chinantec (Mexico), Nsenga (Zambia), and White Sands (Vanuatu).  He is now living in the Manila area in order to build lexicons and grammars for several of the Malayo-Polynesian languages spoken here in the Philippines.  He hopes that the texts generated by LA will empower the speakers of these languages by enabling them to participate in the larger world, and by providing them with vital information which helps them live longer, healthier, and more productive lives.

Comments