Yaser Al-Onaizan

Translating Named Entities Using Monolingual and Bilingual Resources

Named entity phrases are some of the most difficult phrases to translate because new phrases can appear from nowhere, and because many are domain specific, not to be found in bilingual dictionaries. We present a novel algorithm for translating named entity phrases using easily obtainable monolingual and bilingual resources. We report on the application and evaluation of this algorithm in translating Arabic named entities to English. We also compare our results with the results obtained from human translations and a commercial system for the same task.

Machine Transliteration of Names in Arabic Texts

We present a transliteration algorithm based on sound and spelling mappings using finite state machines. The transliteration models can be trained on relatively small lists of names. We introduce a new spelling-based model that is much more accurate than state-of-the-art phonetic-based models and can be trained on easier-to-obtain training data. We apply our transliteration algorithm to the transliteration of names from Arabic into English. We report on the accuracy of our algorithm based on exact-matching criterion and based on human-subjective evaluation. We also compare the accuracy of our system to the accuracy of human translators.

On being a teammate: experiences acquired in the design of RoboCup teams

Increasingly, multi-agent systems are being designed for a variety of complex, dynamic domains. Effective agent interactions in such domains raise some of the most fundamental research challenges for agent-based systems, in teamwork, multi-agent learning and agent modelling. The RoboCup research initiative, particularly the simulation league, has been proposed to pursue such multi-agent research challenges, using the common testbed of simulation soccer. Despite the significant popularity of RoboCup within the research community, general lessons have not often been extracted from participation in RoboCup. This is what we attempt to do here. We have fielded two teams, ISIS97 and ISIS98, in RoboCup competitions. These teams have been in the top four teams in these competitions. We compare the teams, and attempt to analyze and generalize the lessons learned. This analysis reveals several surprises, pointing out lessons for teamwork and for multi-agent learning.

Experiences Acquired in the Design of RoboCup Teams: A Comparison of Two Fielded Teams

Increasingly, multi-agent systems are being designed for a variety of complex, dynamic domains. Effective agent interactions in such domains raise some of the most fundamental research challenges for agent-based systems, in teamwork, multi-agent learning and agent modelling. The RoboCup research initiative, particularly the simulation league, has been proposed to pursue such multi-agent research challenges, using the common testbed of simulation soccer. Despite the significant popularity of RoboCup within the research community, general lessons have not often been extracted from participation in RoboCup. This is what we attempt to do here. We have fielded two teams, ISIS97 and ISIS98, in RoboCup competitions. These teams have been in the top four teams in these competitions. We compare the teams, and attempt to analyze and generalize the lessons learned. This analysis reveals several surprises, pointing out lessons for teamwork and for multi-agent learning.

Translation with Scarce Bilingual Resources

Machine translation of human languages is a field almost as old as computers themselves. Recent approaches to this challenging problem aim at learning translation knowledge automatically (or semi-automatically) from online text corpora, especially human-translated documents. For some language pairs, substantial translation resources exist, and these corpus-based systems can perform well. But for most language pairs, data is scarce, andcurrent techniques do not work well. To examine the gap betweenhuman and machine translators, we created an experiment in which humanbeings were asked to translate an unknown language into English on thesole basis of a very small bilingual text. Participants performed quite well,and debriefings revealed a number of valuable strategies. We discuss thesestrategies and apply some of them to a statistical translation system.

Beam Search Strategies for Neural Machine Translation.

The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new translations that approximately maximize the trained conditional probability. The current beam search strategy generates the target sentence word by word from left-to- right while keeping a fixed amount of active candidates at each time step. First, this simple search is less adaptive as it also expands candidates whose scores are much worse than the current best. Secondly, it does not expand hypotheses if they are not within the best scoring candidates, even if their scores are close to the best one. The latter one can be avoided by increasing the beam size until no performance improvement can be observed. While you can reach better performance, this has the draw- back of a slower decoding speed. In this paper, we concentrate on speeding up the decoder by applying a more flexible beam search strategy whose candidate size may vary at each time step depending on the candidate scores. We speed up the original decoder by up to 43% for the two language pairs German-English and Chinese-English without losing any translation quality.

Using an Explicit Teamwork Model and Learning in RoboCup: An Extended Abstract

The RoboCup research initiative has established synthetic and robotic soccer as testbeds for pursuing research challenges in Articial Intelligence and robotics. This extended abstract focuses on teamwork and learning, two of the multi- agent research challenges highlighted in RoboCup. To address the challenge of teamwork, we discuss the use of a domain-independent explicit model of team- work, and an explicit representation of team plans and goals. We also discuss the application of agent learning in RoboCup.

ISIS: An Explicit Model of Teamwork at RobotCup-97

56 AI MAGAZINE Group A: LAI (Université Carlos III De Madrid), FC MELLON (CMU), RM KNIGHTS (RMIT), ICHIMURA (Kinki University, Japan). Group B: RIEKKI (University of Oulu, Finland), CMUNITED (CMU), HEADLESS CHICKENS (RMIT), NIT-STONES (Nagoya Institute of Technology, Japan). Group C: MICROB (Université de Paris VI), BALCH (Georgia Institute of Technology), PROJECT MAGI (Aoyama University, Japan), OHTA (Tokyo Institute of Technology, Japan). Group D: AT HUMBOLDT (Humboldt University, Germany), TEAM SICILY (Stanford University), KASUGA-BITO (Chubu University, Japan), ANDHILL (Tokyo Institute of Technology, Japan). Group E: PAGELLO (University of Padua, Italy), HAARLEM (Chukyo University, Japan), ORIENT (Toyo University, Japan). Group F: UBC DYNAMO (University of British Columbia, Canada), LUKE (University of Maryland), OGALETS (University of Tokyo, Japan), TUT (Toyohashi University of Technology, Japan). Group G: CHRISTENSEN (Charlmers University of Technology, Sweden), TEAM GAMMA (ETL, Japan), KOSUE (Kinki University, Japan). Group H: ISIS (USC-ISI), GARBAGE COLLECTORS (private, Japan), I&W (Waseda University, Japan).