Name Tagging for Low-resource Incident Languages based on Expectation-driven Learning

Proceedings of NAACL-HLT 2016, pages 249–259, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Name Tagging for Low-resource Incident Languages based on Expectation-driven Learning Boliang Zhang1, Xiaoman Pan1, Tianlu Wang2, Ashish Vaswani3, Heng Ji1, Kevin Knight3, Daniel Marcu3 1 Computer Science Department, Rensselaer Polytechnic Institute {zhangb8,panx2,jih}@rpi.edu 2 Computer Science Department, Zhejiang University 3 Information Sciences Institute, University of Southern California {vaswani,knight,marcu}@isi.edu Abstract In this paper we tackle a challenging name tagging problem in an emergent setting - the tagger needs to be complete within a few hours for a new incident language (IL) us- ing very few resources. Inspired by observing how human annotators attack this challenge, we propose a new expectation-driven learning framework. In this framework we rapidly ac- quire, categorize, structure and zoom in on IL- specific expectations (rules, features, patterns, gazetteers, etc.) from various non-traditional sources: consulting and encoding linguistic knowledge from native speakers, mining and projecting patterns from both mono-lingual and cross-lingual corpora, and typing based on cross-lingual entity linking. We also pro- pose a cost-aware combination approach to compose expectations. Experiments on seven low-resource languages demonstrate the effec- tiveness and generality of this framework: we are able to setup a name tagger for a new IL within two hours, and achieve 33.8%-65.1% F-score 1. 1 Introduction: “Tibetan Room” In many emergent situations such as disease out- breaks and natural disasters, there is great demand to rapidly develop a Natural Language Processing (NLP) system, such as name tagger, for a “surprise” Incident Language (IL) with very few resources. Traditional supervised learning methods that rely on large-scale manual annotations would be too costly. 1The resources developed in this paper, includ- ing the survey, patterns and gazetteers, are available at http://nlp.cs.rpi.edu/data/elisaienaacl16.zip Let’s start by investigating how a human would discover information in a foreign IL environment. When we are in a foreign country, even if we don’t know the language, we would still be able to guess the word “gate” from the airport broadcast based on its frequency and position in a sentence; guess the word “station” by pattern mining of many subway station labels; and guess the word “left” or “right” from a taxi driver’s GPS speaker by matching move- ment actions. We designed a “Tibetan Room” game, similar to “Chinese Room” (Searle, 1980), by ask- ing a human user who doesn’t know Tibetan to find persons, locations and organizations from some Ti- betan documents. We designed an interface where test sentences are presented to the player one by one. When the player clicks token, the interface will dis- play up to 100 manually labeled Tibetan sentences that include this token. The player can also see trans- lations of some common words and a small gazetteer of common names (800 entries) in the interface. 14 players who don’t know Tibetan joined the game. Their name tagging F-scores ranged from 0% to 94%. We found that good players usually bring in some kind of “expectations” derived from their own native languages, or general linguistic knowl- …

Content truncated to 500 words