Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging

TLDR

Part‑of‑speech tagging for resource‑poor languages is hampered by scarce annotated data, and type constraints derived from Wiktionary or bitext projections have been used to mitigate this. This study demonstrates that token constraints can be projected from a resource‑rich source language to a resource‑poor target language using word‑aligned bitext. The authors employ a partially observed conditional random field model that integrates coupled token and type constraints to train taggers. Across eight Indo‑European languages, the model reduces tagging error by 25 % relative to the previous state of the art, and it also succeeds on seven additional languages from diverse families.

Abstract

We consider the construction of part-of-speech taggers for resource-poor languages. Recently, manually constructed tag dictionaries from Wiktionary and dictionaries projected via bitext have been used as type constraints to overcome the scarcity of annotated data in this setting. In this paper, we show that additional token constraints can be projected from a resource-rich source language to a resource-poor target language via word-aligned bitext. We present several models to this end; in particular a partially observed conditional random field model, where coupled token and type constraints provide a partial signal for training. Averaged across eight previously studied Indo-European languages, our model achieves a 25% relative error reduction over the prior state of the art. We further present successful results on seven additional languages from different families, empirically demonstrating the applicability of coupled token and type constraints across a diverse set of languages.