Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction

Daniela Gerz, Ivan Vulić, Edoardo Ponti, Jason Naradowsky, Roi Reichart, Anna Korhonen


Abstract
Neural architectures are prominent in the construction of language models (LMs). However, word-level prediction is typically agnostic of subword-level information (characters and character sequences) and operates over a closed vocabulary, consisting of a limited word set. Indeed, while subword-aware models boost performance across a variety of NLP tasks, previous work did not evaluate the ability of these models to assist next-word prediction in language modeling tasks. Such subword-level informed models should be particularly effective for morphologically-rich languages (MRLs) that exhibit high type-to-token ratios. In this work, we present a large-scale LM study on 50 typologically diverse languages covering a wide variety of morphological systems, and offer new LM benchmarks to the community, while considering subword-level information. The main technical contribution of our work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction. We conduct experiments in the LM setting where the number of infrequent words is large, and demonstrate strong perplexity gains across our 50 languages, especially for morphologically-rich languages. Our code and data sets are publicly available.
Anthology ID:
Q18-1032
Volume:
Transactions of the Association for Computational Linguistics, Volume 6
Month:
Year:
2018
Address:
Venue:
TACL
SIG:
Publisher:
Note:
Pages:
451–465
Language:
URL:
https://www.aclweb.org/anthology/Q18-1032
DOI:
10.1162/tacl_a_00032
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/Q18-1032.pdf