Syllabification does not seem to improve word-level RNN language modeling quality when compared to characterbased segmentation. However, our best syllable-aware language model, achieving performance comparable to the competitive character-aware model, has 18%-33% fewer parameters and is trained 1.2-2.2 times faster.

We present our initial experiments on Russian to Kazakh phrase-based statistical machine translation. Following a common approach to SMT between morphologically rich languages, we employ morphological processing techniques. Namely, for our initial experiments, we perform source-side lemmatization. Given a rather humble-sized parallel corpus at hand, we also put some effort in data cleaning and investigate the impact of data quality vs. quantity trade off on the overall performance. Although our experiments mostly focus on source side preprocessing we achieve a substantial, statistically significant improvement over the baseline that operates on raw, unprocessed data.

No abstract

We address the problem of normalizing user generated content in a multilingual setting. Specifically, we target comment sections of popular Kazakhstani Internet news outlets, where comments almost always appear in Kazakh or Russian, or in a mixture of both. Moreover, such comments are noisy, i.e. difficult to process due to (mostly) intentional breach of spelling conventions, which aggravates data sparseness problem. Therefore, we propose a simple yet effective normalization method that accounts for multilingual input. We evaluate our approach extrinsically, on the tasks of language identification and sentiment analysis, showing that in both cases normalization improves overall accuracy.

No abstract