A study of N-gram and Embedding Representations for Native Language Identification
TL
TL;DR
N-grams covering word, character, POS and word-POS mixed representations and embedding based feature representations for Native Language Identification had a relatively poor performance, which could be because of the fact that embeddings capture semantic similarities whereas L1 differences are more stylistic in nature.
Abstract
We report on our experiments with N-gram and embedding based feature representations for Native Language Identification (NLI) as a part of the NLI Shared Task 2017 (team name: NLI-ISU). Our best performing system on the test set for written essays had a macro F1 of 0.8264 and was based on word uni, bi and trigram features. We explored n-grams covering word, character, POS and word-POS mixed representations for this task. For embedding based feature representations, we employed both word and document embeddings. We had a relatively poor performance with all embedding representations compared to n-grams, which could be because of the fact that embeddings capture semantic similarities whereas L1 differences are more stylistic in nature.
References38 items
1
Efficient, Compositional, Order-sensitive n-gram Embeddings
2
Native Language Identification using Stacked Generalization
3
Discriminating between Similar Languages and Arabic Dialect Identification: A Report on the Third DSL Shared Task
4
Advancing Linguistic Features and Insights by Label-informed Feature Grouping: An Exploration in the Context of Native Language Identification
5