Language Identification with a Reciprocal Rank Classifier
This addresses the problem of domain adaptation and data scarcity in language identification for NLP pipelines, though it is incremental with a novel method for a known bottleneck.
The paper tackles language identification in real-world settings by proposing a lightweight Reciprocal Rank Classifier (RRC) that uses ranked lists of words and character frequencies, achieving robust performance with macro F1-scores of 93.1% on Wikipedia and 90.6% on Twitter, outperforming existing systems like SVM, fastText, and langid.
Language identification is a critical component of language processing pipelines (Jauhiainen et al.,2019) and is not a solved problem in real-world settings. We present a lightweight and effective language identifier that is robust to changes of domain and to the absence of copious training data. The key idea for classification is that the reciprocal of the rank in a frequency table makes an effective additive feature score, hence the term Reciprocal Rank Classifier (RRC). The key finding for language classification is that ranked lists of words and frequencies of characters form a sufficient and robust representation of the regularities of key languages and their orthographies. We test this on two 22-language data sets and demonstrate zero-effort domain adaptation from a Wikipedia training set to a Twitter test set. When trained on Wikipedia but applied to Twitter the macro-averaged F1-score of a conventionally trained SVM classifier drops from 90.9% to 77.7%. By contrast, the macro F1-score of RRC drops only from 93.1% to 90.6%. These classifiers are compared with those from fastText and langid. The RRC performs better than these established systems in most experiments, especially on short Wikipedia texts and Twitter. The RRC classifier can be improved for particular domains and conversational situations by adding words to the ranked lists. Using new terms learned from such conversations, we demonstrate a further 7.9% increase in accuracy of sample message classification, and 1.7% increase for conversation classification. Surprisingly, this made results on Twitter data slightly worse. The RRC classifier is available as an open source Python package (https://github.com/LivePersonInc/lplangid).