Sentence embeddings can be decomposed into sparse, interpretable atoms via supervised dictionary learning, and mean pooling preserves mainly atoms aligned with the sentence direction.
Subword Pooling Makes a Difference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Contextual word-representations became a standard in modern natural language processing systems. These models use subword tokenization to handle large vocabularies and unknown words. Word-level usage of such systems requires a way of pooling multiple subwords that correspond to a single word. In this paper we investigate how the choice of subword pooling affects the downstream performance on three tasks: morphological probing, POS tagging and NER, in 9 typologically diverse languages. We compare these in two massively multilingual models, mBERT and XLM-RoBERTa. For morphological tasks, the widely used `choose the first subword' is the worst strategy and the best results are obtained by using attention over the subwords. For POS tagging both of these strategies perform poorly and the best choice is to use a small LSTM over the subwords. The same strategy works best for NER and we show that mBERT is better than XLM-RoBERTa in all 9 languages. We publicly release all code, data and the full result tables at \url{https://github.com/juditacs/subword-choice}.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mechanistic Decomposition of Sentence Representations
Sentence embeddings can be decomposed into sparse, interpretable atoms via supervised dictionary learning, and mean pooling preserves mainly atoms aligned with the sentence direction.