Adding a human-attention similarity term to a transformer loss improved accuracy on small, imbalanced datasets in two NLP tasks, but the printed loss equation has the wrong sign for the stated goal.
From Characters to Words to in Between: Do We Capture Morphology?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they have not been systematically compared, and it is not understood how they interact with different morphological typologies. On a language modeling task, we present experiments that systematically vary (1) the basic unit of representation, (2) the composition of these representations, and (3) the morphological typology of the language modeled. Our results extend previous findings that character representations are effective across typologies, and we find that a previously unstudied combination of character trigram representations composed with bi-LSTMs outperforms most others. But we also find room for improvement: none of the character-level models match the predictive accuracy of a model with access to true morphological analyses, even when learned from an order of magnitude more data.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Aligning Human and Machine Attention for Enhanced Supervised Learning
Adding a human-attention similarity term to a transformer loss improved accuracy on small, imbalanced datasets in two NLP tasks, but the printed loss equation has the wrong sign for the stated goal.