SOTAVerified

Morphological Inflection

Morphological Inflection is the task of generating a target (inflected form) word from a source word (base form), given a morphological attribute, e.g. number, tense, and person etc. It is useful for alleviating data sparsity issues in translating morphologically rich languages. The transformation from a base form to an inflected form usually includes concatenating the base form with a prefix or a suffix and substituting some characters. For example, the inflected form of a Finnish stem eläkeikä (retirement age) is eläkeiittä when the case is abessive and the number is plural.

Source: Tackling Sequence to Sequence Mapping Problems with Neural Networks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 135 papers

TitleStatusHype
BME Submission for SIGMORPHON 2021 Shared Task 0. A Three Step Training Approach with Data Augmentation for Morphological Inflection—0
Were We There Already? Applying Minimal Generalization to the SIGMORPHON-UniMorph Shared Task on Cognitively Plausible Morphological Inflection—0
Do RNN States Encode Abstract Phonological Alternations?—0
Falling Through the Gaps: Neural Architectures as Models of Morphological Rule LearningCode0
Minimal Supervision for Morphological InflectionCode0
Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models—0
On Biasing Transformer Attention Towards MonotonicityCode0
Do RNN States Encode Abstract Phonological Processes?—0
Interpretability for Morphological Inflection: from Character-level Predictions to Subword-level RulesCode0
Smoothing and Shrinking the Sparse Seq2Seq Search SpaceCode0
Show:102550
← PrevPage 5 of 14Next →

No leaderboard results yet.