121 |
Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions ...
|
|
|
|
BASE
|
|
Show details
|
|
124 |
Examining Gender Bias in Languages with Grammatical Gender ...
|
|
|
|
BASE
|
|
Show details
|
|
126 |
The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
127 |
Uncovering Probabilistic Implications in Typological Knowledge Bases ...
|
|
|
|
BASE
|
|
Show details
|
|
128 |
On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study ...
|
|
|
|
BASE
|
|
Show details
|
|
129 |
On the Idiosyncrasies of the Mandarin Chinese Classifier System ...
|
|
|
|
BASE
|
|
Show details
|
|
130 |
Combining Sentiment Lexica with a Multi-View Variational Autoencoder ...
|
|
|
|
BASE
|
|
Show details
|
|
131 |
Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction ...
|
|
|
|
Abstract:
Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a statistically rare inflection such as habláramos. Note the lexeme itself, hablar, is relatively common. In this work, we investigate whether state-of-the-art bilingual lexicon inducers are capable of learning this kind of generalization. We introduce 40 morphologically complete dictionaries in 10 languages and evaluate three of the state-of-the-art models on the task of translation of less frequent morphological forms. We demonstrate that the performance of state-of-the-art models drops considerably when evaluated on infrequent morphological inflections and then show that adding a simple morphological constraint at training time improves the performance, proving that the bilingual lexicon inducers can benefit from better encoding of morphology. ... : EMNLP 2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1909.02855 https://dx.doi.org/10.48550/arxiv.1909.02855
|
|
BASE
|
|
Hide details
|
|
133 |
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
135 |
Are All Languages Equally Hard to Language-Model?
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
136 |
Rethinking Phonotactic Complexity
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
137 |
On the Complexity and Typology of Inflectional Morphological Systems
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 327-342 (2019) (2019)
|
|
BASE
|
|
Show details
|
|
138 |
Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
139 |
Marrying Universal Dependencies and Universal Morphology ...
|
|
|
|
BASE
|
|
Show details
|
|
140 |
On the Complexity and Typology of Inflectional Morphological Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|