Morphological Word-Embeddings
By Ryan Cotterell, Hinrich Schütze. 2019
104 citations recorded by the source corpus.
Linguistic similarity is multi-faceted. For instance, two words may be similar with respect to semantics, syntax, or morphology inter alia. Continuous word-embeddings have been shown to capture most of these shades of similarity to some degree. This work considers guiding word-embeddings with morphologically annotated data, a form of semi-supervised learning, encouraging the vectors to encode a word's morphology, i.e., words close in the embedded space share morphological features. We extend the log-bilinear model to this end and show that indeed our learned embeddings achieve this, using German as a case study.
Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Armand Joulin
- Edouard Grave
- Piotr Bojanowski
- Luke S. Zettlemoyer
- Douwe Kiela
- Kyunghyun Cho
- Mohit Bansal
- Jason Aaron Edward Weston
In Natural Language Processing
- Armand Joulin
- Edouard Grave
- Piotr Bojanowski
- Douwe Kiela
- Luke S. Zettlemoyer
- Jason Aaron Edward Weston
- Hinrich Schütze
- Tomas Mikolov
In Representation & Self-Supervised Learning
- Armand Joulin
- Piotr Bojanowski
- Edouard Grave
- Tomas Mikolov
- Clara Vania
- Hinrich Schütze
- Adam Lopez
- Benoît Sagot
Citations in the corpus
- Enriching Word Vectors with Subword Information (2016, background): “Cui et al. (2015) proposed to constrain morphologically similar words to have similar representations.”
- From Characters to Words to in Between: Do We Capture Morphology? (2017, methodology): “word units obtained from morphological segmentation or analysis (Luong et al., 2013; Botha and Blunsom, 2014; Cotterell and Schütze, 2015).”