A Graph Auto-encoder Model of Derivational Morphology
Valentin Hofmann, Hinrich Schütze, Janet B. Pierrehumbert
2020年份
10被引次数
2顶会引用
摘要
There has been little work on modeling the morphological well-formedness (MWF) of derivatives, a problem judged to be complex and difficult in linguistics (Bauer, 2019) . We present a graph auto-encoder that learns embeddings capturing information about the compatibility of affixes and stems in derivation. The auto-encoder models MWF in English surprisingly well by combining syntactic and semantic information with associative information from the mental lexicon.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
引用它的顶会 Paper2
- Predicting the Growth of Morphological Families from Social and Linguistic FactorsValentin Hofmann, Janet B. Pierrehumbert, Hinrich SchützeACL 2020 · 被引用 13 次
- Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language ModelLeonie Weissweiler, Valentin Hofmann, Anjali Kantharuban, Anna Cai 等EMNLP 2023 · 被引用 10 次
它引用的顶会 Paper1
相关 Paper
- Semi-Supervised Semantic Dependency Parsing Using CRF AutoencodersZixia Jia, Youmi Ma, Jiong Cai, Kewei TuACL 2020 · 被引用 10 次
- 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker DesignYinan Huang, Xingang Peng, Jianzhu Ma, Muhan ZhangICML 2022 · 被引用 65 次
- DagoBERT: Generating Derivational Morphology with a Pretrained Language ModelValentin Hofmann, Janet B. Pierrehumbert, Hinrich SchützeEMNLP 2020 · 被引用 1 次
- Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex WordsValentin Hofmann, Janet B. Pierrehumbert, Hinrich SchützeACL 2021
- Unbiased learning of deep generative models with structured discrete representationsHenry C. Bendekgey, Gabe Hope, Erik B. SudderthNeurIPS 2023 · 被引用 2 次
