paper-with-me

Papers

A Structured Variational Autoencoder for Contextual Morphological Inflection

2018-06-10 · ACL 2018 7 · Lawrence Wolf-Sonkin, Jason Naradowsky, Sabrina J. Mielke, Ryan Cotterell

Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.

📄 PDF Abstract BibTeX arXiv:1806.03746

Code (2)

LeenaShekhar/NLP-Linguistics-ML-Resources tf
LeenaShekhar/NLP-ML-Resources tf

Tasks

Morphological InflectionVariational Inference

Similar Papers 제목 키워드 기반

The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection

2019-10-25 · WS 2019 8 · Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya 외

The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic…

Cross-Lingual TransferLemmatizationMorphological AnalysisMorphological Inflection+1

Remote Elicitation of Inflectional Paradigms to Seed Morphological Analysis in Low-Resource Languages

2016-05-01 · LREC 2016 5 · John Sylak-Glassman, Christo Kirov, David Yarowsky

Structured, complete inflectional paradigm data exists for very few of the world{'}s languages, but is crucial to training morphological analysis tools. We present methods inspired by linguistic fieldwork for gathering i…

Morphological Analysis

Morphological Inflection Generation with Multi-space Variational Encoder-Decoders

2017-08-01 · CONLL 2017 8 · Chunting Zhou, Graham Neubig
Information RetrievalMachine TranslationMorphological Inflection

Well-Defined Morphology is Sentence-Level Morphology

2021-11-01 · EMNLP (MRL) 2021 11 · Omer Goldman, Reut Tsarfaty

Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context. However, the lack …

Morphological AnalysisMorphological InflectionSentence

On the Complexity and Typology of Inflectional Morphological Systems

2018-07-08 · TACL 2019 3 · Ryan Cotterell, Christo Kirov, Mans Hulden, Jason Eisner

We quantify the linguistic complexity of different languages' morphological systems. We verify that there is an empirical trade-off between paradigm size and irregularity: a language's inflectional paradigms may be eithe…