How to Make a Frenemy: Multitape FSTs for Portmanteau Generation

Deri, Aliya; Knight, Kevin

doi:10.3115/v1/n15-1021

Cited by 14 publications

(31 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our model to previous methods namely (Deri and Knight, 2015) and (Gangal et al, 2017). Inline with (Gangal et al, 2017), we evaluate our model on D knight and D blind (consisting of 1078 instances) 8 .…”

Section: Discussionmentioning

confidence: 99%

Simple Models for Word Formation in Slang

Kulkarni

Wang

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

We propose generative models for three types of extra-grammatical word formation phenomena abounding in English slang: Blends, Clippings, and Reduplicatives. Adopting a datadriven approach coupled with linguistic knowledge, we propose simple models with state of the art performance on human annotated gold standard datasets. Overall, our models reveal insights into the generative processes of word formation in slang -insights which are increasingly relevant in the context of the rising prevalence of slang and non-standard varieties on the Internet.

show abstract

Section: Discussionmentioning

confidence: 99%

Simple Models for Word Formation in Slang

Kulkarni

Wang

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

show abstract

“…In this section, we show results comparing various configurations of our model to the baseline FST model of Deri and Knight (2015) (BASELINE). Models are evaluated using exactmatches (Matches) and average Levenshtein editdistance (Distance) w.r.t ground truth.…”

Section: Methodsmentioning

confidence: 99%

“…The existing dataset by Deri and Knight (2015) contains 401 portmanteau examples from Wikipedia. We refer to this dataset as D Wiki .…”

Section: Datasetmentioning

confidence: 99%

“…For instance, Shaw et al (2014) state that the composition of the portmanteau from its root words depends on several factors, two important ones being maintaining prosody and retaining character segments from the root words, especially the head. An existing work by Deri and Knight (2015) aims to solve the problem of predicting portmanteau using a multi-tape FST model, which is datadriven, unlike prior approaches. Their methods rely on a grapheme to phoneme converter, which takes into account the phonetic features of the language, but may not be available or accurate for non-dictionary words, or low resource languages.…”

Section: Introductionmentioning

confidence: 99%

“…shows the results of Experiment 1 for various model configurations. We get the BASELINE numbers fromDeri and Knight (2015). Our best model obtains 48.75% Matches and 1.12 Distance, compared to 45.39% Matches and 1.59 Distance using BASE-LINE.For Experiment 2, we seek to compare our best approaches from Experiment 1 to the BASELINE on a large, held-out dataset.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Charmanteau: Character Embedding Models For Portmanteau Creation

Gangal

Jhamtani

Neubig

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Portmanteaus are a word formation phenomenon where two words are combined to form a new word. We propose character-level neural sequence-tosequence (S2S) methods for the task of portmanteau generation that are end-toend-trainable, language independent, and do not explicitly use additional phonetic information. We propose a noisy-channelstyle model, which allows for the incorporation of unsupervised word lists, improving performance over a standard sourceto-target model. This model is made possible by an exhaustive candidate generation strategy specifically enabled by the features of the portmanteau task. Experiments find our approach superior to a state-of-the-art FST-based baseline with respect to ground truth accuracy and human evaluation.

show abstract