Fetching the paper…
Reading the bibliography…
How does the input segmentation of pretrained language models (PLMs) affect their interpretations of complex words? We present the first study investigating this question, taking BERT as the example PLM and focusing on its semantic representations of English derivatives.
Lexical storage and retrieval of prefixed words
Marcus Taft and Kenneth I. Forster. 1975 · 1975
Earlier work this paper cites.
The processing of affixed words
Leon Manelis and David A. Tharp. 1977 · 1977
Earlier work this paper cites.
Recognition of affixed words and the word frequency effect
Marcus Taft. 1979 · 1979
Earlier work this paper cites.
Prefix stripping revisited
Marcus Taft. 1981 · 1981
Earlier work this paper cites.
Lexical representation
Brian Butterworth. 1983 · 1983
Earlier work this paper cites.
Address mechanisms to decomposed lexical entries
Alessandro Laudanna and Cristina Burani. 1985 · 1985
Earlier work this paper cites.
Representation and processing of derived words
Cristina Burani and Alfonso Caramazza. 1987 · 1987
Earlier work this paper cites.
The inflected noun system in Serbo-Croatian: Lexical representation of morphological structure
Laurie B. Feldman and Carol A. Fowler. 1987 · 1987
Earlier work this paper cites.
Morphology as lexical organization
Joan Bybee. 1988 · 1988
Earlier work this paper cites.
Lexical access and inflectional morphology
Alfonso Caramazza, Alessandro Laudanna, and Cristina Romani. 1988 · 1988
Earlier work this paper cites.
A morphological-decomposition model of lexical representation
Marcus Taft. 1988 · 1988
Earlier work this paper cites.
Indexing by latent semantic analysis
Scott Deerwester, Susan T. Dumais, George Furnas, Thomas Landauer, and Richard Harshman. 1990 · 1990
Earlier work this paper cites.
Productivity and English derivation: A corpus-based study
R. Harald Baayen and Rochelle Lieber. 1991 · 1991
Earlier work this paper cites.
Constraining psycholinguistic models of morphological processing and representation: The role of productivity
Uli H. Frauenfelder and Robert Schreuder. 1992 · 1991
Earlier work this paper cites.
Reading and the mental lexicon
Marcus Taft. 1991 · 1991
Earlier work this paper cites.
Units of representation for derived words in the lexicon
Cristina Burani and Alessandro Laudanna. 1992 · 1992
Earlier work this paper cites.
Word space
Hinrich Schütze. 1992 · 1992
Earlier work this paper cites.
A new algorithm for data compression
Philip Gage. 1994 · 1994
Earlier work this paper cites.
Rule-less morphology at the phonology-lexicon interface
Joseph P. Stemberger. 1994 · 1994
Earlier work this paper cites.
Interactive-activation as a framework for understanding morphological processing
Marcus Taft. 1994 · 1994
Earlier work this paper cites.
Regular morphology and the lexicon
Joan Bybee. 1995 · 1995
Earlier work this paper cites.
Distributional properties of derivational affixes: Implications for processing
Alessandro Laudanna and Cristina Burani. 1995 · 1995
Earlier work this paper cites.
Modeling morphological processing
Robert Schreuder and R. Harald Baayen. 1995 · 1995
Earlier work this paper cites.
Singulars and plurals in Dutch: Evidence for a parallel dual-route model
R. Harald Baayen, Ton Dijkstra, and Robert Schreuder. 1997 · 1997
Earlier work this paper cites.
Frequency effects and the representational status of regular inflections
Maria Alegre and Peter Gordon. 1999 · 1999
Earlier work this paper cites.
Morphology in the mental lexicon: A computational model for visual word recognition
R. Harald Baayen, Robert Schreuder, and Richard Sproat. 2000 · 2000
Earlier work this paper cites.
On the role of derivational affixes in recognizing complex words: Evidence from masked priming
Hélène Giraudo and Jonathan Grainger. 2003 · 2003
Earlier work this paper cites.
Word-formation in English
Ingo Plag. 2003 · 2003
Earlier work this paper cites.
A systematic analysis of morphological content in BERT models for multiple languages
Daniel Edmiston. 2020 · 2004
Earlier work this paper cites.
The processing of singular and plural nouns in french and english
Boris New, Marc Brysbaert, Juan Segui, Ludovic Ferrand, and Kathleen Rastle. 2004 · 2004
Earlier work this paper cites.
The broth in my brother’s brothel: Morpho-orthographic segmentation in visual word recognition
Kathleen Rastle, Matthew H. Davis, and Boris New. 2004 · 2004
Earlier work this paper cites.
Morphological decomposition and the reverse base frequency effect
Marcus Taft. 2004 · 2004
Earlier work this paper cites.
Morphological dynamics in compound processing
Victor Kuperman, Raymond Bertram, and R. Harald Baayen. 2008 · 2008
Cited alongside, same era.
Morphological decomposition based on the analysis of orthography
Kathleen Rastle and Matthew H. Davis. 2008 · 2008
Cited alongside, same era.
Reading of polymorphemic Dutch compounds: Towards a multiple route model of lexical processing
Victor Kuperman, Robert Schreuder, Raymond Bertram, and R. Harald Baayen. 2009 · 2009
Cited alongside, same era.
Distant supervision for relation extraction without labeled data
Mike Mintz, Steven Bills, Rion Snow, and Dan Jurafsky. 2009 · 2009
Cited alongside, same era.
Understanding morphology
Martin Haspelmath and Andrea D. Sims. 2010 · 2010
Cited alongside, same era.
Lexical normalisation of short text messages: Makn sens a #twitter
Bo Han and Timothy Baldwin. 2011 · 2011
Joint semantic synthesis and morphological analysis of the derived word
Ryan Cotterell and Hinrich Schütze. 2018 · 2018
Later among the works it cites.
A distributional and orthographic aggregation model for English derivational morphology
Daniel Deutsch, John Hewitt, and Dan Roth. 2018 · 2018
Later among the works it cites.
Gendered associations of english morphology
Jeremy M. Needle and Janet B. Pierrehumbert. 2018 · 2018
Later among the works it cites.
Incorporating subword information into matrix factorization word embeddings
Alexandre Salle and Aline Villavicencio. 2018 · 2018
Later among the works it cites.
BERT: Pre-training of deep bidirectional transformers for language understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019 · 2019
Later among the works it cites.
Show your work: Improved reporting of experimental results
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Enhancing deep neural networks with morphological information
Matej Klemen, Luka Krsnik, and Marko Robnik-Šikonja. 2020 · 2011
Cited alongside, same era.
Japanese and Korean voice search
Mike Schuster and Kaisuke Nakajima. 2012 · 2012
Cited alongside, same era.
Compositional-ly derived representations of morphologically complex words in distributional semantics
Angeliki Lazaridou, Marco Marelli, Roberto Zamparelli, and Marco Baroni. 2013 · 2013
Cited alongside, same era.
Better word representations with recursive neural networks for morphology
Minh-Thang Luong, Richard Socher, and Christopher D. Manning. 2013 · 2013
Cited alongside, same era.
Compositional morphology for word representations and language modelling
Jan A. Botha and Phil Blunsom. 2014 · 2014
Cited alongside, same era.
Delineating derivation and inflection
Pius ten Hacken. 2014 · 2014
Cited alongside, same era.
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, and Noah A. Smith. 2019 · 2019
Later among the works it cites.
How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings
Kawin Ethayarajh. 2019 · 2019
Later among the works it cites.
Sequence tagging with contextual and non-contextual subword representations: A multilingual evaluation
Benjamin Heinzerling and Michael Strube. 2019 · 2019
Later among the works it cites.
A structural probe for finding syntax in word representations
John Hewitt and Christopher D. Manning. 2019 · 2019
Later among the works it cites.
What does BERT learn about the structure of language?
Ganesh Jawahar, Benoit Sagot, and Djamé Seddah. 2019 · 2019
Later among the works it cites.
Morphological processing in the brain: The good (inflection), the bad (derivation) and the ugly (compounding)
Alina Leminen, Eva Smolka, Jon Duñabeitia, and Christos Pliatsikas. 2019 · 2019
Later among the works it cites.
Justifying recommendations using distantly-labeled reviews and fined-grained aspects
Jianmo Ni, Jiacheng Li, and Julian McAuley. 2019 · 2019
Later among the works it cites.
Language models are unsupervised multitask learners
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019 · 2019
Later among the works it cites.
Some sources of apparent gaps in derivational paradigms
Gregory Stump. 2019 · 2019
Later among the works it cites.
XLNet: Generalized autoregressive pretraining for language understanding
Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. 2019 · 2019
Later among the works it cites.
Byte pair encoding is suboptimal for language model pretraining
Kaj Bostrom and Greg Durrett. 2020 · 2020
Later among the works it cites.
Efficient intent detection with dual sentence encoders
Iñigo Casanueva, Tadas Temčinas, Daniela Gerz, Matthew Henderson, and Ivan Vulić. 2020 · 2020
Later among the works it cites.
Emerging trends: Subwords, seriously?
Kenneth Church. 2020 · 2020
Later among the works it cites.
ELECTRA: Pre-training text encoders as discriminators rather than generators
Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020 · 2020
Later among the works it cites.
What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models
Allyson Ettinger. 2020 · 2020
Later among the works it cites.
DagoBERT: Generating derivational morphology with a pretrained language model
Valentin Hofmann, Janet B. Pierrehumbert, and Hinrich Schütze. 2020a · 2020
Later among the works it cites.
Finnish ASR with deep transformer models
Abhilash Jain, Aku Rouhe, Stig-Arne Grönroos, and Mikko Kurimo. 2020 · 2020
Later among the works it cites.
Negated and misprimed probes for pretrained language models: Birds can talk, but cannot fly
Nora Kassner and Hinrich Schütze. 2020 · 2020
Later among the works it cites.
CharBERT: Character-aware pre-trained language model
Wentao Ma, Yiming Cui, Chenglei Si, Ting Liu, Shijin Wang, and Guoping Hu. 2020 · 2020
Later among the works it cites.
CamemBERT: A tasty French language model
Louis Martin, Benjamin Muller, Pedro J. Suárez, Yoann Dupont, Laurent Romary, de la Clergerie, Éric V., Djamé Seddah, and Benoit Sagot. 2020 · 2020
Later among the works it cites.
Will it unblend?
Yuval Pinter, Cassandra L. Jacobs, and Jacob Eisenstein. 2020 · 2020
Later among the works it cites.
Morphological convergence as on-line lexical analogy
Péter Rácz, Clay Beckner, Jennifer Hay, and Janet B. Pierrehumbert. 2020 · 2020
Later among the works it cites.
Exploring the limits of transfer learning with a unified text-to-text transformer
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020 · 2020
Later among the works it cites.
Tired of topic models? Clusters of pretrained word embeddings make for fast and good topics too!
Suzanna Sia, Ayush Dalmia, and Sabrina J. Mielke. 2020 · 2020
Later among the works it cites.
Mind your inflections! Improving NLP for non-standard Englishes with base-inflection encoding
Samson Tan, Shafiq Joty, Lav R. Varshney, and Min-Yen Kan. 2020 · 2020
Later among the works it cites.
Probing pretrained language models for lexical semantics
Ivan Vulić, Edoardo M. Ponti, Robert Litschko, Goran Glavaš, and Anna Korhonen. 2020 · 2020
Later among the works it cites.