Grammaticality, Acceptability, and Probability: A Probabilistic View of Linguistic Knowledge

By Jey Han Lau, Alexander Clark, Shalom Lappin. 2017

241 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Natural Language Processing

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

In Cognitive Neuroscience

In Natural Language Processing

Citations in the corpus

Neural Network Acceptability Judgments (2018, methodology): “ls use word embeddings or hidden states from the LM as input. (ii) The LM generates fake data for the real/fake task. (iii) The LM is an integral part of our implementation of the method proposed by (Lau et al., 2016). We train the LM on the 100 million-token British National Corpus (BNC). It learns”
Targeted Syntactic Evaluation of Language Models (2018, methodology): “Following previous work (Lau et al., 2017; Linzen et al., 2016; Gulordava et al., 2018), we suggest that given two sentences that differ minimally from each other, one of which is grammatical and the other which is not, it is desirable for the model to assign a higher probability to the grammatical ”
Masked Language Model Scoring (2019, methodology): “Its graded form is well-proxied by neural language model scores (logPLM) once length and lexical frequency are accounted for (Lau et al., 2017).”
BLiMP: The Benchmark of Linguistic Minimal Pairs for English (2019, background): “Corpora of sentences and their grammaticality are collected for this purpose in a number of studies (Heilman et al., 2014; Lau et al., 2017; Warstadt et al., 2019b).”
What do RNN Language Models Learn about Filler–Gap Dependencies? (2018, methodology): “…method can indicate whether there is a link between ﬁllers and gaps, the relationship between language model probability and grammaticality is complex (Lau et al., 2017) and interpreting our patterns in terms of grammaticality judgments would require auxiliary assumptions that we don’t pursue here.”
Cross-Linguistic Syntactic Evaluation of Word Prediction Models (2020, background): “In computational linguistics, acceptability judgments have been used extensively to assess the grammatical abilities of LMs (Linzen et al., 2016; Lau et al., 2017).”
SNAP judgments: A small N acceptability paradigm (SNAP) for linguistic acceptability judgments (2016, methodology): “…to further discussions of the weaknesses of the informal method (e.g. Arppe & Järvikivi 2007, Cowart 1997, Featherston 2005, Gibson & Fedorenko 2010, 2013, Gibson et al. 2013, Gross & Culbertson 2011, Lau et al. 2017, Linzen & Oseki 2015, Schütze 1996, Sorace & Keller 2005, Wasow & Arnold 2005).”
A Systematic Assessment of Syntactic Generalization in Neural Language Models (2020, background): “Alternatively, a language model can be evaluated on its ability to make human-like generalizations for speciﬁc syntactic phenomena (Linzen et al., 2016; Lau et al., 2017; Gulordava et al., 2018).”
Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation (2019, background): “Lau et al (2016) take an unsupervised, language modeling approach to predicting grammaticality.”
BLiMP: A Benchmark of Linguistic Minimal Pairs for English (2020, background): “tences and their grammaticality are collected for this purpose in a number of computational studies on grammaticality judgment (Heilman et al., 2014; Lau et al., 2017; Warstadt et al., 2019b).”
Linguistic Analysis of Pretrained Sentence Encoders with Acceptability Judgments (2019, methodology): “viously: Lawrence et al. (2000) train RNNs to do acceptability classification over sequences of POS tags corresponding to example sentences from a syntax textbook.”
Grammatical Analysis of Pretrained Sentence Encoders with Acceptability Judgments (2019, background): “Lau et al. (2016) Jey Han Lau, Alexander Clark, and Shalom Lappin.”