Page: 1 2 3 4 5 6 7 8 9 10... 992
101 |
How Well Do LSTM Language Models Learn Filler-gap Dependencies?
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
102 |
A split-gesture, competitive, coupled oscillator model of syllable structure predicts the emergence of edge gemination and degemination
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
103 |
Linguistic Complexity and Planning Effects on Word Duration in Hindi Read Aloud Speech
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
104 |
Learning Argument Structures with Recurrent Neural Network Grammars
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
105 |
MaxEnt Learners are Biased Against Giving Probability to Harmonically Bounded Candidates
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
106 |
Evaluating Structural Economy Claims in Relative Clause Attachment
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
107 |
A Model Theoretic Perspective on Phonological Feature Systems
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
108 |
Representing Multiple Dependencies in Prosodic Structures
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
109 |
Incremental Acquisition of a Minimalist Grammar using an SMT-Solver
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
110 |
Concurrent hidden structure & grammar learning
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
111 |
Can language models capture syntactic associations without surface cues? A case study of reflexive anaphor licensing in English control constructions
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
112 |
Universal Dependencies and Semantics for English and Hebrew Child-directed Speech
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
113 |
Learning Input Strictly Local Functions: Comparing Approaches with Catalan Adjectives
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
114 |
Learning Constraints on Wh-Dependencies by Learning How to Efficiently Represent Wh-Dependencies: A Developmental Modeling Investigation With Fragment Grammars
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
115 |
Typological Implications of Tier-Based Strictly Local Movement
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
116 |
Parsing Early Modern English for Linguistic Search
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
117 |
When Classifying Arguments, BERT Doesn't Care About Word Order. Except When It Matters
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
Abstract:
We probe nouns in BERT contextual embedding space for grammatical role (subject vs. object of a clause), and examine how probing results vary between prototypical examples, where the role matches what we would expect from seeing that word in the context, and non-prototypical examples, where the role is mostly imparted by the context. In this way, engage with the contrast that has arisen in the literature, between studies that show contextual models as grammatically sensitive, and others that show that these models are robust to changes in word order. Our experiments yield three results: 1) Grammatical role is recovered in later layers for difficult non-prototypical cases, while prototypical cases are accurate without many layers of context 2) When we switch the subject and the object of a sentence around (eg, The chef cut the onion, The onion cut the chef), we see that the same word (eg, onion) can be fluently identified as both a subject and an object 3) Subjecthood probing breaks if we ablate local word order by shuffle words locally and break grammaticality.
|
|
Keyword:
BERT; Computational Linguistics; Contextual embeddings; grammatical role; prototype; subjecthood; verb arguments; word order
|
|
URL: https://scholarworks.umass.edu/scil/vol5/iss1/18 https://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1244&context=scil
|
|
BASE
|
|
Hide details
|
|
118 |
Remodelling complement coercion interpretation
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
119 |
Inferring Inferences: Relational Propositions for Argument Mining
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
120 |
ANLIzing the Adversarial Natural Language Inference Dataset
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9 10... 992
|
|