RNN Simulations of Grammaticality Judgments on Long-distance Dependencies (C18-1)
Copied to clipboard
| Challenge: | LSTM networks can detect linguistic structures which are ungrammatical due to extraction violations, but are sensitive to linguistic processing factors. |
| Approach: | They propose to use LSTM networks to detect ungrammatical sentences by detecting extra arguments and subject-relative clause island violations. |
| Outcome: | The proposed model can correctly classify (un)grammatical sentences, in certain conditions, but is sensitive to linguistic processing factors and unable to induce a more abstract notion of grammaticality. |
Similar Papers
Overestimation of Syntactic Representation in Neural Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Several testing methodologies have been developed to probe models’ syntactic representations. |
| Approach: | They propose a method to determine syntactic structure by training a model on strings generated according to a template and testing its ability to distinguish between similar ones with different syntax. |
| Outcome: | The proposed method reproduces positive results with two non-syntactic baseline language models: an n-gram model and an LSTM model trained on scrambled inputs. |
How much complexity does an RNN architecture need to learn syntax-sensitive dependencies? (2020.acl-srw)
Copied to clipboard
| Challenge: | Long-term memory (LSTM) networks are capable of encapsulating long-range dependencies . but simple recurrent networks (SRNs) have been less successful at capturing long-term dependencies and loci of grammatical errors in an unsupervised setting. |
| Approach: | They propose a new architecture that incorporates the decaying nature of neuronal activations and models the excitatory and inhibitory connections in a population of neurons. |
| Outcome: | The proposed architecture shows competitive performance relative to LSTMs on subject-verb agreement, sentence grammaticality, and language modeling tasks. |
On Efficiently Representing Regular Languages as RNNs (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent work by Hewitt et al. (2020) provides an interpretation of the empirical success of recurrent neural networks (RNNs) as language models (LMs). |
| Approach: | They generalize their construction and show that RNNs can efficiently represent a larger class of LMs than previously claimed. |
| Outcome: | The results suggest that RNNs can represent a larger class of LMs than previously claimed . |
Neural language models as psycholinguistic subjects: Representations of syntactic state (N19-1)
Copied to clipboard
| Challenge: | a recent study examines the extent to which neural network language models reflect incremental representations of syntactic state . we examine neural network model behavior on sentences chosen to probe specific aspects of the learned representations . |
| Approach: | They employ experimental methodologies developed in psycholinguistics to study syntactic representation in the human mind. |
| Outcome: | The proposed models are trained on large datasets and only sensitive to subtle cues . the results raise questions about the accuracy of the models and their performance . |
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages (N19-1)
Copied to clipboard
| Challenge: | Recent studies have identified both strengths and limitations of recurrent neural networks (RNNs) in applied natural language processing tasks. |
| Approach: | They propose a paradigm that addresses typological differences between languages . they create synthetic versions of English and train them to predict agreement features . |
| Outcome: | The proposed model improves on predicting agreement with subject and object, suggesting that RNNs have a recency bias. |
Structural Supervision Improves Learning of Non-Local Grammatical Dependencies (N19-1)
Copied to clipboard
| Challenge: | State-of-the-art LSTM language models learn sequential contingencies with some success . LS models fail to learn other non-local grammatical dependencies, however . |
| Approach: | They compare LSTM language models with RNNGs to examine grammatical dependencies . they find that hierarchical supervision improves learning of non-local dependencies. |
| Outcome: | The proposed model outperforms the existing model on non-local dependencies and learns many of the Island Constraints on the filler-gap dependency. |
Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment (2020.acl-main)
Copied to clipboard
| Challenge: | Language modeling is widely used as pretraining for many tasks involving language processing. |
| Approach: | They extend a standard approach to evaluating language models to cases of valid interpretations . they compare model performance in English and Spanish to show that non-linguistic bias overlaps with syntactic structure in English but not Spanish. |
| Outcome: | The proposed model performance in English and Spanish shows that non-linguistic bias overlaps with syntactic structure in English but not in Spanish. |
Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject. |
| Approach: | They propose to take an alternative look at these results by studying whether neural networks are able to build an abstract sentence representation rather than capture surface statistical regularities. |
| Outcome: | The proposed model can achieve high accuracy on the long-range French object-verb agreement, indicating a possible flaw in the model's syntactic ability. |
Priorless Recurrent Networks Learn Curiously (2020.coling-main)
Copied to clipboard
| Challenge: | a recent study shows domain-general recurrent neural networks reproduce human language behaviours . a lack of a unified concept of number agreement between these processes is a limitation of the model . |
| Approach: | They propose to use domain-general recurrent neural networks without explicit linguistic inductive biases to reproduce human language behaviours. |
| Outcome: | The proposed model can learn number agreement within unnatural sentences, the authors show . they show that the model has an effective understanding of singular versus plural for individual sentences . |
Predicting Reference: What do Language Models Learn about Discourse Models? (2020.emnlp-main)
Copied to clipboard
| Challenge: | a growing literature that probes neural language models to assess their latent acquisition of grammatical knowledge has not investigated their acquisition of discourse modeling ability. |
| Approach: | They draw on a psycholinguistic literature that has established how different contexts affect referential biases concerning who is likely to be referred to next. |
| Outcome: | The proposed models do not resemble human language users, the authors show . their models capture the linguistic knowledge required to perform discourse modeling . |