| Challenge: | a new study shows that neural models implicitly encode linguistic features . but no research shows how these encodings arise as the models are trained . |
| Approach: | They propose a method that compares learning across time and across models using annotated data. |
| Outcome: | The proposed method compares learned representations across time and across models without evaluation on annotated data. |
Similar Papers
The Grammar-Learning Trajectories of Neural Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | In this paper, we show that neural language models with different initialization, architecture, and training data acquire linguistic phenomena in a similar order, despite their different end performance. |
| Approach: | They propose to use mutual inductive bias to study linguistic representations implicit in NLMs. |
| Outcome: | The proposed approach shows that NLMs with different initialization, architecture, and training data acquire linguistic phenomena in a similar order, despite their different end performance. |
Implicit Representations of Meaning in Neural Language Models (2021.acl-long)
Copied to clipboard
| Challenge: | Neural language models (NLMs) encode lexical relations and syntactic structure, but their effectiveness is still unclear. |
| Approach: | They propose to use text as a model to model entities and situations as they evolve throughout a discourse. |
| Outcome: | The proposed models have functional similarities to linguistic models of dynamic semantics and can be learned with only text as training data. |
Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models of language understanding are based on explicit representations of hierarchical structure, but there are good reasons to doubt that they can be said to understand language in any meaningful way. |
| Approach: | They examine whether syntactic and semantic graph representations can complement and improve neural language modeling. |
| Outcome: | The proposed model outperforms pretrained models on English WSJ in perplexity and other metrics. |
Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Contemporary advances in NLP are built on the representational power of latent embedding spaces learned by self-supervised language models (LMs). |
| Approach: | They use a new information theoretic probing suite to analyze representational subspaces in language models. |
| Outcome: | The proposed approach compared performance of nine tasks across 2M pre-training steps and five seeds. |
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. |
Analyzing Individual Neurons in Pre-trained Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows that deep NLP models capture linguistic knowledge but little attention is paid to individual neurons. |
| Approach: | They conduct a neuron-level analysis of pre-trained neural language models to determine linguistic properties. |
| Outcome: | The proposed model is more localized and disjoint when predicting properties than BERT and others. |
A Closer Look at Parameter Contributions When Training Neural Language and Translation Models (2022.coling-1)
Copied to clipboard
| Challenge: | Neural models and Transformers have been used for almost every NLP task . however, the intrinsic dynamics of the training procedure have not been studied in depth for highly complex network architectures. |
| Approach: | They analyze the learning dynamics of neural language and translation models using Loss Change Allocation indicator . they use a standard Transformer architecture to train a model with three learning objectives . |
| Outcome: | The proposed model is based on a standard model that is used for training tasks. |
Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models learn non-trivial abstractions during pretraining, but it is not well understood when and how these specific linguistic abilities emerge. |
| Approach: | They propose a method to track the evolution of linguistic features during pretraining by using sparse crosscoders to discover and align features across model checkpoints. |
| Outcome: | The proposed approach can detect features emergence, maintenance, and discontinuation during training stages. |
A Systematic Assessment of Syntactic Generalization in Neural Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on syntactic knowledge models has not provided a clear picture of the properties required to produce proper syntaktic generalizations. |
| Approach: | They propose to evaluate syntactic knowledge of language models by varying model architectures . they find substantial differences in syntaktic generalization performance by model architecture . |
| Outcome: | The proposed model architectures outperform other architectures on a set of 34 English-language syntactic test suites. |
A Survey on Dynamic Neural Networks for Natural Language Processing (2023.findings-eacl)
Copied to clipboard
| Challenge: | Dynamic neural networks can scale up pretrainable models with sub-linear increases in computation and time. |
| Approach: | They summarize the progress of three types of dynamic neural networks in NLP . skimming, mixtures of experts, and early exit are among the most popular . |
| Outcome: | The proposed models can scale up with sub-linear increases in computation and time . skimming, mixture of experts, and early exit are the most popular approaches . |