Can Transformers Process Recursive Nested Constructions, Like Humans? (2022.coling-1)
Copied to clipboard
| Challenge: | A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance level on embedded dependencies within nested constructions. |
| Approach: | They evaluated recursive processing in recurrent neural language models and found that Transformers perform below chance level on embedded dependencies within nested constructions. |
| Outcome: | The proposed models perform below chance level on embedded dependencies within nested constructions, compared to humans. |
Similar Papers
On the Ability and Limitations of Transformers to Recognize Formal Languages (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on LSTMs have not revealed their ability to model syntactic properties. |
| Approach: | They propose to build a Transformers model for a subclass of counter languages and find that their learning mechanism strongly correlates with their construction. |
| Outcome: | The proposed model generalizes well on counter languages and its learned mechanism correlates with it. |
Can Transformers Learn n-gram Language Models? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing work has tested transformers' ability to represent formal languages, but language models are not classifiers of strings but rather distributions over them. |
| Approach: | They relate transformers' ability to learn random n-gram language models to ngram language model (LM) they find add- smoothing outperforms transformers on the former, while transformers perform better on the latter . |
| Outcome: | The proposed models outperform classical methods designed to learn n-gram LMs, while transformers perform better on the latter. |
Hierarchical Transformers Are More Efficient Language Models (2022.findings-naacl)
Copied to clipboard
Piotr Nawrot, Szymon Tworkowski, Michał Tyrolski, Lukasz Kaiser, Yuhuai Wu, Christian Szegedy, Henryk Michalewski
| Challenge: | Transformers are impressive but inefficient and costly, which limits their applications and accessibility. |
| Approach: | They first use different ways to downsample and upsamplify activations in Transformers to make them hierarchical. |
| Outcome: | The proposed model outperforms Transformers on the ImageNet32 and enwik8 benchmarks. |
Analyzing the Inner Workings of Transformers in Compositional Generalization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on compositional generalization abilities of neural models have focused on benchmarks, but the results do not reflect the underlying competence of the model. |
| Approach: | They propose to find an existing subnetwork that contributes to the generalization performance and perform causal analyses on how the model utilizes syntactic features. |
| Outcome: | The proposed model relies on syntactic features but the subnetwork with better generalization performance relies mainly on a non-compositional algorithm . |
Can the Transformer Learn Nested Recursion with Symbol Masking? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on self-attention models show they can generalise to context-free languages . |
| Approach: | They use encoder-only models to train to generalise nested symbols . they find that the predictions made correspond to a simple parenthesis counting strategy . |
| Outcome: | The proposed model can generalise to nested structures at higher nesting depth and with a push-down automaton. |
Developmental Negation Processing in Transformer Language Models (2022.acl-short)
Copied to clipboard
| Challenge: | Negation is an important construct in language for reasoning over the truth of propositions, garnering interest from philosophy (Horn, 1989) and psycholinguistics (Zwaan, 2012). |
| Approach: | They propose to frame a natural language inference task as a problem and examine how well transformers can process negation categories. |
| Outcome: | The proposed models perform better on certain categories, suggesting clear differences in how they are processed. |
Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent work attempts to apply incremental processing to NLUs but this is computationally expensive and does not scale efficiently for long sequences. |
| Approach: | They propose to apply Transformers incrementally via restart-incrementality by repeatedly feeding, to an unchanged model, increasingly longer input prefixes to produce partial outputs. |
| Outcome: | The proposed model has better incremental performance and faster inference speed compared to the standard Transformer and LT with restart-incrementality, at the cost of part of the non-incremental quality. |
Can Transformers Reason in Fragments of Natural Language? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on natural language inference has identified two strands of research . |
| Approach: | They investigate whether neural networks have acquired logical principles from natural language . they use transformer-based models to detect valid inferences in controlled fragments of natural language. |
| Outcome: | The proposed model overfits to superficial patterns in the data rather than acquiring the logical principles governing reasoning in natural language fragments. |
Do Transformers Need Deep Long-Range Memory? (2020.acl-main)
Copied to clipboard
| Challenge: | Deep attention models have advanced the modelling of sequential data across many domains. |
| Approach: | They propose to use a Transformer augmented with a long-range memory to model sequential data across many domains. |
| Outcome: | The Transformer-XL has a long-range memory at every layer of the network, rendering its state thousands of times larger than RNN predecessors. |
Do Transformers Parse while Predicting the Masked Word? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that pre-trained language models encode linguistic structures like parse trees while being trained unsupervised. |
| Approach: | They propose to train pre-trained language models to encode linguistic structures like parse trees while unsupervised. |
| Outcome: | The proposed model performs optimally for masked language modeling loss on the English PCFG. |