Challenge: Pretrained neural models lack sensitivity to word order on controlled challenge sets . augmentation methods that improve accuracy on standard training sets may be a problem .
Approach: They propose to augment standard training sets with syntactically informative examples by applying syntastic transformations to sentences from the MNLI corpus.
Outcome: The proposed method improved BERT’s accuracy on controlled examples that diagnose sensitivity to word order from 0.28 to 0.73 without affecting performance on the MNLI test set.

Similar Papers

Simple but Challenging: Natural Language Inference Models Fail on Simple Sentences (2022.findings-emnlp)

Copied to clipboard

Challenge: Natural language inference (NLI) tasks are difficult to perform on large datasets . a small number of simple sentences can improve model performance, authors say .
Approach: They propose to use syntactically simple sentences to test the inference ability of NLI models.
Outcome: The proposed set of simple sentences shows that the models fine-tuned on MNLI and SNLI perform poorly on Simple Pair.
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models (2021.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that powerful pre-trained language models can be fooled by small perturbations or intentional attacks.
Approach: They propose a framework for fine-tuning PLMs using a masked language model and Gaussian noise to augment semantically relevant examples with sufficient diversity.
Outcome: The proposed framework improves the robustness of pre-trained language models and alleviates performance degradation under adversarial attacks.
How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases (2023.acl-long)

Copied to clipboard

Challenge: a recent study found that pre-training can teach language models to rely on hierarchical syntactic features . aaron ramirez: we find that pretraining on simpler language induces a hierarchic bias .
Approach: They find that pre-training can teach language models to rely on hierarchical syntactic features . authors: this suggests that in cognitively plausible language acquisition settings, models may be more data-efficient .
Outcome: a recent study shows that pre-training can teach language models to rely on hierarchical features . the findings suggest that in plausible language acquisition settings, language models may be more data-efficient than previously thought .
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings (2021.findings-acl)

Copied to clipboard

Challenge: Prior art aims to uncover meaningful properties within model representations, but it is unclear how faithfully such probes portray information that the models actually use.
Approach: They propose a technique for generating counterfactual embeddings within models . they produce evidence that some models use a tree-distancelike representation of syntax .
Outcome: The proposed technique produces evidence that some models use tree-distancelike representations of syntax in downstream prediction tasks.
Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models (2025.naacl-short)

Copied to clipboard

Challenge: Existing studies have used class-specific fine-tuned large language models to generate hypotheses and assign pseudo-labels but discarded many LLM-constructed samples to ensure the quality.
Approach: They propose to leverage LLM-constructed samples by injecting the moments of labeled samples during training to properly adjust the level of noise.
Outcome: The proposed method outperforms strong baselines on multiple NLI datasets in low-resource settings.
Exploring Data Augmentation for Code Generation Tasks (2023.findings-eacl)

Copied to clipboard

Challenge: Recent advances in natural language processing have impacted how models are trained for programming language tasks.
Approach: They propose to use augmentation methods that yield consistent improvements in code translation and summarization by up to 6.9% and 7.5% respectively.
Outcome: The proposed methods improve translation and summarization by 6.9% and 7.5% respectively.
Towards preserving word order importance through Forced Invalidation (2023.eacl-main)

Copied to clipboard

Challenge: Recent studies show pre-trained language models are insensitive to word order . performance on NLU tasks remains unchanged even after permuting the word .
Approach: They propose a simple approach called Forced Invalidation to force the model to identify permuted sequences as invalid samples.
Outcome: The proposed approach significantly improves the sensitivity of the models to word order on English NLU and QA tasks over BERT-based and attention-based models over word embeddings.
Handling Syntactic Divergence in Low-resource Machine Translation (D19-1)

Copied to clipboard

Challenge: Existing approaches to neural machine translation (NMT) are dependent on limited parallel data, and can be difficult to use for many language pairs.
Approach: They propose a method where target-language sentences are re-ordered to match the order of the source and used as an additional source of training-time supervision.
Outcome: The proposed method improves on simulated low-resource Japanese-to-English and real low-demand Uyghur-to English scenarios.
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level (2021.findings-acl)

Copied to clipboard

Challenge: Larger models have higher out-of-distribution robustness, while smaller models have lower accuracy on rare subgroups.
Approach: They develop statistically rigorous methods to investigate whether large models are better on every instance . they find that individual predictions are highly sensitive to noise in the randomness in training .
Outcome: The proposed model is worse than BERT-MINI on 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%.
Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge (2022.naacl-main)

Copied to clipboard

Challenge: Existing evidence suggests that pre-trained Transformers encode commonsense knowledge . however, the extent to which this knowledge is acquired is unclear .
Approach: They inject verbalized knowledge into pre-training minibatches and evaluate generalization . they find generalization does not improve over the course of pre- training from scratch .
Outcome: The proposed model generalizes to supported inferences after pre-training on the injected knowledge.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations