Papers with Neural networks
Representations of Meaning in Neural Networks for NLP: a Thesis Proposal (2021.naacl-srw)
Copied to clipboard
| Challenge: | Neural networks are the state-of-the-art method of machine learning for many problems in NLP. |
| Approach: | They propose to examine the distribution of meaning in the vector space representation of words in neural networks trained for NLP tasks. |
| Outcome: | The proposed method would be compatible with distributional hypothesis, structuralism, and semantic holism. |
Domain Differential Adaptation for Neural Machine Translation (D19-56)
Copied to clipboard
| Challenge: | Neural networks are data hungry and domain sensitive, so it is difficult to obtain labeled data for every domain. |
| Approach: | They propose a framework for domain adaptation where we model the difference between domains instead of smoothing over them. |
| Outcome: | The proposed framework improves on domain adaptation in multiple experimental settings. |
Robustness Evaluation of Text Classification Models Using Mathematical Optimization and Its Application to Adversarial Training (2022.findings-aacl)
Copied to clipboard
| Challenge: | Neural networks are vulnerable to adversarial examples due to slightly perturbed input data. |
| Approach: | They propose a method that evaluates the robustness of text classification models by an optimization problem that identifies a minimum synonym swap that changes the classification result. |
| Outcome: | The proposed method achieves high scores in human evaluations of grammatical correctness and semantic similarity for an IMDb dataset and implements adversarial training with the IMD and SST2 datasets. |
Location Attention for Extrapolation to Longer Sequences (2020.acl-main)
Copied to clipboard
| Challenge: | Neural networks are surprisingly good at interpolating, but they are often unable to extrapolate patterns beyond the seen data. |
| Approach: | They propose to use a special type of extrapolation for natural language processing to generalize to sequences that are longer than the training ones. |
| Outcome: | The proposed model is more likely to extrapolate than models with common attention mechanisms. |
An Analysis under a Unified Formulation of Learning Algorithms with Output Constraints (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing work on NN models with output constraints has not been able to categorize them in a unified manner. |
| Approach: | They propose new algorithms to integrate the information of main task and constraint injection . they use the H-score as a metric for considering main task metric and constrain infringement simultaneously . |
| Outcome: | The proposed algorithms integrate the information of main task and constraint injection, inspired by continual-learning algorithms. |
A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Neural networks are at the center of a debate about human behavior in inflectional morphology. |
| Approach: | They measure correlation between human judgments and neural network probabilities for unknown word inflections. |
| Outcome: | The proposed model for morphological inflections correlates best with human wug ratings, but not with humans. |
Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together (N19-1)
Copied to clipboard
| Challenge: | Neural networks equipped with self-attention have parallelizable computation and the ability to capture both long-range and local dependencies. |
| Approach: | They propose a novel attention mechanism called "Multi-mask Tensorized Self-Attention" it captures pairwise and global dependencies by a compatibility function composed of dot-product and additive attentions . |
| Outcome: | The proposed model outperforms CNN-/RNN-/attention-based models on nine NLP benchmarks with compelling memory- and time-efficiency. |
Exploring Data Augmentation in Neural DRS-to-Text Generation (2024.eacl-long)
Copied to clipboard
| Challenge: | Neural networks are notoriously data-hungry, resulting in ungrammatical texts . data augmentation requires a specific design for a structurally rich input format . |
| Approach: | They propose to selectively augment a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns. |
| Outcome: | The proposed approach selectively augments a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns. |
Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Neural networks tend to gradually forget the previously learned knowledge when learning multiple tasks sequentially from dynamic data distributions. |
| Approach: | They propose a method that iteratively provides complementary knowledge to student models by dynamically updating teacher models trained on specific data orders. |
| Outcome: | The proposed method improves on multiple machine translation tasks and improves performance over baseline systems. |
Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training (2022.findings-acl)
Copied to clipboard
| Challenge: | Neural networks are used for various NLP tasks, but their complexity makes them difficult to interpret. |
| Approach: | They propose a framework to mitigate the model pathology and obtain more interpretable models by using contrastive learning and saliency-based samples augmentation to calibrate the sentences representation. |
| Outcome: | The proposed framework can mitigate the model pathology and generate more interpretable models while keeping the model performance. |
Semantic Training Signals Promote Hierarchical Syntactic Generalization in Transformers (2024.emnlp-main)
Copied to clipboard
| Challenge: | Neural networks without hierarchical biases struggle to learn linguistic rules that come naturally to humans . et al., 2018: Transformers trained on form and meaning favor hierarchically generalization more than those trained on forms alone. |
| Approach: | They examine whether neural networks without hierarchical biases can generalize more like humans . they find that Transformers trained on form and meaning favor hierarchic generalization . |
| Outcome: | The proposed neural networks perform better on syntactic evaluations when trained on form and meaning compared to those trained on forms alone. |
Meta-Learning to Compositionally Generalize (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that neural networks struggle with compositional generalization . prior work asserts that there are fundamental differences between cognitive and connectionist architectures that make compositional globalization unlikely. |
| Approach: | They propose a meta-learning augmented version of supervised learning that optimizes for out-of-distribution generalization. |
| Outcome: | The proposed model improves generalization performance on COGS and SCAN datasets. |
Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks (2020.emnlp-main)
Copied to clipboard
| Challenge: | Neural networks typically need large labeled data for training and are not easily interpretable. |
| Approach: | They propose a type of recurrent neural networks that combine neural networks and regular expression rules. |
| Outcome: | The proposed recurrent neural networks outperform previous neural approaches in low- and zero-shot scenarios and remain very competitive in rich-resource settings. |
DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural networks (NNs) are becoming deeper and more complex, making them difficult to understand and interpret. |
| Approach: | They propose a method to distill knowledge concurrently from any neural network architecture for text classification. |
| Outcome: | The proposed method achieves better performance than the target black-box and provides better explanations than existing techniques. |
Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels (2020.coling-main)
Copied to clipboard
| Challenge: | Neural networks can capture expressive language features, but insights into the link between words and sentences are difficult to acquire automatically. |
| Approach: | They propose a deep neural network architecture that explicitly wires lower and higher linguistic components and evaluate its ability to perform the same task at different hierarchical levels. |
| Outcome: | The proposed model outperforms equivalent models that are not incentivized towards compositional representations. |
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation (D19-1)
Copied to clipboard
Po-Sen Huang, Robert Stanforth, Johannes Welbl, Chris Dyer, Dani Yogatama, Sven Gowal, Krishnamurthy Dvijotham, Pushmeet Kohli
| Challenge: | Recent work has exposed the vulnerabilities of neural NLP models, e.g. with small, semantically invariant input alterations. |
| Approach: | They propose to model text classification under synonym replacements or character flip perturbations and then use a formal model verification method to verify its robustness. |
| Outcome: | The proposed models show little difference in terms of nominal accuracy, but have much improved verified accuracy under perturbations and come with an efficiently computable formal guarantee on worst case adversaries. |
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks (2022.coling-1)
Copied to clipboard
| Challenge: | Neural networks are vulnerable to adversarial examples, i.e., under a black-box scenario. |
| Approach: | They propose a word-level search algorithm that searches for subareas under dynamic search space following the subarea importance. |
| Outcome: | The proposed algorithm can achieve comparable success rates to complex search methods while saving numerous queries and time. |
On Tree-Based Neural Sentence Modeling (D18-1)
Copied to clipboard
| Challenge: | Existing tree-based sentence modeling approaches adopt syntactic parsing trees as the explicit structure prior. |
| Approach: | They replace parsing trees with trivial trees to study their effectiveness . they found that tree-based sentence modeling gives better results when crucial words are closer to the final representation . |
| Outcome: | The proposed tree-based sentences have shown better results on many downstream tasks. |
ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020.acl-main)
Copied to clipboard
Nazneen Fatema Rajani, Rui Zhang, Yi Chern Tan, Stephan Zheng, Jeremy Weiss, Aadit Vyas, Abhijit Gupta, Caiming Xiong, Richard Socher, Dragomir Radev
| Challenge: | Neural networks lack the ability to reason about qualitative physics and cannot generalize to scenarios and tasks unseen during training. |
| Approach: | They propose a framework for reasoning about qualitative physics in natural language that generates interpretable descriptions of physical events. |
| Outcome: | The proposed framework generates explanations of how the physical simulation will causally evolve so that an agent or a human can reason about a solution using interpretable descriptions. |
Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length (2024.acl-long)
Copied to clipboard
| Challenge: | Neural networks offer good approximation to many tasks but fail to reach perfect generalization. |
| Approach: | They propose to use a formal language to test whether a theoretically correct solution is not an optimum of commonly used objectives. |
| Outcome: | The proposed model fails to reach the theoretically correct solution even with regularization techniques. |
Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to understanding compositional generalization of models have focused on novel architectures and alternative learning paradigms. |
| Approach: | They propose a method that harnesses the power of dataset cartography to improve model accuracy by strategically identifying a subset of compositional generalization data. |
| Outcome: | The proposed method improves model accuracy by 10% on CFQ and COGS datasets. |