Papers with computational process
Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition (2020.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that modern neural networks understand sentences implicitly by inducing recursive structures. |
| Approach: | They propose to explicitly induce grammar by tracing the computational process of a long short-term memory network. |
| Outcome: | The proposed model can explicitly induce grammar without external knowledge . tracing the computational process of a long short-term memory network is shown to be effective . |
LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing EA methods inherit the inborn defects from their neural network lineage: poor interpretability and weak scalability. |
| Approach: | They propose a neural-free EA framework that can find equivalent entity pairs between KGs. |
| Outcome: | The proposed framework has impressive scalability, robustness, and interpretability. |
Validity, Agreement, Consensuality and Annotated Data Quality (2022.lrec-1)
Copied to clipboard
| Challenge: | a wide consensus is rife regarding the need for reference annotated datasets . however, the creation of such datasets is accompanied by theorectical and practical issues . |
| Approach: | They propose to use agreement among annotators as an indicator of consensus . they argue that it is difficult to produce gold-standard annotated datasets . |
| Outcome: | The proposed model focuses on the complex relations between agreement and reference and the emergence of consensus. |
LAMAD: A Linguistic Attentional Model for Arabic Text Diacritization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | In Arabic, diacritics are often omitted from written texts increasing the number of possible meanings and pronunciations. |
| Approach: | They propose a linguistic attentional model for Arabic text diacritization which captures key linguistic features from Arabic text. |
| Outcome: | The proposed model outperforms existing state-of-the-art models on three datasets with different sizes. |
Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition (2023.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that word acquisition is an efficient, supervised, and continual process. |
| Approach: | They develop a computational process for word acquisition through comparative learning . they frame the acquisition of words as representation-symbol mapping . |
| Outcome: | The proposed method can be used to learn the meaning of a word efficiently and efficiently. |
Diversification Catalyzes Language Models’ Instruction Generalization To Unseen Semantics (2025.findings-acl)
Copied to clipboard
| Challenge: | Instruction-tuned language models excel in knowledge, reasoning, and instruction-following . however, the factors enabling generalization to unseen instructions remain underexplored . |
| Approach: | They propose to model instruction-following as a computational process and design controlled experiments inspired by the Turing-complete Markov algorithm to disentangle its dynamics. |
| Outcome: | The proposed model outperforms scaling up data volumes in generalist models by combining in-domain and diverse out-of-domain tasks. |