Papers with Deep learning models
On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning (D19-62)
Copied to clipboard
| Challenge: | Existing models for relation extraction use different pooling mechanisms to perform pooling for RE. |
| Approach: | They conduct a comprehensive study to evaluate the effectiveness of different pooling mechanisms for deep learning in biomedical RE. |
| Outcome: | The proposed model outperforms the previous models on two biomedical datasets. |
More Bang for Your Buck: Natural Perturbation for Robust Question Answering (2020.emnlp-main)
Copied to clipboard
| Challenge: | Creating large datasets to train NLP models is becoming increasingly expensive. |
| Approach: | They propose to use a question-answering dataset to expand a training set using human-driven perturbations instead of rule-based machine perturbations. |
| Outcome: | The proposed approach improves on a question-answering dataset with human-driven perturbations. |
Adversarial Sample Generation for Aspect based Sentiment Classification (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing approaches to attack adversarial samples in natural language processing are ineffective . initial attacks perturb characters or words in sentences, resulting in grammatical incorrect or out-of-context sentences. |
| Approach: | They propose an attack algorithm that generates adversarial samples for a given aspect, maintaining more semantic coherency. |
| Outcome: | The proposed method outperforms the state-of-the-art methods in perturbation ratio, success rate, and semantic coherence. |
Adv-OLM: Generating Textual Adversaries via OLM (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent studies have pointed out the vulnerability of deep learning models to adversarial attacks. |
| Approach: | They propose a black-box attack method that adapts the idea of Occlusion and Language Models to the current state of the art attack methods. |
| Outcome: | The proposed method outperforms existing methods on several text classification tasks. |
Stacking with Auxiliary Features for Visual Question Answering (N18-1)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) is a challenging task that requires systems to reason about natural language and vision. |
| Approach: | They propose four categories of auxiliary features for ensembling for VQA . three out of the four categories can be inferred from an image-question pair . fourth category uses model-specific explanations . |
| Outcome: | The proposed techniques improve performance for visual question answering (VQA) given an image and a natural language question, the task is to provide an accurate natural language answer. |
Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment (2021.acl-long)
Copied to clipboard
| Challenge: | Existing deep learning models for automatic readability assessment discard linguistic features traditionally used for the task. |
| Approach: | They propose to incorporate linguistic features into machine learning models by learning syntactic dense embeddings based on linguistic feature extraction. |
| Outcome: | Experiments with six data sets of two proficiency levels show that the proposed model can perform better than existing models. |
Optimizing Annotation Effort Using Active Learning Strategies: A Sentiment Analysis Case Study in Persian (2020.lrec-1)
Copied to clipboard
Seyed Arad Ashrafi Asli, Behnam Sabeti, Zahra Majdabadi, Preni Golazizian, Reza Fahmi, Omid Momenzadeh
| Challenge: | Existing deep learning approaches require huge amounts of data to be trained properly. |
| Approach: | They propose to use Persian as a model to choose the samples for annotation instead of labeling the whole dataset. |
| Outcome: | The proposed models achieve the baseline performance with a significantly lower amount of labeled data. |
Counterfactual Adversarial Learning with Representation Interpolation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models with statistical bias are prone to memorized correlations . large pre-trained models such as BERT have revolutionized the model development paradigm in natural language processing . |
| Approach: | They propose a framework to tackle the problem from a causal perspective using a latent space interpolation approach. |
| Outcome: | Extensive experiments show that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering. |
Alignment Rationale for Natural Language Inference (2021.acl-long)
Copied to clipboard
| Challenge: | Existing explanation methods pick prominent features, but alignments between words or phrases are more enlightening clues to explain the model. |
| Approach: | They propose a method to generate alignment rationale explanations for co-attention based models in NLI by feature selection. |
| Outcome: | The proposed method is more faithful and human-readable compared with existing methods. |
Posing Fair Generalization Tasks for Natural Language Inference (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation methods for deep learning semantics rely on naturalistic corpora, but they often fail to support the kind of generalization we are asking for. |
| Approach: | They define and motivate a formal notion of fairness for evaluations of deep learning models for semantics . they then apply it to natural language inference by constructing challenging but provably fair artificial datasets based on the results . |
| Outcome: | The proposed evaluations show that standard neural models fail to generalize in the required ways and even these models do not solve the task perfectly. |
Pre-trained Language Models for Entity Blocking: A Reproducibility Study (2024.naacl-long)
Copied to clipboard
| Challenge: | Entity Resolution (ER) is an essential task in data integration . state-of-the-art neural IR models that are based on large language models have not been evaluated on the ER task. |
| Approach: | They evaluate state-of-the-art neural IR models that are based on large language models on a wide range of real-world datasets and evaluate their generalization abilities. |
| Outcome: | The proposed methods have been evaluated on a wide range of datasets and their generalization abilities. |
Explain Yourself! Leveraging Language Models for Commonsense Reasoning (P19-1)
Copied to clipboard
| Challenge: | Empirical results indicate that we can effectively leverage language models for commonsense reasoning. |
| Approach: | They propose to use commonsense auto-generated explanations to train language models to generate explanations that can be used during training and inference in a commonsensense Auto-Generated Explanation framework. |
| Outcome: | Empirical results show that the proposed framework improves on the commonsenseQA task by 10%. |
CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples (2025.emnlp-main)
Copied to clipboard
| Challenge: | Spurious correlations are patterns that appear in datasets but do not represent genuine relationships. |
| Approach: | They propose a more general form of counterfactual data augmentation that tackles multiple biases . they propose 'CoBA' that decomposes text into subject-predicate-object triples and modifies them to disrupt spurious correlations. |
| Outcome: | The proposed framework reduces biases and strengthens out-of-distribution resilience. |
Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference (D18-1)
Copied to clipboard
| Challenge: | In this paper, we examine the behavior of deep learning models in their intermediate layers . saliency determines what is critical for the final decision of a deep model . |
| Approach: | They propose to interpret the intermediate layers of deep models by visualizing the saliency of attention and LSTM gating signals. |
| Outcome: | The proposed methods reveal interesting insights and identify critical information contributing to the model decisions. |
Evaluating Saliency Explanations in NLP by Crowdsourcing (2024.lrec-main)
Copied to clipboard
| Challenge: | a crowdsourced method to evaluate saliency methods in NLP is proposed . saliencies are difficult for humans to understand, and can cause psychological harm . |
| Approach: | They propose a method to evaluate saliency methods in NLP by crowdsourcing . they recruited 800 crowd workers and empirically evaluated seven salience methods . |
| Outcome: | The proposed method evaluates saliency methods on two datasets using crowdsourced data . it shows that the results are comparable to existing methods on NLP and CV fields . |
AD-NLP: A Benchmark for Anomaly Detection in Natural Language Processing (2023.emnlp-main)
Copied to clipboard
| Challenge: | Methods for Anomaly Detection in text have shown strong empirical results on ad-hoc anomaly setups that are usually made by downsampling some classes of a labeled dataset. |
| Approach: | They propose a unified benchmark for detecting various types of anomalies . they evaluate two strong shallow baselines and two current state-of-the-art neural approaches . |
| Outcome: | The proposed benchmarks provide insights into the knowledge the neural models are learning when performing the task. |
No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Deep learning models lacking interpretability and interactivity, authors say . lack of interactive mechanisms prevents clinicians from incorporating their own knowledge into decision-making process. |
| Approach: | a new deep learning model is proposed to improve interpretability and interactivity . authors propose a knowledge-enhanced agent-driven causal discovery framework . |
| Outcome: | a new model improves interpretability and interactivity on EHR data . the proposed model improve interpretability through explicit reasoning and causal analysis . |
Data Descriptions from Large Language Models with Influence Estimation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing explainable AI approaches focus on interpreting how models make predictions. |
| Approach: | They propose a pipeline that generates textual descriptions using large language models . they propose 'cross-modal transfer classification' task to examine effectiveness of textual description . |
| Outcome: | The proposed method improves classification accuracy compared to baselines and sheds light on how the model prioritizes and utilizes information for decision-making. |
CANDICE: Agentic Causal Disentanglement with Class Conditional Knowledge Integration for Long Tailed Domain Generalization (2026.findings-acl)
Copied to clipboard
| Challenge: | Domain generalization and long-tailed (LT) learning models face two challenges . domain invariance often suppresses class-discriminative signals essential for long-tail recognition. |
| Approach: | They propose a framework that disentangles domain-invariant and class-discriminative features . they evaluate 10 diverse medical imaging datasets spanning four modalities . |
| Outcome: | The proposed framework achieves an average performance improvement of 10.3% across multi-domain and in-domain long-tailed tasks while preserving minority class performance. |