Papers with deep learning architecture
Interpretable Relevant Emotion Ranking with Event-Driven Attention (D19-1)
Copied to clipboard
| Challenge: | Existing studies ignore the latent event information in documents . Existing methods for detecting emotions are limited to a few words . |
| Approach: | They propose to integrate event information into a deep learning architecture to extract relevant emotion ranking models using corpus-level event embeddings and document-level events. |
| Outcome: | The proposed model performs better than state-of-the-art emotion detection and multi-label approaches on three real-world corpora and interpretable results shed light on the events which trigger certain emotions. |
Large Scale Author Obfuscation Using Siamese Variational Auto-Encoder: The SiamAO System (2020.starsem-1)
Copied to clipboard
| Challenge: | Existing approaches to author obfuscation are largely heuristic, but they can be used to attack author identification. |
| Approach: | They propose a deep learning architecture for constructing adversarial examples against similarity-based learners and explore its application to author obfuscation. |
| Outcome: | The proposed architectures show that they can be used to attack author obfuscation . the proposed architecture shows that it can be applied to obliquacy of text . |
DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference (N18-1)
Copied to clipboard
Reza Ghaeini, Sadid A. Hasan, Vivek Datla, Joey Liu, Kathy Lee, Ashequl Qadir, Yuan Ling, Aaditya Prakash, Xiaoli Fern, Oladimeji Farri
| Challenge: | Existing approaches to natural language inference rely on simple reading mechanisms for independent encoding of the premise and hypothesis. |
| Approach: | They propose a novel bidirectional dependent reading network to efficiently model the relationship between a premise and a hypothesis during encoding and inference. |
| Outcome: | The proposed model outperforms existing methods by a considerable margin on the Stanford Natural Language Inference (SNLI) dataset. |
Discovering Implicit Knowledge with Unary Relations (P18-1)
Copied to clipboard
| Challenge: | State-of-the-art relation extraction methods only recognize relationships between mentions of entity arguments stated explicitly in the text. |
| Approach: | They propose a method to identify relations between two entities using unary relations and a common deep learning based representation. |
| Outcome: | The proposed method outperforms state-of-the-art relation extraction technology on a web scale knowledge base population benchmark. |
An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection (C18-1)
Copied to clipboard
| Challenge: | Existing approaches to spam detection focus on extracting linguistic or behavior features to distinguish the spam and legitimate reviews. |
| Approach: | They propose a deep learning architecture for incorporating entities and their attributes into a unified framework. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on two Yelp datasets. |
Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference (D18-1)
Copied to clipboard
| Challenge: | Using a new architecture, alignment pairs are compared, compressed and then propagated to upper layers for enhanced representation learning. |
| Approach: | They propose a new architecture where alignment pairs are compared, compressed and then propagated to upper layers for enhanced representation learning. |
| Outcome: | The proposed architecture achieves competitive performance on three popular benchmarks, SNLI, MultiNLI and SciTail, while maintaining lightweight parameter size. |
Hate-Speech and Offensive Language Detection in Roman Urdu (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on hate-speech and offensive language detection in social media content is mainly focused on the English language. |
| Approach: | They propose to use an annotated dataset to detect hate-speech and offensive language in social media content . they propose to transfer five existing embedding models to Roman Urdu to test their performance . |
| Outcome: | The proposed model outperforms existing methods on RUHSOLD dataset and train domain-specific embeddings on more than 4.7 million tweets. |
Enhancing Transformers for Generalizable First-Order Logical Entailment (2025.acl-long)
Copied to clipboard
Tianshi Zheng, Jiazheng Wang, Zihao Wang, Jiaxin Bai, Hang Yin, Zheye Deng, Yangqiu Song, Jianxin Li
| Challenge: | Moreover, transformers have demonstrated proficiency in logical reasoning over natural language. |
| Approach: | They propose a logic-aware architecture that improves the performance in generalizable first-order logical entailment by combining distribution shifts and unseen knowledge. |
| Outcome: | The proposed architecture outperforms methods designed specifically for knowledge graph query answering on a dataset with a large dataset. |
Dependent Gated Reading for Cloze-Style Question Answering (C18-1)
Copied to clipboard
| Challenge: | Existing approaches do not fully exploit the interdependency between document and query. |
| Approach: | They propose a novel dependent gated reading bidirectional GRU network to efficiently model the relationship between the document and the query during encoding and decision making. |
| Outcome: | The proposed model performs well on machine comprehension benchmarks such as the Children’s Book Test and Who DiD What. |
Graph-to-Tree Learning for Solving Math Word Problems (2020.acl-main)
Copied to clipboard
| Challenge: | Existing tree-based neural models do not capture the relationships and order information among the quantities well. |
| Approach: | They propose a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. |
| Outcome: | The proposed framework outperforms the state-of-the-art on two available datasets significantly. |
Symmetric Dot-Product Attention for Efficient Training of BERT Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Transformer-based models are stretched to enormous sizes, requiring increasingly larger training datasets and unsustainable amount of compute resources. |
| Approach: | They propose an alternative compatibility function for the Transformer-based attention mechanism that exploits an overlap in the learned representation of the traditional scaled dot-product attention mechanism. |
| Outcome: | The proposed model achieves 79.36 on the GLUE benchmark against 78.74 for the traditional implementation and reduces the number of trainable parameters by 6%. |
Sanskrit Sandhi Splitting using seq2(seq)2 (D18-1)
Copied to clipboard
| Challenge: | Existing methods for word splitting in Sanskrit have low accuracy as the same compound word might be broken down in multiple ways to provide syntactically correct splits. |
| Approach: | They propose a deep learning architecture called Double Decoder RNN which predicts the location of the splits with 95% accuracy and 79.5% accuracy. |
| Outcome: | The proposed model outperforms the state-of-the-art in the problem of Chinese word segmentation with 79.5% accuracy and the existing model's generalization capability. |
BiLSTM-CRF for Persian Named-Entity Recognition ArmanPersoNERCorpus: the First Entity-Annotated Persian Dataset (L18-1)
Copied to clipboard
| Challenge: | Named-entity recognition (NER) is a natural language processing component that aims to identify all the "named entities" (NEs) in an unstructured text. |
| Approach: | They propose a deep learning approach for name-entity recognition in Persian . they publicize an entity-annotated Persian dataset and train word embeddings . |
| Outcome: | The proposed approach achieves a 77.45% CoNLL F 1 score for Persian NER based on a deep learning architecture and pre-trained word embeddings. |