Experiments with Convolutional Neural Networks for Multi-Label Authorship Attribution (L18-1)
Copied to clipboard
| Challenge: | Existing methods for authorship attribution tasks are difficult, but they are effective. |
| Approach: | They propose a CNN that averaging author probability distributions at sentence level for longer documents and treating smaller documents as sentences adapts to single-label datasets and various document sizes. |
| Outcome: | The proposed method outperforms state-of-the-art models on a single-label AA benchmark dataset. |
Similar Papers
Authorship Attribution for Neural Text Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in deep learning have enabled the generation of realistic artifacts . however, the qualities of texts generated by these models are better, often confusing classifiers if they are not real. |
| Approach: | They propose to use neural network-based language models to generate realistic texts . they investigate the authorship attribution problem in three versions of a text . |
| Outcome: | The proposed models generate texts that are difficult to distinguish from human-written ones . the results show that most generators still generate texts significantly different from human ones compared to other models . |
Searching for Effective Neural Extractive Summarization: What Works and What’s Next (P19-1)
Copied to clipboard
| Challenge: | Recent years have seen success in the use of deep neural networks on text summarization, but there is no clear understanding of why they perform so well or how they might be improved. |
| Approach: | They propose to use different types of model architectures to improve extractive summarization systems. |
| Outcome: | The proposed framework achieves state-of-the-art on CNN/DailyMail by a large margin based on observations and analysis. |
Topic or Style? Exploring the Most Useful Features for Authorship Attribution (C18-1)
Copied to clipboard
| Challenge: | Existing approaches to authorship attribution rely on individual's writing style and/or preferred topics. |
| Approach: | They analyse four widely used datasets to explore how different types of features affect authorship attribution accuracy under varying conditions. |
| Outcome: | The proposed model outperforms the state-of-the-art on two out of the four datasets used. |
Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN (2022.naacl-main)
Copied to clipboard
| Challenge: | XML-CNN has been a popular research topic in NLP due to its superior performance . however, the increasing complexity brings difficulties to ensure the true architectural progress . |
| Approach: | They propose to re-examine an influential multi-label text classification method . they propose suitable baselines for multi-level text classification tasks . |
| Outcome: | The proposed method performs better than the original model, the authors show . they show that the re-implementation reveals contradictory results to the original work . |
Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction (P18-2)
Copied to clipboard
| Challenge: | Recent supervised deep learning models have achieved state-of-the-art performance, but there are two other considerations that are important. |
| Approach: | They propose a supervised aspect extraction model using general-purpose embeddings and domain-specific embeddables. |
| Outcome: | The proposed model outperforms state-of-the-art methods without supervision and achieves very good results. |
Article Classification with Graph Neural Networks and Multigraphs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing and newly published articles require complex and complex pipelines to classify them into context-specific label taxonomies. |
| Approach: | They propose to enrich Graph Neural Network pipelines with multi-graph representations that encode multiple signals of article relatedness as distinct edge types. |
| Outcome: | The proposed methods improve the performance of a variety of GNN models compared to default graphs. |
Convolutional Neural Networks with Recurrent Neural Filters (D18-1)
Copied to clipboard
| Challenge: | Convolutional neural networks (CNNs) use recurrent neural networks as convolution filters to capture language compositionality and long-term dependencies. |
| Approach: | They propose to use recurrent neural networks (RNNs) as convolution filters to capture language compositionality and long-term dependencies. |
| Outcome: | The proposed convolutional neural networks achieve state-of-the-art on two sentences and the Stanford Sentiment Treebank. |
Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to summarize documents are not extractive and require an abstractive approach. |
| Approach: | They propose a novel abstractive model which is conditioned on the article’s topics and based entirely on convolutional neural networks. |
| Outcome: | The proposed model outperforms an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans. |
Multi-label Categorization of Accounts of Sexism using a Neural Framework (D19-1)
Copied to clipboard
Pulkit Parikh, Harika Abburi, Pinkesh Badjatiya, Radhika Krishnan, Niyati Chhaya, Manish Gupta, Vasudeva Varma
| Challenge: | Sexism manifests in blatant as well as subtle ways, authors say . existing work on sexism classification has limitations in terms of categories used . authors: categorization of accounts of sexist behavior can aid in countering sextism . |
| Approach: | They propose a neural solution that can combine sentence representations with distributional and linguistic word embeddings. |
| Outcome: | a new method outperforms deep learning and traditional methods by an appreciable margin . the proposed method outpersforms several deep learning as well as traditional baselines by an approval margin compared to baselines . |
Layered Insights: Generalizable Analysis of Human Authorial Style by Leveraging All Transformer Layers (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to authorship attribution model only learn from the output layer of pre-trained transformers, ignoring representations learned at other layers. |
| Approach: | They propose a model that leverages the various linguistic representations learned at different layers of pre-trained transformer-based models to model the authorship attribution task more effectively. |
| Outcome: | The proposed model performs better on out-of-domain and in-domain scenarios, while ignoring representations learned at other layers. |