Papers with Neural network models
Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network (N18-2)
Copied to clipboard
| Challenge: | Abstractive text summarization models are hard to be controlled in the process of generation, which leads to a lack of key information. |
| Approach: | They propose a guiding generation model that combines extractive and abstractive methods to generate text summarization. |
| Outcome: | The proposed model improves on the CNN/Daily Mail dataset. |
Evaluating Transformer Models and Human Behaviors on Chinese Character Naming (2023.tacl-1)
Copied to clipboard
| Challenge: | Neural network models have been proposed to explain the grapheme-phoneme mapping process in humans for many alphabet languages. |
| Approach: | They propose to use a dictionary-like lookup procedure to map the letter strings to their pronunciations and then use 'transformers' to capture human behavior. |
| Outcome: | The proposed models learned the correspondence of the letter strings and their pronunciation, and captured human behavior in nonce word naming tasks. |
Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialog (N19-1)
Copied to clipboard
| Challenge: | Neural network models have gained traction for sentence-level intent classification and token-based slot-label identification. |
| Approach: | They propose a neural network model that performs multi-label classification for identifying multiple intents and produces token-based slot-l labels at the token-level. |
| Outcome: | The proposed model provides a small but statistically significant improvement on the ATIS dataset and 55% accuracy improvement on an internal multi-intent dataset. |
Predicting Foreign Language Usage from English-Only Social Media Posts (N18-2)
Copied to clipboard
| Challenge: | Social media is known for its multi-cultural and multilingual interactions, a natural product of which is code-mixing. |
| Approach: | They analyze 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English to build predictive models to infer non-English languages users speak exclusively from their tweets. |
| Outcome: | The proposed models are based on a corpus of 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English . they show that content, style and syntax are the most predictive of non-English languages that users speak on Twitter. |
Incorporating Word Attention into Character-Based Word Segmentation (N19-1)
Copied to clipboard
Shohei Higashiyama, Masao Utiyama, Eiichiro Sumita, Masao Ideuchi, Yoshiaki Oida, Yohei Sakamoto, Isaac Okada
| Challenge: | Word segmentation models are used to minimize the effort in feature engineering. |
| Approach: | They propose a character-based model that learns the importance of multiple candidate words for a corresponding character on the basis of an attention mechanism and makes use of it for segmentation decisions. |
| Outcome: | The proposed model outperforms the state-of-the-art models on Japanese and Chinese benchmark datasets. |
CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability (2023.emnlp-main)
Copied to clipboard
| Challenge: | Neural network models are vulnerable to adversarial examples, and current methods based on adversarially transferable models rely on substitute models, which can be impractical and costly in real-world scenarios due to the unavailability of training data and the victim model’s structural details. |
| Approach: | They propose a novel approach that directly constructs adversarial examples by extracting transferable features across various tasks. |
| Outcome: | The proposed approach achieves superior attack performance with small cost on ten datasets and demonstrates that it is a novel approach. |
Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection (P19-1)
Copied to clipboard
| Challenge: | linguistics and cognitive science have long debated the cognitive mechanisms needed to account for the English past tense. |
| Approach: | They propose to use an encoder-decoder model to account for the english past tense . they also show that ED models demonstrate humanlike performance in a nonce-word task . |
| Outcome: | The proposed model is unstable across simulations and does not fit to human data . other neural models might do better, but there is insufficient evidence to claim them . |
Rethinking Complex Neural Network Architectures for Document Classification (N19-1)
Copied to clipboard
| Challenge: | Neural network models for many NLP tasks have grown increasingly complex in recent years . authors of recent papers question the necessity of such architectures and find them quite effective . |
| Approach: | They propose to use regularization techniques borrowed from language modeling to improve model accuracy . they find that a simple biLSTM architecture with appropriate regularization yields competitive results . |
| Outcome: | a simple biLSTM model outperforms the state-of-the-art on four benchmark datasets . authors say that improvements are not real, but are attributed to mundane reasons . |