Papers with Neural network models

8 papers
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

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 .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations