Papers with Neural Networks

8 papers
Deep Learning and Sociophonetics: Automatic Coding of Rhoticity Using Neural Networks (N19-3)

Copied to clipboard

Challenge: Automated extraction methods for vowels are available, but coding rhoticity has lagged behind.
Approach: They use Neural Networks/Deep Learning to train a model on 208 speakers in Boston . they find that there is no reliable method for classifying r-dropping .
Outcome: The proposed method trains a model on 208 speakers in Boston, Massachusetts.
Injecting Relational Structural Representation in Neural Networks for Question Similarity (P18-2)

Copied to clipboard

Challenge: Recent years have seen exponential growth and use of web forums, where users can exchange and find information just asking questions in natural language.
Approach: They propose to use Tree Kernels to learn a model on relatively few pairs of questions as gold standard (GS) predicting labels on a very large corpus of question pairs is also a useful approach, they propose .
Outcome: The proposed model can learn more accurate models after fine tuning on GS.
Analogy-Guided Evolutionary Pretraining of Binary Word Embeddings (2022.aacl-main)

Copied to clipboard

Challenge: Existing binary word embeddings are derived from pretrained real-valued embeddables through different simple transformations, which often break the semantic consistency and the “arithmetic” properties of the embedded words.
Approach: They propose a genetic algorithm to learn binary word embeddings from scratch by preserving the semantic relationships between words and the arithmetic properties of the embeddables themselves.
Outcome: Evaluating 16, 32, and 64-bit word embeddings on Mikolov’s word analogy task shows that 95% of the time, the best fit is ranked in the top 5 most similar words in terms of cosine similarity.
Pivot Based Language Modeling for Improved Neural Domain Adaptation (N18-1)

Copied to clipboard

Challenge: Existing work on domain adaptation does not exploit the structure of the input text . PBLM can naturally feed structure aware text classifiers such as LSTM and CNN .
Approach: They propose a model that integrates pivot-based and NN modeling in a structure aware manner.
Outcome: The proposed model can naturally feed structure aware text classifiers such as LSTM and CNN.
Assessing Quality Estimation Models for Sentence-Level Prediction (C18-1)

Copied to clipboard

Challenge: Using a relevant QE model is also very important in QE.
Approach: They evaluate a wide range of advanced sentence-level Quality Estimation models including Support Vector Regression, Ride Regression and Bayesian Neural Networks.
Outcome: The proposed models behave differently in evaluation settings depending on whether test data come from the same domain as the training data or not.
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to detect out-of-domain (OOD) inputs are limited and lack data.
Approach: They propose a new architecture that extends Prototypical Networks to process in-domain and OOD sentences via Mutual Information Maximization objective.
Outcome: The proposed method significantly improves performance up to 20% for OOD detection in low resource settings of text classification.
Non-Parametric Adaptation for Neural Machine Translation (N19-1)

Copied to clipboard

Challenge: Neural Networks trained with gradient descent are susceptible to catastrophic forgetting due to parameter shift during the training process.
Approach: They propose a semi-parametric approach that relies on local phrase level similarities to retrieve neighboring phrases that are useful for translation even when overall sentence similarity is low.
Outcome: The proposed approach performs well on a heterogeneous dataset with WMT, IWSLT, JRC-Acquis and OpenSubtitles.
Low-Rank Updates of pre-trained Weights for Multi-Task Learning (2023.findings-acl)

Copied to clipboard

Challenge: Multi-task learning is a popular approach for learning with pre-trained models due to the complexity of the tasks and the challenges associated with fine-tuning large pre-train models.
Approach: They propose a new approach for Multi-task learning which is based on stacking the weights of Neural Networks as a tensor.
Outcome: The proposed approach achieves equivalent performance to the state-of-the-art on the general language understanding evaluation benchmark by training only 0.3 of the parameters per task while not modifying the baseline weights.

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