Papers with deep architecture

5 papers
BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to improve word embeddings for rare words are limited to uncontextualized word embeds.
Approach: They propose a powerful architecture that can infer high-quality embeddings for rare words . they use the surface form and contexts of a word to interact in a deep architecture .
Outcome: The proposed architecture can infer high-quality embeddings for rare words that are suitable as input representations for deep language models.
Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences (D18-1)

Copied to clipboard

Challenge: a long standing problem in NLP research is learning a matching function between two text sequences . a deep architecture for this task is proposed by a team of researchers .
Approach: They propose a new deep matching model using stacked recurrent encoders to learn affinity weights . they conduct extensive experiments on six well-studied text sequence matching datasets a plethora of applications are possible .
Outcome: The proposed model improves performance on six well-studied text sequence matching datasets.
Modeling Online Discourse with Coupled Distributed Topics (D18-1)

Copied to clipboard

Challenge: a topic model that incorporates structural relationships connecting documents in socially generated corpora is of limited application in the sciences.
Approach: They propose a topic model that incorporates structural relationships connecting documents in socially generated corpora, such as online forums.
Outcome: The proposed model captures discursive interactions along observed reply links and integrates latent distributed representations in a deep architecture.
A Deep Metric Learning Method for Biomedical Passage Retrieval (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for passage retrieval are based on metric learning . the proposed approach is particularly well suited for domain-specific passage retrievals where it is very important to take into account different sources of information.
Approach: They propose a method that learns a metric for questions and passages based on their internal semantic interactions.
Outcome: The proposed method outperforms triplet loss and state-of-the-art methods in a biomedical passage retrieval task and outperformed triplet losses by 10% and 26%.
Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks (P19-1)

Copied to clipboard

Challenge: Existing approaches for text classification are lexicallevel features with Naive Bayes or Support Vector Machines (SVM) .
Approach: They propose a deep-learning model that uses label descriptions to train texts and their labels for multi-label and multi-class classification tasks.
Outcome: The proposed model improves on one set with a high margin and on all other sets with competitive results.

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