Papers with component models

4 papers
A Hybrid Neural Network Model for Commonsense Reasoning (D19-60)

Copied to clipboard

Challenge: a hybrid neural network (HNN) model for commonsense reasoning is proposed . it combines language models and semantic similarity models to achieve new state-of-the-art results .
Approach: They propose a hybrid neural network model for commonsense reasoning . it combines a masked language model and a semantic similarity model .
Outcome: The proposed model outperforms the WNLI, WSC and PDP60 benchmarks on three commonsense reasoning tasks.
ConvLab: Multi-Domain End-to-End Dialog System Platform (P19-3)

Copied to clipboard

Challenge: ConvLab is an open-source multi-domain end-to-end dialog system platform . it allows researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments.
Approach: They propose to use an open-source multi-domain end-to-end dialog system platform to train and evaluate dialog bots in common environments.
Outcome: The proposed system enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments.
Stacking with Auxiliary Features for Visual Question Answering (N18-1)

Copied to clipboard

Challenge: Visual Question Answering (VQA) is a challenging task that requires systems to reason about natural language and vision.
Approach: They propose four categories of auxiliary features for ensembling for VQA . three out of the four categories can be inferred from an image-question pair . fourth category uses model-specific explanations .
Outcome: The proposed techniques improve performance for visual question answering (VQA) given an image and a natural language question, the task is to provide an accurate natural language answer.
Boosted Dense Retriever (2022.naacl-main)

Copied to clipboard

Challenge: DrBoost is a dense retrieval ensemble that is trained in stages to correct retrieval mistakes . it produces representations which are 4x more compact, while delivering comparable retrieval results.
Approach: They propose a dense retrieval ensemble inspired by boosting that is trained in stages . they produce representations which are 4x more compact, while delivering comparable retrieval results .
Outcome: The proposed model performs surprisingly well under approximate search with coarse quantization, reducing latency and bandwidth needs by another 4x.

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