research
∙
06/06/2023
Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks
Despite readily memorizing world knowledge about entities, pre-trained l...
share
research
∙
05/29/2023
Brainformers: Trading Simplicity for Efficiency
Transformers are central to recent successes in natural language process...
research
∙
02/26/2023
Generative Models for 3D Point Clouds
Point clouds are rich geometric data structures, where their three dimen...
research
∙
02/11/2023
Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models
Despite recent progress, it has been difficult to prevent semantic hallu...
research
∙
10/20/2022
Transcending Scaling Laws with 0.1
Scaling language models improves performance but comes with significant ...
research
∙
10/10/2022
Knowledge Prompts: Injecting World Knowledge into Language Models through Soft Prompts
Soft prompts have been recently proposed as a tool for adapting large fr...
research
∙
08/10/2022
Reducing Retraining by Recycling Parameter-Efficient Prompts
Parameter-efficient methods are able to use a single frozen pre-trained ...
research
∙
10/16/2021
EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks
Encoder-decoder transformer architectures have become popular recently w...
research
∙
10/23/2020
Large Scale Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training
Generating natural sentences from Knowledge Graph (KG) triples, known as...
research
∙
10/22/2020
Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension
We propose a simple method to generate large amounts of multilingual que...
research
∙
10/12/2020
End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems
We propose an end-to-end approach for synthetic QA data generation. Our ...
research
∙
09/22/2020
Embedding-based Zero-shot Retrieval through Query Generation
Passage retrieval addresses the problem of locating relevant passages, u...
research
∙
01/10/2020
TableQnA: Answering List Intent Queries With Web Tables
The web contains a vast corpus of HTML tables. They can be used to provi...
research
∙
01/10/2020
Open Domain Question Answering Using Web Tables
Tables extracted from web documents can be used to directly answer many ...
research
∙
11/27/2019
Label Dependent Deep Variational Paraphrase Generation
Generating paraphrases that are lexically similar but semantically diffe...
research
∙
11/11/2019
Knowledge Distillation in Document Retrieval
Complex deep learning models now achieve state of the art performance fo...
research
∙
10/30/2018
Differentiable Greedy Networks
Optimal selection of a subset of items from a given set is a hard proble...
research
∙
09/28/2018