paper-with-me

Papers Riddle Sense

“Riddle Sense” 태그가 달린 논문 5편 · 필터 해제

Deep Bidirectional Language-Knowledge Graph Pretraining

2022-10-17 · Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang 외

Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks. Recent works show that a knowledge graph (KG) can complement text data, offering structured background knowledge that provide…

Common Sense ReasoningKnowledge GraphsLanguage ModelingLanguage Modelling+4

Training Compute-Optimal Large Language Models

2022-03-29 · Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya 외

We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. We find that current large language models are significantly undertrained, a consequence …

AnachronismsAnalogical SimilarityAnalytic EntailmentCausal Judgment+69

Scaling Language Models: Methods, Analysis & Insights from Training Gopher

2021-12-08 · NA 2021 12 · Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican 외

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis o…

Abstract AlgebraAnachronismsAnalogical SimilarityAnalytic Entailment+143

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

2021-04-13 · NAACL 2021 4 · Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang 외

The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify …

Common Sense ReasoningGraph Representation LearningKnowledge GraphsLanguage Modelling+5

RoBERTa: A Robustly Optimized BERT Pretraining Approach

2019-07-26 · Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du 외

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different s…

Common Sense ReasoningDocument Image ClassificationLanguage ModelingLanguage Modelling+14
1–5 / 5