paper-with-me

Papers

ERNIE-NLI: Analyzing the Impact of Domain-Specific External Knowledge on Enhanced Representations for NLI

2021-06-01 · NAACL (DeeLIO) 2021 6 · Lisa Bauer, Lingjia Deng, Mohit Bansal

We examine the effect of domain-specific external knowledge variations on deep large scale language model performance. Recent work in enhancing BERT with external knowledge has been very popular, resulting in models such as ERNIE (Zhang et al., 2019a). Using the ERNIE architecture, we provide a detailed analysis on the types of knowledge that result in a performance increase on the Natural Language Inference (NLI) task, specifically on the Multi-Genre Natural Language Inference Corpus (MNLI). While ERNIE uses general TransE embeddings, we instead train domain-specific knowledge embeddings and insert this knowledge via an information fusion layer in the ERNIE architecture, allowing us to directly control and analyze knowledge input. Using several different knowledge training objectives, sources of knowledge, and knowledge ablations, we find a strong correlation between knowledge and classification labels within the same polarity, illustrating that knowledge polarity is an important feature in predicting entailment. We also perform classification change analysis across different knowledge variations to illustrate the importance of selecting appropriate knowledge input regarding content and polarity, and show representative examples of these changes.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingNatural Language Inference

Methods 이 논문이 사용한 방법론

ERNIE ERNIE is a transformer-based model consisting of two stacked modules: 1) textual encoder and 2) knowledgeable encoder, which is responsible to integrate extra token-oriented…

Similar Papers 제목 키워드 기반

ERNIE: Enhanced Language Representation with Informative Entities

2019-05-17 · ACL 2019 7 · Zhengyan Zhang, Xu Han, Zhiyuan Liu, Xin Jiang 외

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP task…

Entity LinkingEntity TypingKnowledge GraphsLinguistic Acceptability+6

Internal and External Impacts of Natural Language Processing Papers

2025-05-21 · Yu Zhang

We investigate the impacts of NLP research published in top-tier conferences (i.e., ACL, EMNLP, and NAACL) from 1979 to 2024. By analyzing citations from research articles and external sources such as patents, media, and…

ArticlesEthicsFairnessLanguage Modeling+1

ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph

2020-06-30 · Fei Yu, Jiji Tang, Weichong Yin, Yu Sun 외

We propose a knowledge-enhanced approach, ERNIE-ViL, which incorporates structured knowledge obtained from scene graphs to learn joint representations of vision-language. ERNIE-ViL tries to build the detailed semantic co…

AttributePredictionReferring Expression ComprehensionSentence+1

Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Ernie

2023-09-17 · Kyrie Zhixuan Zhou, Madelyn Rose Sanfilippo

Large language models are quickly gaining momentum, yet are found to demonstrate gender bias in their responses. In this paper, we conducted a content analysis of social media discussions to gauge public perceptions of g…

ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation

2021-12-23 · Shuohuan Wang, Yu Sun, Yang Xiang, Zhihua Wu 외

Pre-trained language models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. GPT-3 has shown that scaling up pre-trained language models can further exploit their enormous potent…

Language ModelingLanguage Modelling