paper-with-me

Papers

Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference

2019-04-27 · Tianda Li, Xiaodan Zhu, Quan Liu, Qian Chen, Zhigang Chen, Si Wei

Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives has shown to be very effective on a wide range of NLP problems. It would still be desirable to further understand how it helps NLI; e.g., if it learns artifacts in data annotation or instead learn true inference knowledge. In addition, external knowledge that does not exist in the limited amount of NLI training data may be added to NLI models in two typical ways, e.g., from human-created resources or an unsupervised pretraining paradigm. We runs several experiments here to investigate whether they help NLI in the same way, and if not,how?

📄 PDF Abstract BibTeX arXiv:1904.12104

Code (1)

TeddLi/Further-manually-annotated-glockner

Tasks

Language ModelingLanguage ModellingNatural Language InferenceNatural Language UnderstandingSentence

Similar Papers 제목 키워드 기반

Investigating Continual Pretraining in Large Language Models: Insights and Implications

2024-02-27 · Çağatay Yıldız, Nishaanth Kanna Ravichandran, Prishruit Punia, Matthias Bethge 외

This paper studies the evolving domain of Continual Learning (CL) in large language models (LLMs), with a focus on developing strategies for efficient and sustainable training. Our primary emphasis is on continual domain…

Continual LearningContinual PretrainingSemantic SimilaritySemantic Textual Similarity+1

Renaissance: Investigating the Pretraining of Vision-Language Encoders

2024-11-11 · Clayton Fields, Casey Kennington

In the past several years there has been an explosion of available models for vision-language tasks. Unfortunately, the literature still leaves open a number of questions related to best practices in designing and traini…

KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation

2021-01-02 · ACL 2021 5 · Yiran Xing, Zai Shi, Zhao Meng, Gerhard Lakemeyer 외

We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the g…

Knowledge GraphsLanguage ModelingLanguage ModellingLarge Language Model

Knowledge-enhanced Visual-Language Pretraining for Computational Pathology

2024-04-15 · Xiao Zhou, Xiaoman Zhang, Chaoyi Wu, Ya zhang 외

In this paper, we consider the problem of visual representation learning for computational pathology, by exploiting large-scale image-text pairs gathered from public resources, along with the domain-specific knowledge in…

Cross-Modal RetrievalLanguage ModelingLanguage ModellingRepresentation Learning+4

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

2025-05-14 · Siyuan Yan, Xieji Li, Ming Hu, Yiwen Jiang 외

Dermatological diagnosis represents a complex multimodal challenge that requires integrating visual features with specialized clinical knowledge. While vision-language pretraining (VLP) has advanced medical AI, its effec…

Clinical KnowledgeContrastive LearningCross-Modal Retrieval