信息抽取论文调研集合1。

A Survey of Large Language Models

人大，arXiv 2023.05，代码。

Ever since the Turing Test was proposed in the 1950s, humans have explored the mastering of language intelligence by machine. Language is essentially a complex, intricate system of human expressions governed by grammatical rules. It poses a significant challenge to develop capable artificial intelligence (AI) algorithms for comprehending and grasping a language. As a major approach, language modeling has been widely studied for language understanding and generation in the past two decades, evolving from statistical language models to neural language models. Recently, pre-trained language models (PLMs) have been proposed by pretraining Transformer models over large-scale corpora, showing strong capabilities in solving various natural language processing (NLP) tasks. Since the researchers have found that model scaling can lead to an improved model capacity, they further investigate the scaling effect by increasing the parameter scale to an even larger size. Interestingly, when the parameter scale exceeds a certain level, these enlarged language models not only achieve a significant performance improvement, but also exhibit some special abilities (e.g., incontext learning) that are not present in small-scale language models (e.g., BERT). To discriminate the language models in different parameter scales, the research community has coined the term large language models (LLM) for the PLMs of significant size (e.g., containing tens or hundreds of billions of parameters). Recently, the research on LLMs has been largely advanced by both academia and industry, and a remarkable progress is the launch of ChatGPT (a powerful AI chatbot developed based on LLMs), which has attracted widespread attention from society. The technical evolution of LLMs has been making an important impact on the entire AI community, which would revolutionize the way how we develop and use AI algorithms. Considering this rapid technical progress, in this survey, we review the recent advances of LLMs by introducing the background, key findings, and mainstream techniques. In particular, we focus on four major aspects of LLMs, namely pre-training, adaptation tuning, utilization, and capacity evaluation. Furthermore, we also summarize the available resources for developing LLMs and discuss the remaining issues for future directions. This survey provides an up-to-date review of the literature on LLMs, which can be a useful resource for both researchers and engineers.

PromptMNER: Prompt-Based Entity-Related Visual Clue Extraction and Integration for Multimodal Named Entity Recognition

复旦大学计算机科学学院，上海数据科学重点实验室，DASFAA 2022

作者提出了一种利用prompt来更好的导出实体相关的视觉特征的方法。

Multimodal named entity recognition (MNER) is an emerging task that incorporates visual and textual inputs to detect named entities and predicts their corresponding entity types. However, existing MNER methods often fail to capture certain entity-related but textloosely-related visual clues from the image, which may introduce taskirrelevant noises or even errors. To address this problem, we propose to utilize entity-related prompts for extracting proper visual clues with a pre-trained vision-language model. To better integrate different modalities and address the popular semantic gap problem, we further propose a modality-aware attention mechanism for better cross-modal fusion. Experimental results on two benchmarks show that our MNER approach outperforms the state-of-the-art MNER approaches with a large margin.

Product-of-Experts and Mixture-of-Experts

这篇博客主要记录PoE和MoE的一些调研笔记。

GPT-4 Technical Report

2023-03-14日OpenAI发布的多模态GPT-4，下面是关于它技术报告的一个总结。大多是简单的high-level的描述和输入输出cases，具体模型细节、部署架构等等都没有说。

We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. GPT-4 is a Transformerbased model pre-trained to predict the next token in a document. The post-training alignment process results in improved performance on measures of factuality and adherence to desired behavior. A core component of this project was developing infrastructure and optimization methods that behave predictably across a wide range of scales. This allowed us to accurately predict some aspects of GPT-4’s performance based on models trained with no more than 1/1,000th the compute of GPT-4.

A Review on Language Models as Knowledge Bases

arxiv 2022，Meta AI的一篇关于把预训练语言模型看做是知识库KB的综述。

Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs trained on a sufficiently large (web) corpus will encode a significant amount of knowledge implicitly in its parameters. The resulting LM can be probed for different kinds of knowledge and thus acting as a KB. This has a major advantage over traditional KBs in that this method requires no human supervision. In this paper, we present a set of aspects that we deem an LM should have to fully act as a KB, and review the recent literature with respect to those aspects.1

Multimodal Learning with Transformers: A Survey

2022-06 arxiv

牛津大学学者的一篇多模态Transformer综述，系统的描述了目前多模态Transformer可能注意的不同改进点。

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal big data era, (2) a theoretical review of Vanilla Transformer, Vision Transformer, and multimodal Transformers, from a geometrically topological perspective, (3) a review of multimodal Transformer applications, via two important paradigms, i.e., for multimodal pretraining and for specific multimodal tasks, (4) a summary of the common challenges and designs shared by the multimodal Transformer models and applications, and (5) a discussion of open problems and potential research directions for the community.

On the Opportunities and Risks of Foundation Models

2021 斯坦福大学 arxiv

在这篇论文里，斯坦福大学的研究者提出了一个概念“foundation models”用来指代在大规模数据上进行训练，可以用于大范围应用的模型。

下面仅仅是基础概念和发展的笔记，具体请参考论文。

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles (e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities, and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

Joint Multimodal Entity-Relation Extraction Based on Edge-enhanced Graph Alignment Network and Word-pair Relation Tagging

EEGA，https://github.com/YuanLi95/EEGA-for-JMERE，AAAI 2023，联合MNER和MRE。

首个提出将MNER和MRE联合训练的方法，作者将text和image表示为两个graph，然后除了进行visual object和textual entity的对齐，还进行了object-object relation和entity-entity relation的对齐。

Multimodal named entity recognition (MNER) and multimodal relation extraction (MRE) are two fundamental subtasks in the multimodal knowledge graph construction task. However, the existing methods usually handle two tasks independently, which ignores the bidirectional interaction between them. This paper is the first to propose jointly performing MNER and MRE as a joint multimodal entity-relation extraction task (JMERE). Besides, the current MNER and MRE models only consider aligning the visual objects with textual entities in visual and textual graphs but ignore the entity-entity relationships and object-object relationships. To address the above challenges, we propose an edge-enhanced graph alignment network and a word-pair relation tagging (EEGA) for JMERE task. Specifically, we first design a word-pair relation tagging to exploit the bidirectional interaction between MNER and MRE and avoid the error propagation. Then, we propose an edge-enhanced graph alignment network to enhance the JMERE task by aligning nodes and edges in the cross-graph. Compared with previous methods, the proposed method can leverage the edge information to auxiliary alignment between objects and entities and find the correlations between entity-entity relationships and object-object relationships. Experiments are conducted to show the effectiveness of our model.

Neural Architectures for Named Entity Recognition

NAACL 2016，CMU

作者针对NER问题，提出了基于bi-LSTM和CRF（条件随机场）的模型以及transition-based的方法s-LSTM（该模型为详细阅读）。

State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available. In this paper, we introduce two new neural architectures—one based on bidirectional LSTMs and conditional random fields, and the other that constructs and labels segments using a transition-based approach inspired by shift-reduce parsers. Our models rely on two sources of information about words: character-based word representations learned from the supervised corpus and unsupervised word representations learned from unannotated corpora. Our models obtain state-of-the-art performance in NER in four languages without resorting to any language-specific knowledge or resources such as gazetteers.