【ACL2020放榜!】事件抽取、关系抽取、NER、Few-Shot 相关论文整理

2020 年 5 月 22 日 深度学习自然语言处理
【ACL2020放榜!】事件抽取、关系抽取、NER、Few-Shot 相关论文整理

重磅!ACL2020 官方放榜啦!传送门: https://acl2020.org/program/accepted/



小编在此整理出了一份事件抽取关系抽取命名实体识别Few-Shot以及在模型中使用GCN和其他一些感兴趣相关论文的列表,希望可以为需要的小伙伴提供便利吖~

(深夜整理,就不放链接了/(ㄒoㄒ)/~~)

事件抽取

  • Cross-media Structured Common Space for Multimedia Event Extraction

  • Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event

  • Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding

  • Improving Event Detection via Open-domain Trigger Knowledge

  • A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal

  • A Two-Step Approach for Implicit Event Argument Detection

关系抽取

  • A Novel Cascade Binary Tagging Framework for Relational Triple Extraction

  • Dialogue-Based Relation Extraction

  • Exploiting the Syntax-Model Consistency for Neural Relation Extraction

  • Generalizing Natural Language Analysis through Span-relation Representations

  • In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts

  • Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts

  • Probing Linguistic Features of Sentence-Level Representations in Relation Extraction

  • Rationalizing Medical Relation Prediction from Corpus-level Statistics

  • Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

  • Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents

  • TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task

  • Towards Understanding Gender Bias in Relation Extraction

  • TransS-Driven Joint Learning Architecture for Implicit Discourse Relation Recognition

  • ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages

  • A Relational Memory-based Embedding Model for Triple Classification and Search Personalization

  • Implicit Discourse Relation Classification: We Need to Talk about Evaluation

  • Relation Extraction with Explanation

  • Revisiting Unsupervised Relation Extraction

命名实体识别

  • An Effective Transition-based Model for Discontinuous NER

  • Multi-Cell Compositional LSTM for NER Domain Adaptation

  • Simplify the Usage of Lexicon in Chinese NER

  • Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language

  • FLAT: Chinese NER Using Flat-Lattice Transformer

  • TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition

  • A Unified MRC Framework for Named Entity Recognition

  • Bipartite Flat-Graph Network for Nested Named Entity Recognition

  • Code and Named Entity Recognition in StackOverflow

  • Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer

  • Multi-Domain Named Entity Recognition with Genre-Aware and Agnostic Inference

  • Named Entity Recognition without Labelled Data: A Weak Supervision Approach

  • Pyramid: A Layered Model for Nested Named Entity Recognition

  • Sources of Transfer in Multilingual Named Entity Recognition

  • Temporally-Informed Analysis of Named Entity Recognition

  • Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling

  • Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

  • Named Entity Recognition as Dependency Parsing

  • Soft Gazetteers for Low-Resource Named Entity Recognition

Few-Shot

  • Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

  • Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks

  • Dynamic Memory Induction Networks for Few-Shot Text Classification

  • Few-Shot NLG with Pre-Trained Language Model

  • Shaping Visual Representations with Language for Few-Shot Classification

  • Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations

GCN-based

  • Aligned Dual Channel Graph Convolutional Network for Visual Question Answering

  • Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics

  • Bipartite Flat-Graph Network for Nested Named Entity Recognition

  • Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension

  • Fine-grained Fact Verification with Kernel Graph Attention Network

  • GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media

  • Graph Neural News Recommendation with Unsupervised Preference Disentanglement

  • Heterogeneous Graph Neural Networks for Extractive Document Summarization

  • Heterogeneous Graph Transformer for Graph-to-Sequence Learning

  • Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection

其他~

  • BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection

  • Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding

  • Relational Graph Attention Network for Aspect-based Sentiment Analysis

  • Neighborhood Matching Network for Entity Alignment

  • Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification

  • SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction

  • Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations

整理过程中可能有疏漏错误之处(尤其是分类),请大家多多包含呐~(●'◡'●)




投稿或交流学习,备注: 昵称-学校(公司)-方向,进入DL&NLP交流群。
方向有很多: 机器学习、深度学习,python,情感分析、意见挖掘、句法分析、机器翻译、人机对话、知识图谱、语音识别等
记得备注呦


登录查看更多
14

相关内容

事件抽取指的是从非结构化文本中抽取事件信息,并将其以结构化形式呈现出来的任务。例如从“毛泽东1893 年出生于湖南湘潭”这句话中抽取事件{类型:出生,人物:毛泽东,时间:1893 年,出生地:湖南湘潭}。 事件抽取任务通常包含事件类型识别和事件元素填充两个子任务。

【导读】自然语言处理顶会ACL2020本周公布了接受论文,在这里专知小编整理20篇ACL2020论文,来自世界各地顶级学术单位,涉及BERT、表示学习、对话、偏见等,看下2020NLP在研究什么

The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020) 将于2020年7月5日至10日在美国华盛顿州西雅图举行。ACL年会是计算语言学和自然语言处理领域最重要的顶级国际会议,CCF A类会议,由计算语言学协会主办,每年举办一次。其接收的论文覆盖了对话交互系统、语义分析、摘要生成、信息抽取、问答系统、文本挖掘、机器翻译、语篇语用学、情感分析和意见挖掘、社会计算等自然语言处理领域众多研究方向。该会议的论文基本代表自然语言处理领域最新研究进展和最高研究水平,受到学术界和产业界的高度关注。

  1. BPE-Dropout:简单有效的子词正则化,Simple and Effective Subword Regularization,俄罗斯Yandex https://arxiv.org/abs/1910.13267

  1. 预训练语言模型中的跨语言结构,Emerging Cross-lingual Structure in Pretrained Language Models,Facebook

https://arxiv.org/abs/1911.01464

  1. 大规模无监督跨语言表示学习,Unsupervised Cross-lingual Representation Learning at Scale,Facebook AI

https://arxiv.org/abs/1911.02116

  1. 学习鲁棒度量的文本生成,BLEURT: Learning Robust Metrics for Text Generation,Google

https://arxiv.org/pdf/2004.04696.pdf

  1. 基于领域自适应的减少神经机器翻译中的性别偏见,Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem,剑桥大学

https://arxiv.org/pdf/2004.04498.pdf

  1. 在语言模型中注入数值推理技巧,Injecting Numerical Reasoning Skills into Language Models,Allen AI https://arxiv.org/pdf/2004.04487.pdf

  2. 多轮对话数据集,MuTual: A Dataset for Multi-Turn Dialogue Reasoning,浙大,微软

https://arxiv.org/pdf/2004.04494.pdf

  1. TAPAS:通过预训练进行的弱监督表解析,TAPAS: Weakly Supervised Table Parsing via Pre-training,谷歌

https://arxiv.org/pdf/2004.02349.pdf

  1. 提高神经语言模型句法能力,An analysis of the utility of explicit negative examples to improve the syntactic abilities of neural language models,谷歌

https://arxiv.org/pdf/2004.02451.pdf

  1. 多级学习排序的层次实体标注,Hierarchical Entity Typing via Multi-level Learning to Rank,霍普金斯大学

https://arxiv.org/pdf/2004.02286.pdf

  1. 数据操作:通过学习增加和调整权重,实现有效的实例学习,生成神经对话,Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight,中科院计算所

https://arxiv.org/pdf/2004.02594.pdf

  1. 法律判决,Distinguish Confusing Law Articles for Legal Judgment Prediction,西安交大 https://arxiv.org/pdf/2004.02557.pdf

  2. MobileBERT:用于资源受限设备的任务无关“瘦版”BERT,MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices,谷歌https://arxiv.org/pdf/2004.02984.pdf

  3. 信息论探索语言结构,Information-Theoretic Probing for Linguistic Structure,剑桥

https://arxiv.org/pdf/2004.03061.pdf

  1. 多方对话学习层次结构,Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering,EMORY

https://arxiv.org/pdf/2004.03561.pdf

  1. 对话学习器,Conversation Learner – A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems,微软

https://arxiv.org/pdf/2004.04228.pdf

  1. 反对网络仇恨言论的反叙述:数据和策略,Generating Counter Narratives against Online Hate Speech: Data and Strategies

https://arxiv.org/pdf/2004.04216.pdf

  1. 多语言序列标记的结构层次知识提取,Structure-Level Knowledge Distillation For Multilingual Sequence Labeling,上科大,阿里巴巴达摩院

https://arxiv.org/pdf/2004.03846.pdf

  1. 基于角色感知奖励分解的多代理面向任务的对话策略学习,Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition,清华大学

https://arxiv.org/pdf/2004.03809.pdf

  1. FastBERT:一种具有自适应推理时间的自适应BERT?,FastBERT: a Self-distilling BERT with Adaptive Inference Time,北京大学,腾讯

https://arxiv.org/pdf/2004.02178.pdf

成为VIP会员查看完整内容
0
90

To understand a scene in depth not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them. However, since the distribution of real-world relationships is seriously unbalanced, existing methods perform quite poorly for the less frequent relationships. In this work, we find that the statistical correlations between object pairs and their relationships can effectively regularize semantic space and make prediction less ambiguous, and thus well address the unbalanced distribution issue. To achieve this, we incorporate these statistical correlations into deep neural networks to facilitate scene graph generation by developing a Knowledge-Embedded Routing Network. More specifically, we show that the statistical correlations between objects appearing in images and their relationships, can be explicitly represented by a structured knowledge graph, and a routing mechanism is learned to propagate messages through the graph to explore their interactions. Extensive experiments on the large-scale Visual Genome dataset demonstrate the superiority of the proposed method over current state-of-the-art competitors.

0
3
下载
预览

We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.

0
13
下载
预览

The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high precision and recall only when manual annotations for each website are available. Although there have been efforts to learn extractors from automatically-generated labels, these methods are not sufficiently robust to succeed in settings with complex schemas and information-rich websites. In this paper we present a new method for automatic extraction from semi-structured websites based on distant supervision. We automatically generate training labels by aligning an existing knowledge base with a web page and leveraging the unique structural characteristics of semi-structured websites. We then train a classifier based on the potentially noisy and incomplete labels to predict new relation instances. Our method can compete with annotation-based techniques in the literature in terms of extraction quality. A large-scale experiment on over 400,000 pages from dozens of multi-lingual long-tail websites harvested 1.25 million facts at a precision of 90%.

0
6
下载
预览

Knowledge Graph Embedding methods aim at representing entities and relations in a knowledge base as points or vectors in a continuous vector space. Several approaches using embeddings have shown promising results on tasks such as link prediction, entity recommendation, question answering, and triplet classification. However, only a few methods can compute low-dimensional embeddings of very large knowledge bases. In this paper, we propose KG2Vec, a novel approach to Knowledge Graph Embedding based on the skip-gram model. Instead of using a predefined scoring function, we learn it relying on Long Short-Term Memories. We evaluated the goodness of our embeddings on knowledge graph completion and show that KG2Vec is comparable to the quality of the scalable state-of-the-art approaches and can process large graphs by parsing more than a hundred million triples in less than 6 hours on common hardware.

0
7
下载
预览

We report an evaluation of the effectiveness of the existing knowledge base embedding models for relation prediction and for relation extraction on a wide range of benchmarks. We also describe a new benchmark, which is much larger and complex than previous ones, which we introduce to help validate the effectiveness of both tasks. The results demonstrate that knowledge base embedding models are generally effective for relation prediction but unable to give improvements for the state-of-art neural relation extraction model with the existing strategies, while pointing limitations of existing methods.

0
8
下载
预览

Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data. One of the most effective methods in representing knowledge graphs is to embed symbolic relations and entities into continuous spaces, where relations are approximately linear translation between projected images of entities in the relation space. However, state-of-the-art relation projection methods such as TransR, TransD or TransSparse do not model the correlation between relations, and thus are not scalable to complex knowledge graphs with thousands of relations, both in computational demand and in statistical robustness. To this end we introduce TransF, a novel translation-based method which mitigates the burden of relation projection by explicitly modeling the basis subspaces of projection matrices. As a result, TransF is far more light weight than the existing projection methods, and is robust when facing a high number of relations. Experimental results on the canonical link prediction task show that our proposed model outperforms competing rivals by a large margin and achieves state-of-the-art performance. Especially, TransF improves by 9%/5% in the head/tail entity prediction task for N-to-1/1-to-N relations over the best performing translation-based method.

0
4
下载
预览

The task of event extraction has long been investigated in a supervised learning paradigm, which is bound by the number and the quality of the training instances. Existing training data must be manually generated through a combination of expert domain knowledge and extensive human involvement. However, due to drastic efforts required in annotating text, the resultant datasets are usually small, which severally affects the quality of the learned model, making it hard to generalize. Our work develops an automatic approach for generating training data for event extraction. Our approach allows us to scale up event extraction training instances from thousands to hundreds of thousands, and it does this at a much lower cost than a manual approach. We achieve this by employing distant supervision to automatically create event annotations from unlabelled text using existing structured knowledge bases or tables.We then develop a neural network model with post inference to transfer the knowledge extracted from structured knowledge bases to automatically annotate typed events with corresponding arguments in text.We evaluate our approach by using the knowledge extracted from Freebase to label texts from Wikipedia articles. Experimental results show that our approach can generate a large number of high quality training instances. We show that this large volume of training data not only leads to a better event extractor, but also allows us to detect multiple typed events.

0
6
下载
预览
小贴士
相关VIP内容
相关论文
Tianshui Chen,Weihao Yu,Riquan Chen,Liang Lin
3+阅读 · 2019年3月8日
Tongtao Zhang,Heng Ji
13+阅读 · 2018年4月21日
Yu Su,Honglei Liu,Semih Yavuz,Izzeddin Gur,Huan Sun,Xifeng Yan
10+阅读 · 2018年4月19日
Colin Lockard,Xin Luna Dong,Arash Einolghozati,Prashant Shiralkar
6+阅读 · 2018年4月12日
Simon Gottschalk,Elena Demidova
9+阅读 · 2018年4月12日
Shaohui Liu,Yi Wei,Jiwen Lu,Jie Zhou
3+阅读 · 2018年3月27日
Tommaso Soru,Stefano Ruberto,Diego Moussallem,Edgard Marx,Diego Esteves,Axel-Cyrille Ngonga Ngomo
7+阅读 · 2018年3月21日
Kien Do,Truyen Tran,Svetha Venkatesh
4+阅读 · 2018年1月26日
Ying Zeng,Yansong Feng,Rong Ma,Zheng Wang,Rui Yan,Chongde Shi,Dongyan Zhao
6+阅读 · 2017年12月11日
Top