尝试进行实体识别
使用简单的分词和词性标注以及关键词计算尝试进行实体识别
情况不太好
prinsiple.py
使用南京大学的学生手册印证如下
总词数4000+（无重复）名词加入范围
对于学生手册由于不是小说，所以人名实体和地点实体都很少，更多的是概念和物品
下一步考虑使用关键词和词性进行交叉验证，(使用福尔摩斯的小说进行试验的时候，提取人名实体的情况比较优秀)
若有收获，就点个赞吧
0 人点赞
初试实体识别
- 学术小记
- 2022.05
- 2022.03
- 22.03.08 Improving Evidence Retrieval for Automated Explainable Fact-Checking
- 22.03.07 Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
- 22.03.05 Controllable Natural Language Generation with Contrastive Prefixes
- 22.03.05 Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks
- 22.03.05 Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding
- 22.03.04 SpanBert
- 22.03.02 Improving Language Models by Retrieving from Trillions of Tokens
- 22.03.02 Retrieval Augmented NLP
- 22.03.01 Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
- 2022.02
- 22.02.28 Bert-Whitening
- 22.02.27 各向异性
- 22.02.27 Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
- 22.02.26 Impact of Pretraining Term Frequencies on Few-Shot Reasoning
- 22.02.19 A Primer in BERTology: What We Know About How BERT Works
- 22.02.19 模型压缩 From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression
- 2022.01
- 2021.12
- 21.12.30 Robust Neural Machine Translation with Doubly Adversarial Inputs
- 21.12.30 Towards a Universal Continuous Knowledge Base 连续性知识库
- 21.12.20 Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
- 21.12.20 Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
- 21.12.20 FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization
- 21.12.20 Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
- 21.12.20 Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization
- 21.12.20 Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization [NIPS19]
- 21.12.19 Improving Truthfulness of Headline Generation
- 21.12.18 Multi-Fact Correction in Abstractive Text Summarization.
- 21.12.18 Reducing Quantity Hallucinations in Abstractive Summarization【EMNLP20】
- 21.12.18 GO FIGURE: A Meta Evaluation of Factuality in Summarization
- 21.12.18 Truth or Error? Towards systematic analysis of factual errors in abstractive summaries
- 21.12.17 Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation
- 21.12.17 Detecting Hallucinated Content in Conditional Neural Sequence Generation
- 21.12.16 Assessing The Factual Accuracy of Generated Text
- 21.12.15 Enhancing Factual Consistency of Abstractive Summarization
- 21.12.15 QuestEval: Summarization Asks for Fact-based Evaluation
- 21.12.11 Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection 【NAACL2021】
- 21.12.9 Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks
- 21.12.2 Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics
- 21.12.2 Annotating and Modeling Fine-grained Factuality in Summarization
- 21.12.1 Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization
- 21.12.1 Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries
- 2021.11
- 21.11.30 MOFE: MIXTURE OF FACTUAL EXPERTS FOR CONTROLLING HALLUCINATIONS IN ABSTRACTIVE SUMMARIZATION
- 21.11.30 Fine-grained Factual Consistency Assessment for Abstractive Summarization Models 【EMNLP21】
- 21.11.30 Dialogue Inspectional Summarization with Factual Inconsistency Awareness
- 21.11.30 SUMMAC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization 【TACL】
- 21.11.29 Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization [EMNLP21]
- 21.11.28
- 21.11.27 Factual Probing Is [MASK]: Learning vs. Learning to Recall【NAACL2021】
- 21.11.27 BARTSCORE: Evaluating Generated Text as Text Generation 【NIPS2021】
- 21.11.26 Prefix-Tuning: Optimizing Continuous Prompts for Generation [ACL2021]
- 21.11.24 相似度分析
- 21.11.22 DEEP: DEnoising Entity Pre-training for Neural Machine Translation
- 21.11.22 NJU HPC Tips
- 21.11.22 NLP多进程处理框架 如何高效处理文本？
- 21.11.19 BM25和TFIDF转载
- 21.11.19 SJL博客6篇
- 21.11.18 转载苏巨 Bert初始化以及Norm，梯度消失的讨论
- 21.11.18 SJL博客8篇
- 21.11.18 Discourse Understanding and Factual Consistency in Abstractive Summarization EACL2021
- 21.11.17 SJL博客3篇
- 21.11.16 Factual Error Correction for Abstractive Summarization Models EMNLP20 short
- 21.11.16 NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
- 21.11.15 初步做的论文Servey
- 21.11.6 EMNLP2021 论文预讲笔记
- 21.11.5 Fairseq Code review
- 21.11.4 PEGASUS Pre-training with Extracted Gap-sentences for Abstractive Summarization【ICML 2020】
- 21.11.3 On Faithfulness and Factuality in Abstractive Summarization【ACL 2020】
- 21.11.1 BERTSCORE: EVALUATING TEXT GENERATION WITH BERT 【ICLR2020】
- 21.11.1 Focus Attention: Promoting Faithfulness and Diversity in Summarization【ACL2021】 pending
- 21.11.1 采样策略
- 2021.10
- 21.10.31 Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation 【EMNLP2021】
- 21.10.29 Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization
- 21.10.27 MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization 【EMNLP2021】
- 21.10.26 Improving Factual Consistency of Abstractive Summarization via Question Answering 【pending】
- 21.10.25 Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization
- 21.10.24 CTRLSUM: TOWARDS GENERIC CONTROLLABLE TEXT SUMMARIZATION
- 21.10.20 Training Dynamics for Text Summarization Models
- 21.10.15 GSum: A General Framework for Guided Neural Abstractive Summarization 【NAACL 2021】
- 21.10.10 VAETransformer进一步实验
- 21.10.3 CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization 【EMNLP2021】
- 21.10.1 Controllable Neural Dialogue Summarization with Personal Named Entity Planning 【EMNLP2021】
- 2021.9
- Before
- 奇怪的技巧
- 懒得整理
- 以前的论文笔记
- 事实一致性
- 对话摘要 Dialog Summarization
- Two-stage encoding Extractive Summarization
- Neural Document Summarization by Jointly Learning to Score and Select Sentences
- CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
- CoLAKE: Contextualized Language and Knowledge Embedding
- A Closer Look at Data Bias in Neural Extractive Summarization Models
- Deep Communicating Agents for Abstractive Summarization
- Abstractive News Summarization based on Event Semantic Link Network
- A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
- BART Denoising
- What Have We Achieved on Text Summarization?
- Abstractive Summarization: A Survey of the State of the Art
- Summary Level Training of Sentence Rewriting for Abstractive Summarization
- Heterogeneous Graph Neural Networks
- STRUCTURED NEURAL SUMMARIZATION
- Text Summarization with Pretrained Encoders
- SummaRuNNer
- Attention is All you Need
- Toward Making the Most of Context in NMT
- Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
- Text Summarization Techniques
- Extractive Summarization as Text Matching
暂无相关搜索结果！
让时间为你证明
