0%

【arxiv论文】 Computation and Language 2020-01-16

发表于 2020-01-17 更新于 2020-03-05 分类于 arxiv ， CL 32k 53 分钟

目录

1. AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [PDF] 摘要

2. A BERT based Sentiment Analysis and Key Entity Detection Approach for Online Financial Texts [PDF] 摘要

3. Authorship Attribution in Bangla literature using Character-level CNN [PDF] 摘要

4. A Continuous Space Neural Language Model for Bengali Language [PDF] 摘要

5. Embedding Compression with Isotropic Iterative Quantization [PDF] 摘要

6. Tensor Graph Convolutional Networks for Text Classification [PDF] 摘要

7. Dialectal Layers in West Iranian: a Hierarchical Dirichlet Process Approach to Linguistic Relationships [PDF] 摘要

8. Urdu-English Machine Transliteration using Neural Networks [PDF] 摘要

9. Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data [PDF] 摘要

10. The empirical structure of word frequency distributions [PDF] 摘要

11. Exploring and Improving Robustness of Multi Task Deep Neural Networks via Domain Agnostic Defenses [PDF] 摘要

12. Detecting New Word Meanings: A Comparison of Word Embedding Models in Spanish [PDF] 摘要

13. Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses [PDF] 摘要

14. FGN: Fusion Glyph Network for Chinese Named Entity Recognition [PDF] 摘要

15. A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation [PDF] 摘要

16. Parallel Machine Translation with Disentangled Context Transformer [PDF] 摘要

17. Robust Speaker Recognition Using Speech Enhancement And Attention Model [PDF] 摘要

18. A Tree Adjoining Grammar Representation for Models Of Stochastic Dynamical Systems [PDF] 摘要

19. Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders [PDF] 摘要

20. Teddy: A System for Interactive Review Analysis [PDF] 摘要

21. Modeling Product Search Relevance in e-Commerce [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-01-15

发表于 2020-01-16 更新于 2020-03-05 分类于 arxiv ， CL 9.7k 16 分钟

目录

1. Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning [PDF] 摘要

2. Balancing the composition of word embeddings across heterogenous data sets [PDF] 摘要

3. Bi-Decoder Augmented Network for Neural Machine Translation [PDF] 摘要

4. On the Replicability of Combining Word Embeddings and Retrieval Models [PDF] 摘要

5. Detecting depression in dyadic conversations with multimodal narratives and visualizations [PDF] 摘要

6. A (Simplified) Supreme Being Necessarily Exists -- Says the Computer! [PDF] 摘要

7. Improved Robust ASR for Social Robots in Public Spaces [PDF] 摘要

8. Faster Transformer Decoding: N-gram Masked Self-Attention [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-01-14

发表于 2020-01-15 更新于 2020-03-05 分类于 arxiv ， CL 33k 54 分钟

目录

1. Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits [PDF] 摘要

2. CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese [PDF] 摘要

3. AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search [PDF] 摘要

4. Mining customer product reviews for product development: A summarization process [PDF] 摘要

5. Joint Reasoning for Multi-Faceted Commonsense Knowledge [PDF] 摘要

6. ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training [PDF] 摘要

7. Stochastic Natural Language Generation Using Dependency Information [PDF] 摘要

8. Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study [PDF] 摘要

9. Revisiting Challenges in Data-to-Text Generation with Fact Grounding [PDF] 摘要

10. Learning Cross-Context Entity Representations from Text [PDF] 摘要

11. PatentTransformer-2: Controlling Patent Text Generation by Structural Metadata [PDF] 摘要

12. Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks [PDF] 摘要

13. Reformer: The Efficient Transformer [PDF] 摘要

14. LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction [PDF] 摘要

15. Negative Statements Considered Useful [PDF] 摘要

16. Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation [PDF] 摘要

17. Shareable Representations for Search Query Understanding [PDF] 摘要

18. Improving Dysarthric Speech Intelligibility Using Cycle-consistent Adversarial Training [PDF] 摘要

19. Structural Decompositions of Epistemic Logic Programs [PDF] 摘要

20. A logic-based relational learning approach to relation extraction: The OntoILPER system [PDF] 摘要

21. Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-01-13

发表于 2020-01-14 更新于 2020-03-05 分类于 arxiv ， CL 11k 18 分钟

目录

1. Towards Minimal Supervision BERT-based Grammar Error Correction [PDF] 摘要

2. Co-evolution of language and agents in referential games [PDF] 摘要

3. Machine Learning Approaches for Amharic Parts-of-speech Tagging [PDF] 摘要

4. Learning to Multi-Task Learn for Better Neural Machine Translation [PDF] 摘要

5. A Scalable Chatbot Platform Leveraging Online Community Posts: A Proof-of-Concept Study [PDF] 摘要

6. Simulating Lexical Semantic Change from Sense-Annotated Data [PDF] 摘要

7. Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs [PDF] 摘要

8. Inductive Document Network Embedding with Topic-Word Attention [PDF] 摘要

9. Linking Social Media Posts to News with Siamese Transformers [PDF] 摘要

阅读全文 »

【论文笔记】Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

发表于 2020-01-12 更新于 2020-01-13 分类于论文笔记 443 1 分钟

Dialog System

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context. Yichi Zhang, Zhijian Ou, Zhou Yu. [PDF]

动机

在对话中，对于同一句话，可以有多种回复。但是，现有模型往往趋于生成出现概率最高的回复，而忽视了概率较低的回复。本文通过数据增强的方法，使得模型具备生成多样化回复的能力。

阅读全文 »

【论文笔记】Integrating Relation Constraints with Neural Relation Extractors

发表于 2020-01-08 更新于 2020-01-12 分类于论文笔记 534 1 分钟

Neural Relation Extraction Relation Constraints

Integrating Relation Constraints with Neural Relation Extractors. Yuan Ye, Yansong Feng, Bingfeng Luo, Yuxuan Lai, Dongyan Zhao. AAAI 2020. [PDF]

动机

在关系抽取任务中，某个关系的所有subject或者object属于同一种类型（如：在“母校”的所有subject都属于“人”），或者多个关系之间往往存在依赖关系（如“城市”和“地区”的subject都是地名），但是现有模型都没有考虑这个约束，只是单独考虑每一个关系。本文工作利用这种约束以提升关系抽取任务的效果。

阅读全文 »

智源社区2019年大会PPT分享

发表于 2020-01-08 53 1 分钟

获取方式 https://mp.weixin.qq.com/s/zqqQVwr16EhqA2zxYUQSWQ

阅读全文 »

【shell】批量删除除了某个文件外的其他所有文件

发表于 2020-01-08 分类于技术杂谈， shell 75 1 分钟

批量删除

1	rm -f !(no_delete_file1\|no_delete_file2)

或者

1	ls \|grep -v no_delete_file \|xargs rm -f