同步公众号(arXiv每日论文速递),欢迎关注,感谢支持哦~
cs.CL 方向,今日共计32篇
【1】 Putting Machine Translation in Context with the Noisy Channel Model
标题:将机器翻译置于噪声信道模型的上下文中
作者: Lei Yu, Chris Dyer
链接:https://arxiv.org/abs/1910.00553
【2】 Type-aware Convolutional Neural Networks for Slot Filling
标题:用于缝隙填充的类型感知卷积神经网络
作者: Heike Adel, Hinrich Schütze
链接:https://arxiv.org/abs/1910.00546
【3】 BillSum: A Corpus for Automatic Summarization of US Legislation
标题:BillSum:美国立法自动摘要语料库
作者: Anastassia Kornilova, Vlad Eidelman
链接:https://arxiv.org/abs/1910.00523
【4】 Detecting Alzheimer's Disease by estimating attention and elicitation path through the alignment of spoken picture descriptions with the picture prompt
标题:通过将口头图像描述与图像提示对齐来估计注意力和启发路径来检测阿尔茨海默病
作者: Bahman Mirheidari, Heidi Christensen
链接:https://arxiv.org/abs/1910.00515
【5】 Dialogue Transformers
标题:对话变压器
作者: Vladimir Vlasov, Alan Nichol
链接:https://arxiv.org/abs/1910.00486
【6】 Machine Translation for Machines: the Sentiment Classification Use Case
标题:机器的机器翻译:情感分类用例
作者: Amirhossein Tebbifakhr, Marco Turchi
链接:https://arxiv.org/abs/1910.00478
【7】 MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
标题:MMM:多选择阅读理解的多阶段多任务学习
作者: Di Jin, Dilek Hakkani-tur
备注:Submitted to AAAI 2020, under review
链接:https://arxiv.org/abs/1910.00458
【8】 Global Voices: Crossing Borders in Automatic News Summarization
标题:全球之声:在自动新闻摘要中跨越国界
作者: Khanh Nguyen, Hal Daumé III
备注:NewSum workshop at EMNLP 2019, 7 pages
链接:https://arxiv.org/abs/1910.00421
【9】 Latent-Variable Generative Models for Data-Efficient Text Classification
标题:用于数据高效文本分类的潜变量生成模型
作者: Xiaoan Ding, Kevin Gimpel
备注:11 pages, EMNLP 2019
链接:https://arxiv.org/abs/1910.00382
【10】 A Survey of Methods to Leverage Monolingual Data in Low-resource Neural Machine Translation
标题:低资源神经网络机器翻译中利用单语数据的方法综述
作者: Ilshat Gibadullin, Adil Khan
备注:Presented in ICATHS'19
链接:https://arxiv.org/abs/1910.00373
【11】 Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair
标题:低资源机器翻译技术在俄语-鞑靼语言对中的应用
作者: Aidar Valeev, Adil Khan
备注:Presented on ICATHS'19
链接:https://arxiv.org/abs/1910.00368
【12】 Grammatical Error Correction in Low-Resource Scenarios
标题:低资源场景中的语法错误校正
作者: Jakub Náplava, Milan Straka
链接:https://arxiv.org/abs/1910.00353
【13】 TMLab: Generative Enhanced Model (GEM) for adversarial attacks
标题:TMLab:对抗攻击的生成增强模型(GEM)
作者: Piotr Niewinski, Maria Janicka
链接:https://arxiv.org/abs/1910.00337
【14】 When and Why is Document-level Context Useful in Neural Machine Translation?
标题:何时以及为什么文档级上下文在神经机器翻译中有用?
作者: Yunsu Kim, Hermann Ney
备注:DiscoMT 2019 camera-ready
链接:https://arxiv.org/abs/1910.00294
【15】 Bad Form: Comparing Context-Based and Form-Based Few-Shot Learning in Distributional Semantic Models
标题:不良形式:分布式语义模型中基于上下文和基于形式的少发学习的比较
作者: Jeroen Van Hautte, Marek Rei
备注:Accepted to the Proceedings of the Second Workshop on Deep Learning for Low-Resource NLP (DeepLo 2019)
链接:https://arxiv.org/abs/1910.00275
【16】 Multilingual End-to-End Speech Translation
标题:多语言端到端语音翻译
作者: Hirofumi Inaguma, Shinji Watanabe
备注:Accepted to ASRU 2019
链接:https://arxiv.org/abs/1910.00254
【17】 Analyzing Sentence Fusion in Abstractive Summarization
标题:摘要中的句子融合分析
作者: Logan Lebanoff, Fei Liu
链接:https://arxiv.org/abs/1910.00203
【18】 Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
标题:使用预先训练的上下文单词表示的改进的词义消歧
作者: Christian Hadiwinoto, Wee Chung Gan
备注:10 pages, 2 figures, EMNLP 2019
链接:https://arxiv.org/abs/1910.00194
【19】 Writing habits and telltale neighbors: analyzing clinical concept usage patterns with sublanguage embeddings
标题:写作习惯和告密邻居:用子语言嵌入分析临床概念使用模式
作者: Denis Newman-Griffis, Eric Fosler-Lussier
备注:LOUHI 2019 (co-located with EMNLP)
链接:https://arxiv.org/abs/1910.00192
【20】 Specializing Word Embeddings (for Parsing) by Information Bottleneck
标题:通过信息瓶颈专门化单词嵌入(用于解析)
作者: Xiang Lisa Li, Jason Eisner
备注:Accepted for publication at EMNLP 2019
链接:https://arxiv.org/abs/1910.00163
【21】 Interrogating the Explanatory Power of Attention in Neural Machine Translation
标题:质疑神经机器翻译中注意的解释力
作者: Pooya Moradi, Anoop Sarkar
备注:Accepted at the 3rd Workshop on Neural Generation and Translation (WNGT 2019) held at EMNLP-IJCNLP 2019 (Camera ready)
链接:https://arxiv.org/abs/1910.00139
【22】 Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power
标题:词汇特征更易受攻击,句法特征具有更强的预测力
作者: Jekaterina Novikova, Frank Rudzicz
备注:EMNLP Workshop on Noisy User-generated Text (W-NUT 2019)
链接:https://arxiv.org/abs/1910.00065
【23】 Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations
标题:具有多样性的多头注意学习扎根多语言多模态表征
作者: Po-Yao Huang, Alexander Hauptmann
备注:Accepted at EMNLP 2019
链接:https://arxiv.org/abs/1910.00058
【24】 Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
标题:基于递归神经网络DAG文法的语义图分析
作者: Federico Fancellu, Mirella Lapata
备注:9 pages, to appear in EMNLP2019
链接:https://arxiv.org/abs/1910.00051
【25】 VOnDA: A Framework for Ontology-Based Dialogue Management
标题:Vonda:一种基于本体的对话管理框架
作者: Bernd Kiefer, Christophe Biwer
备注:Presented at the Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS), April 24-26, 2019
链接:https://arxiv.org/abs/1910.00340
【26】 Towards French Smart Building Code: Compliance Checking Based on Semantic Rules
标题:走向法国智能建筑规范:基于语义规则的符合性检查
作者: Nicolas Bus (CSTB), Muhammad Fahad (CSTB)
链接:https://arxiv.org/abs/1910.00334
【27】 A Multi-Modal Feature Embedding Approach to Diagnose Alzheimer Disease from Spoken Language
标题:从口语中诊断阿尔茨海默病的多模态特征嵌入方法
作者: S. Soroush Haj Zargarbashi, Bagher Babaali
链接:https://arxiv.org/abs/1910.00330
【28】 BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using Topics and Attention Based Query-Document-Sentence Interactions
标题:BioNLP-OST 2019 RDoC任务:使用主题和基于注意力的查询-文档-句子交互的多粒度神经相关性排序
作者: Yatin Chaudhary, Hinrich Schütze
备注:EMNLP2019, 10 pages, 2 figures, 7 tables
链接:https://arxiv.org/abs/1910.00314
【29】 Generalization in Generation: A closer look at Exposure Bias
标题:世代中的泛化:对曝光偏差的更近距离观察
作者: Florian Schmidt
备注:wngt2019 camera ready
链接:https://arxiv.org/abs/1910.00292
【30】 Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
标题:基于文档图网络的多跳问题回答的支持事实识别
作者: Mokanarangan Thayaparan, Andre Freitas
链接:https://arxiv.org/abs/1910.00290
【31】 Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs
标题:在不完全知识图上回答逻辑查询时的上下文图注意
作者: Gengchen Mai, Ni Lao
备注:8 pages, 3 figures, camera ready version of article accepted to K-CAP 2019, Marina del Rey, California, United States
链接:https://arxiv.org/abs/1910.00084
【32】 Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health
标题:用于细粒度意见挖掘和公共卫生的弱监督注意网络
作者: Giannis Karamanolakis, Luis Gravano
备注:Accepted for the 5th Workshop on Noisy User-generated Text (W-NUT 2019), held in conjunction with EMNLP 2019
链接:https://arxiv.org/abs/1910.00054
机器翻译,仅供参考
网友评论