回顧:EMNLP2017論文集28篇論文解讀
EMNLP(Conference on Empirical Methods in Natural Language Processing)是自然語言處理領域的頂級會議,由ACL學會下屬特殊興趣小組 SIGDAT(ACL Special Interest Group on Linguistic data and Corpus-based Approaches to NLP)組織,每年召開一次。EMNLP2017已於2017年9月7-11日在丹麥哥本哈根市召開。
本文對讀芯術之前關於EMNLP2017的部分論文解讀進行了匯總,希望能有幫助到你的地方。
讀芯術讀者論文交流群,請加小編微信號:zhizhizhuji。等你。
EMNLP 2017 | Regular Papers
點擊相應標題進入詳情頁
NITE:針對特定領域命名實體識別的神經網路歸納學習框架
NITE: A Neural Inductive Teaching Framework for Domain-Specific NER
政治競選演講中的主題籤名
Topic Signatures in Political Campaign Speeches
推特論證挖掘 - 論點、事實和來源
Argument Mining on Twitter: Arguments, Facts and Sources
控制人類對基本用戶特徵的感知
Controlling Human Perception of Basic User Traits
利用觀眾聊天反應的視頻集錦預測
Video Highlight Prediction Using Audience Chat Reactions
不同陰影下的真相:虛假新聞與政治事實審查中的語言分析
Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking
將結構化引入摘要:眾包概念圖的基準語料庫
Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps
EMNLP 2017 | Long Papers
點擊相應標題進入詳情頁
針對基於社交媒體的藥物使用預測的多視圖無監督用戶特徵嵌入
Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction
基於閱讀時眼球運動分析的輕度認知障礙檢測
An analysis of eye-movements during reading for the detection of mild cognitive impairment
在線網路犯罪市場中識別產品:一個細粒度域適應的數據集
Identifying Products in Online Cybercrime Marketplaces: A Dataset for Fine-grained Domain Adaptation
一種基於深度神經網路的生物醫學文獻洞察提取系統
An Insight Extraction System on BioMedical Literature with Deep Neural Networks
學慣用法律依據預測刑事案件的指控
Learning to Predict Charge for Criminal Cases with Legal Basis
基於在線論壇的抑鬱症和自我傷害的風險評估
Depression and Self-Harm Risk Assessment in Online Forums
EMNLP 2017 | System Demonstrations
點擊相應標題進入詳情頁
NLTK框架API: 豐富語言資源的可發現性設計
The NLTK FrameNet API: Designing for Discoverability with a Rich Linguistic Resource
事件新聞推文的互動式摘要生成
Interactive Abstractive Summarization for Event News Tweets
HeidelPlace - 一個Geoparsing的可擴展框架
HeidelPlace: An Extensible Framework for Geoparsing
MoodSwipe - 一種根據用戶特定情緒來推薦信息的軟鍵盤
MoodSwipe: A Soft Keyboard that Suggests Messages Based on User-Specified Emotions
GraphDocExplore:一個基於圖的文檔搜索技術實驗比較框架
GraphDocExplore: A Framework for the Experimental Comparison of Graph-based Document Exploration Techniques
SGNMT—一個用於新模型和搜索策略快速原型設計的靈活NMT解碼平台
SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
Argotario: 計算論辯遇到嚴肅遊戲
Argotario: Computational Argumentation Meets Serious Games
一個用於語言概念案例研究學習的分析和可視化工具
An Analysis and Visualization Tool for Case Study Learning of Linguistic Concepts
KnowYourNyms?一種語義關係改編遊戲
KnowYourNyms? A Game of Semantic Relationships Adaptation
QUINT: 知識庫上的解釋性問答
QUINT: Interpretable Question Answering over Knowledge Bases
DLATK: 差別語言分析工具箱
DLATK: Differential Language Analysis ToolKit
ParlAI: 一個對話研究軟體平台
ParlAI: A Dialog Research Software Platform
函數助手:用於NL查詢API的工具
Function Assistant: A Tool for NL Querying of APIs
基於注意力神經網路機器翻譯的互動式可視化和操控
Interactive Visualization and Manipulation of Attention-based Neural Machine Translation
NeuroNER:一個基於神經網路的簡單易用的命名實體識別程序
NeuroNER: an easy-to-use program for named-entity recognition based on neural networks
留言 點贊 發個朋友圈
我們一起探討AI落地的最後一公里
※今日芯聲:「AI+IoT」是未來的風口,也是小米核心戰略
※今日芯聲:僱主忽視矽谷員工的強烈抗議,堅持服務軍方,為何?
TAG:讀芯術 |