干货 | 为你解读34篇ACL论文

本文转载自公众号“读芯术”（ID：AI_Discovery）

本文约1000字，建议阅读5分钟。

论文解读共包括Long Papers、Short Papers、Student Research Workshop、System Demonstrations 等几个部分。

ACL2017（www.aclweb.org/anthology/P/P17）共分为 Long Papers、Short Papers、Student Research Workshop、System Demonstrations 等几个部分。以下是我们针对其中34篇论文的翻译及解读。

特别感谢：Stanford - Chris Manning Lab，中科院 - LXC、北邮 - GJF。

ACL 2017 | Long Papers

Affect-LM：一个定制情感文本生成的神经语言模型

Affect-LM:A Neural Language Model for Customizable Affective Text Generation

语义表示研究发展现状综述

The State of the Art in Semantic Representation

PositionRank：一种学术文档关键短语提取的无监督方法

PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents

通过联合嵌入文本和行为信息来处理垃圾评论检测中的冷启动问题

Handling Cold-Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors

基于传播结构核学习的微博谣言检测

Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning

利用深度多模态模型打击人口贩卖

Combating Human Trafficking with Deep Multimodal Models

基于新标注方案的实体与关系联合抽取

Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme

ACL 2017 | Short Papers

关于将NLP研究转化为商业产品所面临的挑战

On the Challenges of Translating NLP Research into Commercial Products

将方言多变性纳入社会公平语言识别

Incorporating Dialectal Variability for Socially Equitable Language Identification

关于上下文感知的神经对话模型的实证研究

An Empirical Study on Context-Aware Neural Conversational Models

利用分词表示学习来提高中文社交网络命名实体识别

Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning

多语言标注框架：关于目标情感分析与预测的社交媒体案例研究

Multilingual Connotation Frames: A Case Study on Social Media for Targeted Sentiment Analysis and Forecast

Salience Rank：基于主题建模的高效关键短语抽取

Salience Rank: Efficient Keyphrase Extraction with Topic Modeling

学习主题敏感的词表示方法

Learning Topic-Sensitive Word Representations

指代消解的词汇特征：谨慎使用

Lexical Features in Coreference Resolution: To be Used With Caution

问答问题中基于大规模细粒度监督数据的迁移学习研究

Question Answering through Transfer Learning from Large Fine-grained Supervision Data

改进文本简化系统的句子对齐方法

Sentence Alignment Methods for Improving Text Simplification Systems

使用特定语境词向量表示改进隐式篇章关系识别

Improving Implicit Discourse Relation Recognition with  Discourse-specific Word Embeddings

List-only实体链接

List-only Entity Linking

基于社会媒体文本的反事实思维识别

Recognizing Counterfactual Thinking in Social Media Texts

基于分组权重共享将领域知识应用于文本分类

Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization

基于时间倾向的推特用户收入预测

Temporal Orientation of Tweets for Predicting Income of Users

意见挖掘中的隐式极性和属性识别

Implicit Polarity and Implicit Aspect Recognition in Opinion Mining

基于核学习传播结构的微博谣言发现

Don’t Count, Predict! An Automatic Approach to Learning Sentiment Lexicons for Short Text

AliMe聊天：基于序列到序列和重排的聊天机器人引擎

AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine

以实体为中心的公司描述生成方法

An Entity-Focused Approach to Generating Company Descriptions

ACL 2017 | Student Research Workshop

特定领域的文本问题自动生成

Domain Specific Automatic Question Generation from Text

改进推文分布式表示-现在与未来

Improving Distributed Representations of Tweets Present and Future

ACL 2017 | System Demonstrations

Olelo:一个生物医学领域的问答系统应用

Olelo:AQuestion Answering Application for Biomedicine

Life-iNet：一个基于网络的结构化生命科学领域知识探索与分析系统

Life-iNet:A Structured Network-Based Knowledge Exploration and Analytics System for LifeSciences

SEMEDICO：一个生命科学领域的综合语义搜索引擎

SEMEDICO: A Comprehensive Semantic Search Engine for the Life Sciences

扩展命名实体识别API及其在语言教育中的应用

Extended Named Entity Recognition API and Its Applications in Language Education

基于JESEME的历时词汇语义学研究

Exploring Diachronic Lexical Semantics with JESEME

笨笨：一个中文智能聊天机器人

Benben: A Chinese Intelligent Conversational Robot