ACL 2017接受了哪些論文？這份可視化分析讓你輕鬆看懂

選自ACL 2017

機器之心報道

參與：蔣思源

國際計算語言學協會 (ACL，The Association for Computational Linguistics)，是世界上影響力最大、最具活力的國際學術組織之一，其會員遍佈世界各地。

國際計算語言學協會（ACL）第 55 屆年會將在加拿大溫哥華舉行。這一次會議將於 2017 年 7 月 30 日至 8 月 4 日在溫哥華市中心的威斯汀灣海岸酒店（Westin Bayshore Hotel）舉辦。

ACL 2017 除了主要會議之外，還如同其他頂級會議一樣包含研討會、專題報告、研習會和演示等。ACL 會議是計算語言學領域的首要會議，廣泛涉及自然語言的計算方法及其各類研究領域。

下面列出了 ACL 2017 所接收的長篇論文、短篇論文和軟件展示，所有論文或展示採取分類無序排列。

恭喜作者們！

在我們詳細瞭解這些論文和作者之前，可以通過可視化看一看 ACL 2017 接收論文的標題特點與分佈。

該可視化的項目地址：http://nbviewer.jupyter.org/github/JasonKessler/jasonkessler.github.io/blob/master/Analysis-of-Accepted-ACL-2017-Papers.ipynb

首先如下圖所示，我們可以瞭解短篇論文和長篇論文標題的不同之處。端到端建模、聯合建模、對抗性學習和閱讀理解在長篇論文標題中較為普遍。案例研究、社交媒體和多語言分析在短篇論文中更為流行。學習、神經和翻譯在兩組論文中都很常見。

下圖展示了 TACL 與長篇論文的區別。有趣的是沒有 TACL 使用「網絡」這一單詞，但長篇論文很多都使用了。

下面幾張可視化圖表展示了 ACL 2017 接收論文的一些描述性統計學數據，並能瞭解論文類別的變化。

其中我們可以發現絕大多數論文都是長篇論文。機器翻譯、語義學和總結性的更多是長篇論文，而機器學習、社交媒體和多學科論文更多是短篇論文。

下面是具體的 ACL 2017 接收論文和軟件展示等名單（由於篇幅限制，以下只展示了部分接收的長篇論文，完整名單請點擊「閱讀原文」查閱）。

接收長篇論文

生物醫學（Biomedical/共 1 篇）

• Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts

• Authors: Leandro Santos, Edilson Anselmo Corrêa Júnior, Osvaldo Oliveira Jr, Diego Amancio, Letícia Mansur and Sandra Aluísio

認知建模與心理語言學（Cognitive Modelling and Psycholinguistics/共 3 篇）

• Representations of language in a model of visually grounded speech signal

• Authors: Grzegorz Chrupała, Lieke Gelderloos and Afra Alishahi

• Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance

• Authors: Yang Xu and David Reitter

交互式對話系統（Dialog Interactive Systems/共 13 篇）

• Adversarial Adaptation of Synthetic or Stale Data

• Authors: Young-Bum Kim, Karl Stratos and Dongchan Kim

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

• Authors: Sayan Ghosh, Mathieu Chollet, Eugene Laksana, Stefan Scherer and Louis-Philippe Morency

語篇語用學（Discourse Pragmatics/共 8 篇）

• Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification

• Authors: Lianhui Qin, Zhisong Zhang, Hai Zhao, Eric Xing and Zhiting Hu

• Argument Mining with Structured SVMs and RNNs

• Authors: Vlad Niculae, Claire Cardie and Joonsuk Park

摘要生成（Generation Summarization/共 16 篇）

• Abstractive Document Summarization with a Graph-Based Attentional Neural Model

• Authors: Jiwei Tan and Xiaojun Wan

• Automatically Generating Rhythmic Verse with Neural Networks

• Authors: Jack Hopkins and Douwe Kiela

IE QA 文本挖掘應用（IE QA Text Mining Applications/共 37 篇）

• A Constituent-Centric Neural Architecture for Reading Comprehension

• Authors: Pengtao Xie and Eric Xing

• A FOFE-based Local Detection Approach for Named Entity Recognition and Mention Detection

• Authors: Mingbin Xu, Hui Jiang and Sedtawut Watcharawittayakul

• Adversarial Multi-task Learning for Text Classification

• Authors: Pengfei Liu, Xipeng Qiu and Xuanjing Huang

機器學習（Machine Learning/共 13 篇）

• An Algebra for Feature Extraction

• Authors: Vivek Srikumar

• Bayesian Modeling of Lexical Resources for Low-Resource Settings

• Authors: Nicholas Andrews, Jason Eisner, Mark Dredze and Benjamin Van Durme

• Context Sensitive Lemmatization Using Two Successive Bidirectional Gated Recurrent Networks

• Authors: Abhisek Chakrabarty, Onkar Arun Pandit and Utpal Garain

機器翻譯（Machine Translation/共 15 篇）

• A Convolutional Encoder Model for Neural Machine Translation

• Authors: Jonas Gehring, Michael Auli, David Grangier and Yann Dauphin

• A Teacher-Student Framework for Zero-Resource Neural Machine Translation

• Authors: Yun Chen, Yang Liu, Yong Cheng and Victor O.K. Li

• Bandit Structured Prediction for Neural Sequence-to-Sequence Learning

• Authors: Julia Kreutzer, Artem Sokolov and Stefan Riezler

多學科論文（Multidisciplinary/共 4 篇）

• A Nested Attention Neural Hybrid Model for Grammatical Error Correction

• Authors: Jianshu Ji, Qinlong Wang, Kristina Toutanova, Yongen Gong, Steven Truong and Jianfeng Gao

• Combating Human Trafficking with Multimodal Deep Models

• Authors: Edmund Tong, Amir Zadeh and Louis-Philippe Morency

多語言論文（Multilingual/共 6 篇）

• Adversarial Training for Unsupervised Bilingual Lexicon Induction

• Authors: Meng Zhang, Yang Liu, Huanbo Luan and Maosong Sun

• Cross-lingual Name Tagging and Linking for 282 Languages

• Authors: Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight and Heng Ji

音系形態學詞切分（Phonology Morphology Word Segmentation/共 5 篇）

• Adversarial Multi-Criteria Learning for Chinese Word Segmentation

• Authors: Xinchi Chen, Zhan Shi, Xipeng Qiu and Xuanjing Huang

• From Characters to Words to in Between: Do We Capture Morphology?

• Authors: Clara Vania and Adam Lopez

資源評估（Resources Evaluation/共 6 篇）

• A Corpus of Annotated Revisions for Studying Argumentative Writing

• Authors: Fan Zhang, Homa B. Hashemi, Rebecca Hwa and Diane Litman

• Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction

• Authors: Christopher Bryant, Mariano Felice and Ted Briscoe

語義學（Semantics/共 30 篇）

• A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data

• Authors: Qiaolin Xia, Zhifang Sui and Baobao Chang

• A Transition-Based Directed Acyclic Graph Parser for UCCA

• Authors: Daniel Hershcovich, Omri Abend and Ari Rappoport

• A Syntactic Neural Model for General-Purpose Code Generation

• Authors: Pengcheng Yin and Graham Neubig

情感分析和觀點挖掘（Sentiment Analysis Opinion Mining/共 11 篇）

• A Multidimensional Lexicon for Interpersonal Stancetaking

• Authors: Umashanthi Pavalanathan, Jim Fitzpatrick, Scott Kiesling and Jacob Eisenstein

• Active Sentiment Domain Adaptation

• Authors: Fangzhao Wu and Yongfeng Huang

社交媒體（Social Media/共 6 篇）

• Beyond Binary Labels: Political Ideology Prediction of Twitter Users

• Authors: Daniel Preoţiuc-Pietro, Ye Liu, Daniel Hopkins and Lyle Ungar

• CANE: Context-Aware Network Embedding for Relation Modeling

• Authors: Cunchao Tu, Han Liu, Zhiyuan Liu and Maosong Sun

語音（Speech/共 2 篇）

• Joint CTC-attention End-to-end Speech Recognition

• Authors: Shinji Watanabe, Takaaki Hori and John Hershey

• Learning Word-Like Units from Joint Audio-Visual Analysis

• Authors: David Harwath and James Glass

標註塊句法分析（Tagging Chunking Syntax Parsing/共 13 篇）

• A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing

• Authors: Daniel Fernández-González and Carlos Gómez-Rodríguez

• A Minimal Span-Based Neural Constituent Parser

• Authors: Mitchell Stern, Jacob Andreas and Dan Klein

機器人視覺基礎（Vision Robots Grounding/共 5 篇）

• Combining distributional and referential information for naming objects through cross-modal mapping and direct word prediction

• Authors: Sina Zarrieß and David Schlangen

• FOIL it! Find One mismatch between Image and Language caption

• Authors: Ravi Shekhar, Sandro Pezzelle, Yauhen Klimovich, Aurélie Herbelot, Moin Nabi, Enver Sangineto and Raffaella Bernardi

接收短篇論文

生物醫學（Biomedical/共 2 篇）

• Neural Architecture for Temporal Relation Extraction: A Bi-LSTM Approach for Detecting Narrative Containers

• Authors: Julien Tourille, Olivier Ferret, Aurelie Neveol and Xavier Tannier

• Vector space models for evaluating semantic fluency in autism

• Authors: Emily Prud』hommeaux, Jan van Santen and Douglas Gliner

認知建模與心理語言學（Cognitive Modelling and Psycholinguistics/共 1 篇）

• The Role of Prosody and Speech Register in Word Segmentation: A Computational Modelling Perspective

• Authors: Bogdan Ludusan, Reiko Mazuka, Mathieu Bernard, Alejandrina Cristia and Emmanuel Dupoux

交互式對話系統（Dialog Interactive Systems/共 3 篇）

• A Conditional Variational Framework for Dialog Generation

• Authors: Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu and Akiko Aizawa

• How to Make Contexts More Useful? An Empirical Study to Context-Aware Neural Conversation Models

• Authors: Zhiliang Tian, Rui Yan, Lili Mou, Yiping Song, Yansong Feng and Dongyan Zhao

語篇語用學（Discourse Pragmatics/共 8 篇）

• A Recurrent Neural Model with Attention for the Recognition of Chinese Implicit Discourse Relations

• Authors: Niko Schenk and Samuel Rönnqvist

• A Two-stage Parsing Method for Text-level Discourse Analysis

• Authors: Yizhong Wang and Sujian Li

摘要生成（Generation Summarization/共 4 篇）

• A Principled Framework for Evaluating Summarizers: Comparing Models of Summary Quality against Human Judgments

• Authors: Maxime Peyrard and Judith Eckle-Kohler

• Japanese Sentence Compression with a Large Training Dataset

• Authors: Shun Hasegawa, Yuta Kikuchi, Hiroya Takamura and Manabu Okumura

IE QA 文本挖掘應用（IE QA Text Mining Applications/共 19 篇）

• A Generative Attentional Neural Network Model for Dialogue Act Classification

• Authors: Quan Hung Tran, Gholamreza Haffari and Ingrid Zukerman

• Bootstrapping for Numerical Open IE

• Authors: Swarnadeep Saha, Harinder Pal and Mausam

機器學習（Machine Learning/共 6 篇）

• A Deep Network with Visual Text Composition Behavior

• Authors: Hongyu GUO

• Differentiable Scheduled Sampling for Credit Assignment

• Authors: Kartik Goyal, Chris Dyer and Taylor Berg-Kirkpatrick

機器翻譯（Machine Translation/共 12 篇）

• Alternative Objective Functions for Training MT Evaluation Metrics

• Authors: Miloš Stanojević and Khalil Sima‘ an

• An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation

• Authors: Chenhui Chu, Raj Dabre and Sadao Kurohashi

多學科論文（Multidisciplinary/共 6 篇）

• Automatic Compositor Attribution in the First Folio of Shakespeare

• Authors: Maria Ryskina, Hannah Alpert-Abrams, Dan Garrette and Taylor Berg-Kirkpatrick

• Detection of Chinese Word Usage Errors for Non-Native Chinese Learners with Bidirectional LSTM

• Authors: Yow-Ting Shiue, Hen-Hsen Huang and Hsin-Hsi Chen

多語言論文（Multilingual/共 3 篇）

• EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text

• Authors: Claudio Delli Bovi, Jose Camacho-Collados, Alessandro Raganato and Roberto Navigli

• Incorporating Dialectal Variability for Socially Equitable Language Identification

• Authors: David Jurgens, Yulia Tsvetkov and Dan Jurafsky

音系形態學詞切分（Phonology Morphology Word Segmentation/共 3 篇）

• Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging

• Authors: Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Ahmed Abdelali, Yonatan Belinkov and Stephan Vogel

• Evaluation of Compound Splitting with Textual Entailment

• Authors: Glorianna Jagfeld, Patrick Ziering and Lonneke van der Plas

資源評估（Resources Evaluation/共 5 篇）

• 「Liar, Liar Pants on Fire」: A New Benchmark Dataset for Fake News Detection

• Authors: William Yang Wang

• Constructing Large-Scale Japanese Image Caption Dataset

• Authors: Yuya Yoshikawa, Yutaro Shigeto and Akikazu Takeuchi

語義學（Semantics/共 9 篇）

• AMR-to-text Generation with Synchronous Node Replacement Grammar

• Authors: Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang and Daniel Gildea

• Geometry of Sentences

• Authors: Jiaqi Mu, Suma Bhat and Pramod Viswanath

情感分析和觀點挖掘（Sentiment Analysis Opinion Mining/共 6 篇）

• Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation

• Authors: Svetlana Kiritchenko and Saif Mohammad

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

• Authors: Ye Zhang, Matthew Lease and Byron C. Wallace

社交媒體（Social Media/共 10 篇）

• A Network Framework for Noisy Label Aggregation in Social Media

• Authors: Xueying Zhan, Yaowei Wang, Yanghui Rao, Haoran Xie, Qing Li, Fu Lee Wang and Tak-Lam Wong

• A Neural Model for User Geolocation and Lexical Dialectology

• Authors: Afshin Rahimi, Trevor Cohn and Timothy Baldwin

語音（Speech/共 1 篇）

• Incorporating Uncertainty into Deep Learning for Spoken Language Assessment

• Authors: Andrey Malinin, Anton Ragni, Kate Knill and Mark Gales

標註塊句法分析（Tagging Chunking Syntax Parsing/共 7 篇）

• A Generative Parser with a Discriminative Recognition Algorithm

• Authors: Jianpeng Cheng, Adam Lopez and Mirella Lapata

• Arc-swift: A Novel Transition System for Dependency Parsing

• Authors: Peng Qi and Christopher D. Manning

機器人視覺基礎（Vision Robots Grounding/共 2 篇）

• A Corpus of Compositional Language for Visual Reasoning

• Authors: Alane Suhr, Mike Lewis, James Yeh and Yoav Artzi

• A Survey on Action Recognition Datasets and Tasks for Still Images

• Authors: Spandana Gella and Frank Keller

接收的軟件展示（共 21 個）

• Extended Named Entity Recognition API and Its Applications in Language Education

• Authors: Tuan Duc Nguyen, Khai Mai, Thai-Hoang Pham, Minh Trung Nguyen, Truc-Vien T. Nguyen, Takashi Eguchi, Ryohei Sasano and Satoshi Sekine

• Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph

• Authors: Gus Hahn-Powell, Marco A. Valenzuela-Escárcega and Mihai Surdeanu

• OpenNMT: Open-Source Toolkit for Neural Machine Translation

• Authors: Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart and Alexander M. Rush

• RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations

• Authors: Kateryna Tymoshenko, Alessandro Moschitti, Massimo Nicosia and Aliaksei Severyn

• Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ

• Authors: Jason Kessler

在 ACL 2017 彙報的 ACL 論文（共 21 篇）

這些論文由 TACL 接收並出版，並且將在 ACL 2017 做主題演講報告。

• Decoding Anagrammed Texts Written in an Unknown Language and Script

• Authors: Bradley Hauer and Grzegorz Kondrak

• Visually Grounded and Textual Semantic Models Differentially Decode Brain Activity Associated with Concrete and Abstract Nouns

• Authors: Andrew J. Anderson, Douwe Kiela, Stephen Clark, Massimo Poesio

• Evaluating Visual Representations for Topic Understanding and Their Effects on Manually Generated Labels

• Authors: Alison Smith, Tak Yeon Lee, Forough-Poursabzi Sangdeh, Jordan Boyd-Graber, Niklas Elmqvist, Leah Findlater

• Joint Semantic Synthesis and Morphological Analysis of the Derived Word

• Authors: Ryan Cotterell and Hinrich Schütze

• Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing

• Authors: Tim Vieira, Jason Eisner