Paper Group NANR 155
Task-driven Webpage Saliency. Tutorial: De-mystifying Neural MT. Towards an argumentative content search engine using weak supervision. Learning from Measurements in Crowdsourcing Models: Inferring Ground Truth from Diverse Annotation Types. The Metalogue Debate Trainee Corpus: Data Collection and Annotations. Argumentation Synthesis following Rhet …
Task-driven Webpage Saliency
| Title | Task-driven Webpage Saliency |
| Authors | Quanlong Zheng, Jianbo Jiao, Ying Cao, Rynson W.H. Lau |
| Abstract | In this paper, we present an end-to-end learning framework for predicting task-driven visual saliency on webpages. Given a webpage, we propose a convolutional neural network to predict where people look at it under different task conditions. Inspired by the observation that given a specific task, human attention is strongly correlated with certain semantic components on a webpage (e.g., images, buttons and input boxes), our network explicitly disentangles saliency prediction into two independent sub-tasks: task-specific attention shift prediction and task-free saliency prediction. The task-specific branch estimates task-driven attention shift over a webpage from its semantic components, while the task-free branch infers visual saliency induced by visual features of the webpage. The outputs of the two branches are combined to produce the final prediction. Such a task decomposition framework allows us to efficiently learn our model from a small-scale task-driven saliency dataset with sparse labels (captured under a single task condition). Experimental results show that our method outperforms the baselines and prior works, achieving state-of-the-art performance on a newly collected benchmark dataset for task-driven webpage saliency detection. |
| Tasks | Saliency Detection, Saliency Prediction |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Quanlong_Zheng_Task-driven_Webpage_Saliency_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Quanlong_Zheng_Task-driven_Webpage_Saliency_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/task-driven-webpage-saliency |
| Repo | |
| Framework | |
Tutorial: De-mystifying Neural MT
| Title | Tutorial: De-mystifying Neural MT |
| Authors | Dragos Munteanu, Ling Tsou |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1924/ |
| https://www.aclweb.org/anthology/W18-1924 | |
| PWC | https://paperswithcode.com/paper/tutorial-de-mystifying-neural-mt |
| Repo | |
| Framework | |
Towards an argumentative content search engine using weak supervision
| Title | Towards an argumentative content search engine using weak supervision |
| Authors | Ran Levy, Ben Bogin, Shai Gretz, Ranit Aharonov, Noam Slonim |
| Abstract | Searching for sentences containing claims in a large text corpus is a key component in developing an argumentative content search engine. Previous works focused on detecting claims in a small set of documents or within documents enriched with argumentative content. However, pinpointing relevant claims in massive unstructured corpora, received little attention. A step in this direction was taken in (Levy et al. 2017), where the authors suggested using a weak signal to develop a relatively strict query for claim{–}sentence detection. Here, we leverage this work to define weak signals for training DNNs to obtain significantly greater performance. This approach allows to relax the query and increase the potential coverage. Our results clearly indicate that the system is able to successfully generalize from the weak signal, outperforming previously reported results in terms of both precision and coverage. Finally, we adapt our system to solve a recent argument mining task of identifying argumentative sentences in Web texts retrieved from heterogeneous sources, and obtain F1 scores comparable to the supervised baseline. |
| Tasks | Argument Mining, Decision Making |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1176/ |
| https://www.aclweb.org/anthology/C18-1176 | |
| PWC | https://paperswithcode.com/paper/towards-an-argumentative-content-search |
| Repo | |
| Framework | |
Learning from Measurements in Crowdsourcing Models: Inferring Ground Truth from Diverse Annotation Types
| Title | Learning from Measurements in Crowdsourcing Models: Inferring Ground Truth from Diverse Annotation Types |
| Authors | Paul Felt, Eric Ringger, Jordan Boyd-Graber, Kevin Seppi |
| Abstract | Annotated corpora enable supervised machine learning and data analysis. To reduce the cost of manual annotation, tasks are often assigned to internet workers whose judgments are reconciled by crowdsourcing models. We approach the problem of crowdsourcing using a framework for learning from rich prior knowledge, and we identify a family of crowdsourcing models with the novel ability to combine annotations with differing structures: e.g., document labels and word labels. Annotator judgments are given in the form of the predicted expected value of measurement functions computed over annotations and the data, unifying annotation models. Our model, a specific instance of this framework, compares favorably with previous work. Furthermore, it enables active sample selection, jointly selecting annotator, data item, and annotation structure to reduce annotation effort. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1144/ |
| https://www.aclweb.org/anthology/C18-1144 | |
| PWC | https://paperswithcode.com/paper/learning-from-measurements-in-crowdsourcing |
| Repo | |
| Framework | |
The Metalogue Debate Trainee Corpus: Data Collection and Annotations
| Title | The Metalogue Debate Trainee Corpus: Data Collection and Annotations |
| Authors | Volha Petukhova, Andrei Malchanau, Youssef Oualil, Dietrich Klakow, Saturnino Luz, Fasih Haider, Nick Campbell, Dimitris Koryzis, Dimitris Spiliotopoulos, Pierre Albert, Nicklas Linz, Alex, Jan ersson |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1120/ |
| https://www.aclweb.org/anthology/L18-1120 | |
| PWC | https://paperswithcode.com/paper/the-metalogue-debate-trainee-corpus-data |
| Repo | |
| Framework | |
Argumentation Synthesis following Rhetorical Strategies
| Title | Argumentation Synthesis following Rhetorical Strategies |
| Authors | Henning Wachsmuth, Manfred Stede, Roxanne El Baff, Khalid Al-Khatib, Maria Skeppstedt, Benno Stein |
| Abstract | Persuasion is rarely achieved through a loose set of arguments alone. Rather, an effective delivery of arguments follows a rhetorical strategy, combining logical reasoning with appeals to ethics and emotion. We argue that such a strategy means to select, arrange, and phrase a set of argumentative discourse units. In this paper, we model rhetorical strategies for the computational synthesis of effective argumentation. In a study, we let 26 experts synthesize argumentative texts with different strategies for 10 topics. We find that the experts agree in the selection significantly more when following the same strategy. While the texts notably vary for different strategies, especially their arrangement remains stable. The results suggest that our model enables a strategical synthesis. |
| Tasks | Argument Mining |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1318/ |
| https://www.aclweb.org/anthology/C18-1318 | |
| PWC | https://paperswithcode.com/paper/argumentation-synthesis-following-rhetorical |
| Repo | |
| Framework | |
Detecting Simultaneously Chinese Grammar Errors Based on a BiLSTM-CRF Model
| Title | Detecting Simultaneously Chinese Grammar Errors Based on a BiLSTM-CRF Model |
| Authors | Yajun Liu, Hongying Zan, Mengjie Zhong, Hongchao Ma |
| Abstract | In the process of learning and using Chinese, many learners of Chinese as foreign language(CFL) may have grammar errors due to negative migration of their native languages. This paper introduces our system that can simultaneously diagnose four types of grammatical errors including redundant (R), missing (M), selection (S), disorder (W) in NLPTEA-5 shared task. We proposed a Bidirectional LSTM CRF neural network (BiLSTM-CRF) that combines BiLSTM and CRF without hand-craft features for Chinese Grammatical Error Diagnosis (CGED). Evaluation includes three levels, which are detection level, identification level and position level. At the detection level and identification level, our system got the third recall scores, and achieved good F1 values. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3727/ |
| https://www.aclweb.org/anthology/W18-3727 | |
| PWC | https://paperswithcode.com/paper/detecting-simultaneously-chinese-grammar |
| Repo | |
| Framework | |
HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets
| Title | HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets |
| Authors | Wenting Wang |
| Abstract | This paper describes our system designed for the WASSA-2018 Implicit Emotion Shared Task (IEST). The task is to predict the emotion category expressed in a tweet by removing the terms \textit{angry}, \textit{afraid}, \textit{happy}, \textit{sad}, \textit{surprised}, \textit{disgusted} and their synonyms. Our final submission is an ensemble of one supervised learning model and three deep neural network based models, where each model approaches the problem from essentially different directions. Our system achieves the macro F1 score of 65.8{%}, which is a 5.9{%} performance improvement over the baseline and is ranked 12 out of 30 participating teams. |
| Tasks | Common Sense Reasoning, Emotion Classification, Emotion Recognition, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6229/ |
| https://www.aclweb.org/anthology/W18-6229 | |
| PWC | https://paperswithcode.com/paper/hgsgnlp-at-iest-2018-an-ensemble-of-machine |
| Repo | |
| Framework | |
Decomposing phonological transformations in serial derivations
| Title | Decomposing phonological transformations in serial derivations |
| Authors | Andrew Lamont |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0310/ |
| https://www.aclweb.org/anthology/W18-0310 | |
| PWC | https://paperswithcode.com/paper/decomposing-phonological-transformations-in |
| Repo | |
| Framework | |
Using Rhetorical Topics for Automatic Summarization
| Title | Using Rhetorical Topics for Automatic Summarization |
| Authors | Natalie M. Schrimpf |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0313/ |
| https://www.aclweb.org/anthology/W18-0313 | |
| PWC | https://paperswithcode.com/paper/using-rhetorical-topics-for-automatic |
| Repo | |
| Framework | |
Words Worth: Verbal Content and Hirability Impressions in YouTube Video Resumes
| Title | Words Worth: Verbal Content and Hirability Impressions in YouTube Video Resumes |
| Authors | Sk Muralidhar, a, Laurent Nguyen, Daniel Gatica-Perez |
| Abstract | Automatic hirability prediction from video resumes is gaining increasing attention in both psychology and computing. Most existing works have investigated hirability from the perspective of nonverbal behavior, with verbal content receiving little interest. In this study, we leverage the advances in deep-learning based text representation techniques (like word embedding) in natural language processing to investigate the relationship between verbal content and perceived hirability ratings. To this end, we use 292 conversational video resumes from YouTube, develop a computational framework to automatically extract various representations of verbal content, and evaluate them in a regression task. We obtain a best performance of R{\mbox{$^2$}} = 0.23 using GloVe, and R{\mbox{$^2$}} = 0.22 using Word2Vec representations for manual and automatically transcribed texts respectively. Our inference results indicate the feasibility of using deep learning based verbal content representation in inferring hirability scores from online conversational video resumes. |
| Tasks | Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6247/ |
| https://www.aclweb.org/anthology/W18-6247 | |
| PWC | https://paperswithcode.com/paper/words-worth-verbal-content-and-hirability |
| Repo | |
| Framework | |
Semi-automatic Korean FrameNet Annotation over KAIST Treebank
| Title | Semi-automatic Korean FrameNet Annotation over KAIST Treebank |
| Authors | Younggyun Hahm, Jiseong Kim, Sunggoo Kwon, Key-Sun Choi |
| Abstract | |
| Tasks | Dependency Parsing, Morphological Analysis, Part-Of-Speech Tagging, Question Answering, Semantic Role Labeling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1013/ |
| https://www.aclweb.org/anthology/L18-1013 | |
| PWC | https://paperswithcode.com/paper/semi-automatic-korean-framenet-annotation |
| Repo | |
| Framework | |
Identification of Differences between Dutch Language Varieties with the VarDial2018 Dutch-Flemish Subtitle Data
| Title | Identification of Differences between Dutch Language Varieties with the VarDial2018 Dutch-Flemish Subtitle Data |
| Authors | Hans van Halteren, Nelleke Oostdijk |
| Abstract | With the goal of discovering differences between Belgian and Netherlandic Dutch, we participated as Team Taurus in the Dutch-Flemish Subtitles task of VarDial2018. We used a rather simple marker-based method, but a wide range of features, including lexical, lexico-syntactic and syntactic ones, and achieved a second position in the ranking. Inspection of highly distin-guishing features did point towards differences between the two language varieties, but because of the nature of the experimental data, we have to treat our observations as very tentative and in need of further investigation. |
| Tasks | Text Classification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3923/ |
| https://www.aclweb.org/anthology/W18-3923 | |
| PWC | https://paperswithcode.com/paper/identification-of-differences-between-dutch |
| Repo | |
| Framework | |
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints
| Title | Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints |
| Authors | Ehsan Kazemi, Morteza Zadimoghaddam, Amin Karbasi |
| Abstract | Can we efficiently extract useful information from a large user-generated dataset while protecting the privacy of the users and/or ensuring fairness in representation? We cast this problem as an instance of a deletion-robust submodular maximization where part of the data may be deleted or masked due to privacy concerns or fairness criteria. We propose the first memory-efficient centralized, streaming, and distributed methods with constant-factor approximation guarantees against any number of adversarial deletions. We extensively evaluate the performance of our algorithms on real-world applications, including (i) Uber-pick up locations with location privacy constraints; (ii) feature selection with fairness constraints for income prediction and crime rate prediction; and (iii) robust to deletion summarization of census data, consisting of 2,458,285 feature vectors. Our experiments show that our solution is robust against even $80%$ of data deletion. |
| Tasks | Data Summarization, Feature Selection |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1927 |
| http://proceedings.mlr.press/v80/kazemi18a/kazemi18a.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-deletion-robust-submodular |
| Repo | |
| Framework | |
Twist Bytes - German Dialect Identification with Data Mining Optimization
| Title | Twist Bytes - German Dialect Identification with Data Mining Optimization |
| Authors | Fern Benites, o, Ralf Grubenmann, Pius von D{"a}niken, Dirk von Gr{"u}nigen, Jan Deriu, Mark Cieliebak |
| Abstract | We describe our approaches used in the German Dialect Identification (GDI) task at the VarDial Evaluation Campaign 2018. The goal was to identify to which out of four dialects spoken in German speaking part of Switzerland a sentence belonged to. We adopted two different meta classifier approaches and used some data mining insights to improve the preprocessing and the meta classifier parameters. Especially, we focused on using different feature extraction methods and how to combine them, since they influenced very differently the performance of the system. Our system achieved second place out of 8 teams, with a macro averaged F-1 of 64.6{%}. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3925/ |
| https://www.aclweb.org/anthology/W18-3925 | |
| PWC | https://paperswithcode.com/paper/twist-bytes-german-dialect-identification |
| Repo | |
| Framework | |
