Paper Group NANR 158
The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews – An Adversarial Study. Investigating Active Learning for Short-Answer Scoring. An Interactive System for Exploring Community Question Answering Forums. Automating Feature Engineering. Cognito: Automated Feature Engineering for Supervised Learning. Hashtag Reco …
The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews – An Adversarial Study
| Title | The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews – An Adversarial Study |
| Authors | Dirk Hovy |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2057/ |
| https://www.aclweb.org/anthology/P16-2057 | |
| PWC | https://paperswithcode.com/paper/the-enemy-in-your-own-camp-how-well-can-we |
| Repo | |
| Framework | |
Investigating Active Learning for Short-Answer Scoring
| Title | Investigating Active Learning for Short-Answer Scoring |
| Authors | Andrea Horbach, Alexis Palmer |
| Abstract | |
| Tasks | Active Learning, Reading Comprehension |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0535/ |
| https://www.aclweb.org/anthology/W16-0535 | |
| PWC | https://paperswithcode.com/paper/investigating-active-learning-for-short |
| Repo | |
| Framework | |
An Interactive System for Exploring Community Question Answering Forums
| Title | An Interactive System for Exploring Community Question Answering Forums |
| Authors | Enamul Hoque, Shafiq Joty, Llu{'\i}s M{`a}rquez, Alberto Barr{'o}n-Cede{~n}o, Giovanni Da San Martino, Aless Moschitti, ro, Preslav Nakov, Salvatore Romeo, Giuseppe Carenini |
| Abstract | We present an interactive system to provide effective and efficient search capabilities in Community Question Answering (cQA) forums. The system integrates state-of-the-art technology for answer search with a Web-based user interface specifically tailored to support the cQA forum readers. The answer search module automatically finds relevant answers for a new question by exploring related questions and the comments within their threads. The graphical user interface presents the search results and supports the exploration of related information. The system is running live at \url{http://www.qatarliving.com/betasearch/}. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2001/ |
| https://www.aclweb.org/anthology/C16-2001 | |
| PWC | https://paperswithcode.com/paper/an-interactive-system-for-exploring-community |
| Repo | |
| Framework | |
Automating Feature Engineering
| Title | Automating Feature Engineering |
| Authors | Udayan Khurana, Fatemeh Nargesian, Horst Samulowitz, Elias Khalil, Deepak Turaga |
| Abstract | Feature Engineering is the task of transforming the feature space in a given learning problem to improve the performance of a trained model. It is a crucial but time intensive and skillful process, involving a data scientist or a domain expert. It is often the key determinant of the time and cost required to build an effective learner. In this paper, we discuss our system for performing feature engineering in an automated manner using a combination of exploratory and learning techniques. We also mention our larger charter of an automated data science pipeline. |
| Tasks | Automated Feature Engineering, Feature Engineering |
| Published | 2016-01-01 |
| URL | http://workshops.inf.ed.ac.uk/nips2016-ai4datasci/papers/NIPS2016-AI4DataSci_paper_13.pdf |
| http://workshops.inf.ed.ac.uk/nips2016-ai4datasci/papers/NIPS2016-AI4DataSci_paper_13.pdf | |
| PWC | https://paperswithcode.com/paper/automating-feature-engineering |
| Repo | |
| Framework | |
Cognito: Automated Feature Engineering for Supervised Learning
| Title | Cognito: Automated Feature Engineering for Supervised Learning |
| Authors | Udayan Khurana, Deepak Turaga, Horst Samulowitz, Srinivasan Parthasrathy |
| Abstract | Feature engineering involves constructing novel features from given data with the goal of improving predictive learning performance. Feature engineering is predominantly a human-intensive and time consuming step that is central to the data science workflow. In this paper, we present a novel system called “Cognito”, that performs automatic feature engineering on a given dataset for supervised learning. The system explores various feature construction choices in a hierarchical and non-exhaustive manner, while progressively maximizing the accuracy of the model through a greedy exploration strategy. Additionally, the system allows users to specify domain or data specific choices to prioritize the exploration. Cognito is capable of handling large datasets through sampling and built-in parallelism, and integrates well with a state-of-the-art model selection strategy. We present the design and operation of Cognito, along with experimental results on eight real datasets to demonstrate its efficacy. |
| Tasks | Automated Feature Engineering, Feature Engineering, Model Selection |
| Published | 2016-01-01 |
| URL | https://ieeexplore.ieee.org/abstract/document/7836821/ |
| https://ieeexplore.ieee.org/abstract/document/7836821/ | |
| PWC | https://paperswithcode.com/paper/cognito-automated-feature-engineering-for |
| Repo | |
| Framework | |
Hashtag Recommendation with Topical Attention-Based LSTM
| Title | Hashtag Recommendation with Topical Attention-Based LSTM |
| Authors | Yang Li, Ting Liu, Jing Jiang, Liang Zhang |
| Abstract | Microblogging services allow users to create hashtags to categorize their posts. In recent years, the task of recommending hashtags for microblogs has been given increasing attention. However, most of existing methods depend on hand-crafted features. Motivated by the successful use of long short-term memory (LSTM) for many natural language processing tasks, in this paper, we adopt LSTM to learn the representation of a microblog post. Observing that hashtags indicate the primary topics of microblog posts, we propose a novel attention-based LSTM model which incorporates topic modeling into the LSTM architecture through an attention mechanism. We evaluate our model using a large real-world dataset. Experimental results show that our model significantly outperforms various competitive baseline methods. Furthermore, the incorporation of topical attention mechanism gives more than 7.4{%} improvement in F1 score compared with standard LSTM method. |
| Tasks | Feature Engineering, Information Retrieval, Text Classification, Topic Models |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1284/ |
| https://www.aclweb.org/anthology/C16-1284 | |
| PWC | https://paperswithcode.com/paper/hashtag-recommendation-with-topical-attention |
| Repo | |
| Framework | |
Enhancing Automatic Wordnet Construction Using Word Embeddings
| Title | Enhancing Automatic Wordnet Construction Using Word Embeddings |
| Authors | Feras Al Tarouti, Jugal Kalita |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1204/ |
| https://www.aclweb.org/anthology/W16-1204 | |
| PWC | https://paperswithcode.com/paper/enhancing-automatic-wordnet-construction |
| Repo | |
| Framework | |
Anaphoricity in Connectives: A Case Study on German
| Title | Anaphoricity in Connectives: A Case Study on German |
| Authors | Manfred Stede, Yulia Grishina |
| Abstract | |
| Tasks | Coreference Resolution |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0706/ |
| https://www.aclweb.org/anthology/W16-0706 | |
| PWC | https://paperswithcode.com/paper/anaphoricity-in-connectives-a-case-study-on |
| Repo | |
| Framework | |
VerbCROcean: A Repository of Fine-Grained Semantic Verb Relations for Croatian
| Title | VerbCROcean: A Repository of Fine-Grained Semantic Verb Relations for Croatian |
| Authors | Ivan Sekuli{'c}, Jan {\v{S}}najder |
| Abstract | In this paper we describe VerbCROcean, a broad-coverage repository of fine-grained semantic relations between Croatian verbs. Adopting the methodology of Chklovski and Pantel (2004) used for acquiring the English VerbOcean, we first acquire semantically related verb pairs from a web corpus hrWaC by relying on distributional similarity of subject-verb-object paths in the dependency trees. We then classify the semantic relations between each pair of verbs as similarity, intensity, antonymy, or happens-before, using a number of manually-constructed lexico-syntatic patterns. We evaluate the quality of the resulting resource on a manually annotated sample of 1000 semantic verb relations. The evaluation revealed that the predictions are most accurate for the similarity relation, and least accurate for the intensity relation. We make available two variants of VerbCROcean: a coverage-oriented version, containing about 36k verb pairs at a precision of 41{%}, and a precision-oriented version containing about 5k verb pairs, at a precision of 56{%}. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1425/ |
| https://www.aclweb.org/anthology/L16-1425 | |
| PWC | https://paperswithcode.com/paper/verbcrocean-a-repository-of-fine-grained |
| Repo | |
| Framework | |
Cross-lingual alignment transfer: a chicken-and-egg story?
| Title | Cross-lingual alignment transfer: a chicken-and-egg story? |
| Authors | Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon |
| Abstract | |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Named Entity Recognition, Semantic Role Labeling, Word Alignment |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1205/ |
| https://www.aclweb.org/anthology/W16-1205 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-alignment-transfer-a-chicken |
| Repo | |
| Framework | |
Improved Semantic Parsers For If-Then Statements
| Title | Improved Semantic Parsers For If-Then Statements |
| Authors | I. Beltagy, Chris Quirk |
| Abstract | |
| Tasks | Feature Engineering, Feature Selection, Image Captioning, Machine Translation, Semantic Parsing |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1069/ |
| https://www.aclweb.org/anthology/P16-1069 | |
| PWC | https://paperswithcode.com/paper/improved-semantic-parsers-for-if-then |
| Repo | |
| Framework | |
A Prototype Automatic Simultaneous Interpretation System
| Title | A Prototype Automatic Simultaneous Interpretation System |
| Authors | Xiaolin Wang, Andrew Finch, Masao Utiyama, Eiichiro Sumita |
| Abstract | Simultaneous interpretation allows people to communicate spontaneously across language boundaries, but such services are prohibitively expensive for the general public. This paper presents a fully automatic simultaneous interpretation system to address this problem. Though the development is still at an early stage, the system is capable of keeping up with the fastest of the TED speakers while at the same time delivering high-quality translations. We believe that the system will become an effective tool for facilitating cross-lingual communication in the future. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2007/ |
| https://www.aclweb.org/anthology/C16-2007 | |
| PWC | https://paperswithcode.com/paper/a-prototype-automatic-simultaneous |
| Repo | |
| Framework | |
Leveraging Multilingual Training for Limited Resource Event Extraction
| Title | Leveraging Multilingual Training for Limited Resource Event Extraction |
| Authors | Andrew Hsi, Yiming Yang, Jaime Carbonell, Ruochen Xu |
| Abstract | Event extraction has become one of the most important topics in information extraction, but to date, there is very limited work on leveraging cross-lingual training to boost performance. We propose a new event extraction approach that trains on multiple languages using a combination of both language-dependent and language-independent features, with particular focus on the case where target domain training data is of very limited size. We show empirically that multilingual training can boost performance for the tasks of event trigger extraction and event argument extraction on the Chinese ACE 2005 dataset. |
| Tasks | Dependency Parsing, Machine Translation, Named Entity Recognition, Part-Of-Speech Tagging |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1114/ |
| https://www.aclweb.org/anthology/C16-1114 | |
| PWC | https://paperswithcode.com/paper/leveraging-multilingual-training-for-limited |
| Repo | |
| Framework | |
Incorporating Satellite Documents into Co-citation Networks for Scientific Paper Searches
| Title | Incorporating Satellite Documents into Co-citation Networks for Scientific Paper Searches |
| Authors | Masaki Eto |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1504/ |
| https://www.aclweb.org/anthology/W16-1504 | |
| PWC | https://paperswithcode.com/paper/incorporating-satellite-documents-into-co |
| Repo | |
| Framework | |
Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality – Revisiting the Issue of Meaning Grounded in Syntax
| Title | Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality – Revisiting the Issue of Meaning Grounded in Syntax |
| Authors | Judith Eckle-Kohler |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1077/ |
| https://www.aclweb.org/anthology/P16-1077 | |
| PWC | https://paperswithcode.com/paper/verbs-taking-clausal-and-non-finite-arguments-1 |
| Repo | |
| Framework | |
