Paper Group NAWR 2
A General Optimization Framework for Multi-Document Summarization Using Genetic Algorithms and Swarm Intelligence. Improve Chinese Word Embeddings by Exploiting Internal Structure. Adding Semantic Relations to a Large-Coverage Connective Lexicon of German. Learning Word Importance with the Neural Bag-of-Words Model. Collecting Resources in Sub-Saha …
A General Optimization Framework for Multi-Document Summarization Using Genetic Algorithms and Swarm Intelligence
| Title | A General Optimization Framework for Multi-Document Summarization Using Genetic Algorithms and Swarm Intelligence |
| Authors | Maxime Peyrard, Judith Eckle-Kohler |
| Abstract | Extracting summaries via integer linear programming and submodularity are popular and successful techniques in extractive multi-document summarization. However, many interesting optimization objectives are neither submodular nor factorizable into an integer linear program. We address this issue and present a general optimization framework where any function of input documents and a system summary can be plugged in. Our framework includes two kinds of summarizers {–} one based on genetic algorithms, the other using a swarm intelligence approach. In our experimental evaluation, we investigate the optimization of two information-theoretic summary evaluation metrics and find that our framework yields competitive results compared to several strong summarization baselines. Our comparative analysis of the genetic and swarm summarizers reveals interesting complementary properties. |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1024/ |
| https://www.aclweb.org/anthology/C16-1024 | |
| PWC | https://paperswithcode.com/paper/a-general-optimization-framework-for-multi |
| Repo | https://github.com/UKPLab/coling2016-genetic-swarm-MDS |
| Framework | none |
Improve Chinese Word Embeddings by Exploiting Internal Structure
| Title | Improve Chinese Word Embeddings by Exploiting Internal Structure |
| Authors | Jian Xu, Jiawei Liu, Liangang Zhang, Zhengyu Li, Huanhuan Chen |
| Abstract | |
| Tasks | Semantic Textual Similarity, Text Classification, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1119/ |
| https://www.aclweb.org/anthology/N16-1119 | |
| PWC | https://paperswithcode.com/paper/improve-chinese-word-embeddings-by-exploiting |
| Repo | https://github.com/JianXu123/SCWE |
| Framework | none |
Adding Semantic Relations to a Large-Coverage Connective Lexicon of German
| Title | Adding Semantic Relations to a Large-Coverage Connective Lexicon of German |
| Authors | Tatjana Scheffler, Manfred Stede |
| Abstract | DiMLex is a lexicon of German connectives that can be used for various language understanding purposes. We enhanced the coverage to 275 connectives, which we regard as covering all known German discourse connectives in current use. In this paper, we consider the task of adding the semantic relations that can be expressed by each connective. After discussing different approaches to retrieving semantic information, we settle on annotating each connective with senses from the new PDTB 3.0 sense hierarchy. We describe our new implementation in the extended DiMLex, which will be available for research purposes. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1160/ |
| https://www.aclweb.org/anthology/L16-1160 | |
| PWC | https://paperswithcode.com/paper/adding-semantic-relations-to-a-large-coverage |
| Repo | https://github.com/discourse-lab/dimlex |
| Framework | none |
Learning Word Importance with the Neural Bag-of-Words Model
| Title | Learning Word Importance with the Neural Bag-of-Words Model |
| Authors | Imran Sheikh, Irina Illina, Dominique Fohr, Georges Linar{`e}s |
| Abstract | |
| Tasks | Representation Learning, Sentiment Analysis, Text Classification |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1626/ |
| https://www.aclweb.org/anthology/W16-1626 | |
| PWC | https://paperswithcode.com/paper/learning-word-importance-with-the-neural-bag |
| Repo | https://github.com/mranahmd/nbow2-text-class |
| Framework | none |
Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of Wolof
| Title | Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of Wolof |
| Authors | Elodie Gauthier, Laurent Besacier, Sylvie Voisin, Michael Melese, Uriel Pascal Elingui |
| Abstract | This article presents the data collected and ASR systems developped for 4 sub-saharan african languages (Swahili, Hausa, Amharic and Wolof). To illustrate our methodology, the focus is made on Wolof (a very under-resourced language) for which we designed the first ASR system ever built in this language. All data and scripts are available online on our github repository. |
| Tasks | Speech Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1611/ |
| https://www.aclweb.org/anthology/L16-1611 | |
| PWC | https://paperswithcode.com/paper/collecting-resources-in-sub-saharan-african |
| Repo | https://github.com/besacier/ALFFA_PUBLIC |
| Framework | none |
Support Vector Machines with Time Series Distance Kernels for Action Classification
| Title | Support Vector Machines with Time Series Distance Kernels for Action Classification |
| Authors | Mohammad Ali Bagheri, Qigang Gao, Sergio Escalera |
| Abstract | Despite the outperformance of Support Vector Machine (SVM) on many practical classification problems, the algorithm is not directly applicable to multi-dimensional trajectories having different lengths. In this paper, a new class of SVM that is applicable to trajectory classification, such as action recognition, is developed by incorporating two efficient time-series distances measures into the kernel function. Dynamic Time Warping and Longest Common Subsequence distance measures along with their derivatives are employed as the SVM kernel. In addition, the pairwise proximity learning strategy is utilized in order to make use of non-positive semi-definite kernels in the SVM formulation. The proposed method is employed for a challenging classification problem: action recognition by depth cameras using only skeleton data; and evaluated on three benchmark action datasets. Experimental results demonstrate the outperformance of our methodology compared to the state-of-the-art on the considered datasets. [1] M .A. Bagheri, Q. Gao, and S. Escalera, “Support Vector Machines with Time Series Distance Kernels for Action Classification”, in Proc. IEEE Winter Conference on Applications of Computer Vision, New York, 2016. |
| Tasks | Action Classification, Temporal Action Localization, Time Series, Time Series Classification |
| Published | 2016-03-07 |
| URL | https://ieeexplore.ieee.org/document/7477591 |
| http://sergioescalera.com/wp-content/uploads/2016/02/wacv2016.pdf | |
| PWC | https://paperswithcode.com/paper/support-vector-machines-with-time-series |
| Repo | https://github.com/mabagheri/SVM_DTW_Kernel |
| Framework | none |
Neural Relation Extraction with Selective Attention over Instances
| Title | Neural Relation Extraction with Selective Attention over Instances |
| Authors | Yankai Lin, Shiqi Shen, Zhiyuan Liu, Huanbo Luan, Maosong Sun |
| Abstract | |
| Tasks | Relation Extraction, Relationship Extraction (Distant Supervised) |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/papers/P16-1200/p16-1200 |
| https://www.aclweb.org/anthology/P16-1200v2 | |
| PWC | https://paperswithcode.com/paper/neural-relation-extraction-with-selective |
| Repo | https://github.com/thunlp/NRE |
| Framework | tf |
Attention-based LSTM for Aspect-level Sentiment Classification
| Title | Attention-based LSTM for Aspect-level Sentiment Classification |
| Authors | Yequan Wang, Minlie Huang, Xiaoyan Zhu, Li Zhao |
| Abstract | |
| Tasks | Aspect-Based Sentiment Analysis |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1058/ |
| https://www.aclweb.org/anthology/D16-1058 | |
| PWC | https://paperswithcode.com/paper/attention-based-lstm-for-aspect-level |
| Repo | https://github.com/songyouwei/ABSA-PyTorch |
| Framework | pytorch |
Summarizing Source Code using a Neural Attention Model
| Title | Summarizing Source Code using a Neural Attention Model |
| Authors | Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Luke Zettlemoyer |
| Abstract | |
| Tasks | Code Summarization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1195/ |
| https://www.aclweb.org/anthology/P16-1195 | |
| PWC | https://paperswithcode.com/paper/summarizing-source-code-using-a-neural |
| Repo | https://github.com/sriniiyer/codenn |
| Framework | torch |
Cohere: A Toolkit for Local Coherence
| Title | Cohere: A Toolkit for Local Coherence |
| Authors | Karin Sim Smith, Wilker Aziz, Lucia Specia |
| Abstract | We describe COHERE, our coherence toolkit which incorporates various complementary models for capturing and measuring different aspects of text coherence. In addition to the traditional entity grid model (Lapata, 2005) and graph-based metric (Guinaudeau and Strube, 2013), we provide an implementation of a state-of-the-art syntax-based model (Louis and Nenkova, 2012), as well as an adaptation of this model which shows significant performance improvements in our experiments. We benchmark these models using the standard setting for text coherence: original documents and versions of the document with sentences in shuffled order. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1649/ |
| https://www.aclweb.org/anthology/L16-1649 | |
| PWC | https://paperswithcode.com/paper/cohere-a-toolkit-for-local-coherence |
| Repo | https://github.com/karins/CoherenceFramework |
| Framework | none |
SatiricLR: a Language Resource of Satirical News Articles
| Title | SatiricLR: a Language Resource of Satirical News Articles |
| Authors | Alice Frain, S Wubben, er |
| Abstract | In this paper we introduce the Satirical Language Resource: a dataset containing a balanced collection of satirical and non satirical news texts from various domains. This is the first dataset of this magnitude and scope in the domain of satire. We envision this dataset will facilitate studies on various aspects of of sat- ire in news articles. We test the viability of our data on the task of classification of satire. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1653/ |
| https://www.aclweb.org/anthology/L16-1653 | |
| PWC | https://paperswithcode.com/paper/satiriclr-a-language-resource-of-satirical |
| Repo | https://github.com/swubb/SatiricLR |
| Framework | none |
Predicting Author Age from Weibo Microblog Posts
| Title | Predicting Author Age from Weibo Microblog Posts |
| Authors | Wanru Zhang, Andrew Caines, Dimitrios Alikaniotis, Paula Buttery |
| Abstract | Binary file summaries/958.html matches |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1478/ |
| https://www.aclweb.org/anthology/L16-1478 | |
| PWC | https://paperswithcode.com/paper/predicting-author-age-from-weibo-microblog |
| Repo | https://github.com/cainesap/sino-nlp |
| Framework | none |
Character Identification on Multiparty Conversation: Identifying Mentions of Characters in TV Shows
| Title | Character Identification on Multiparty Conversation: Identifying Mentions of Characters in TV Shows |
| Authors | Yu-Hsin Chen, Jinho D. Choi |
| Abstract | |
| Tasks | Coreference Resolution, Entity Linking, Question Answering, Reading Comprehension |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3612/ |
| https://www.aclweb.org/anthology/W16-3612 | |
| PWC | https://paperswithcode.com/paper/character-identification-on-multiparty |
| Repo | https://github.com/emorynlp/character-mining |
| Framework | none |
Convolutional Neural Network Language Models
| Title | Convolutional Neural Network Language Models |
| Authors | Ngoc-Quan Pham, German Kruszewski, Gemma Boleda |
| Abstract | |
| Tasks | Document Classification, Information Retrieval, Language Modelling, Machine Translation, Relation Extraction, Scene Parsing, Sentence Classification, Sentiment Analysis, Speech Recognition, Temporal Action Localization |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1123/ |
| https://www.aclweb.org/anthology/D16-1123 | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-network-language-models |
| Repo | https://github.com/quanpn90/NCE_CNNLM |
| Framework | torch |
Should Have, Would Have, Could Have. Investigating Verb Group Representations for Parsing with Universal Dependencies.
| Title | Should Have, Would Have, Could Have. Investigating Verb Group Representations for Parsing with Universal Dependencies. |
| Authors | Miryam de Lhoneux, Joakim Nivre |
| Abstract | |
| Tasks | Constituency Parsing, Dependency Parsing |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1202/ |
| https://www.aclweb.org/anthology/W16-1202 | |
| PWC | https://paperswithcode.com/paper/should-have-would-have-could-have |
| Repo | https://github.com/mdelhoneux/oDETTE |
| Framework | none |
