Paper Group NANR 92
Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input. Content-based Influence Modeling for Opinion Behavior Prediction. LIMSI@WMT’16: Machine Translation of News. A Machine Learning based Music Retrieval and Recommendation System. Word embeddings and discourse information for Quality Estimation. papago: A Machine Transl …
Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input
| Title | Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input |
| Authors | Cory Shain, William Bryce, Lifeng Jin, Victoria Krakovna, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz |
| Abstract | This paper presents a new memory-bounded left-corner parsing model for unsupervised raw-text syntax induction, using unsupervised hierarchical hidden Markov models (UHHMM). We deploy this algorithm to shed light on the extent to which human language learners can discover hierarchical syntax through distributional statistics alone, by modeling two widely-accepted features of human language acquisition and sentence processing that have not been simultaneously modeled by any existing grammar induction algorithm: (1) a left-corner parsing strategy and (2) limited working memory capacity. To model realistic input to human language learners, we evaluate our system on a corpus of child-directed speech rather than typical newswire corpora. Results beat or closely match those of three competing systems. |
| Tasks | Language Acquisition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1092/ |
| https://www.aclweb.org/anthology/C16-1092 | |
| PWC | https://paperswithcode.com/paper/memory-bounded-left-corner-unsupervised |
| Repo | |
| Framework | |
Content-based Influence Modeling for Opinion Behavior Prediction
| Title | Content-based Influence Modeling for Opinion Behavior Prediction |
| Authors | Chengyao Chen, Zhitao Wang, Yu Lei, Wenjie Li |
| Abstract | Nowadays, social media has become a popular platform for companies to understand their customers. It provides valuable opportunities to gain new insights into how a person{'}s opinion about a product is influenced by his friends. Though various approaches have been proposed to study the opinion formation problem, they all formulate opinions as the derived sentiment values either discrete or continuous without considering the semantic information. In this paper, we propose a Content-based Social Influence Model to study the implicit mechanism underlying the change of opinions. We then apply the learned model to predict users{'} future opinions. The advantages of the proposed model is the ability to handle the semantic information and to learn two influence components including the opinion influence of the content information and the social relation factors. In the experiments conducted on Twitter datasets, our model significantly outperforms other popular opinion formation models. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1208/ |
| https://www.aclweb.org/anthology/C16-1208 | |
| PWC | https://paperswithcode.com/paper/content-based-influence-modeling-for-opinion |
| Repo | |
| Framework | |
LIMSI@WMT’16: Machine Translation of News
| Title | LIMSI@WMT’16: Machine Translation of News |
| Authors | Alex Allauzen, re, Lauriane Aufrant, Franck Burlot, Oph{'e}lie Lacroix, Elena Knyazeva, Thomas Lavergne, Guillaume Wisniewski, Fran{\c{c}}ois Yvon |
| Abstract | |
| Tasks | Machine Translation, Tokenization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2304/ |
| https://www.aclweb.org/anthology/W16-2304 | |
| PWC | https://paperswithcode.com/paper/limsiwmta16-machine-translation-of-news |
| Repo | |
| Framework | |
A Machine Learning based Music Retrieval and Recommendation System
| Title | A Machine Learning based Music Retrieval and Recommendation System |
| Authors | Naziba Mostafa, Yan Wan, Unnayan Amitabh, Pascale Fung |
| Abstract | In this paper, we present a music retrieval and recommendation system using machine learning techniques. We propose a query by humming system for music retrieval that uses deep neural networks for note transcription and a note-based retrieval system for retrieving the correct song from the database. We evaluate our query by humming system using the standard MIREX QBSH dataset. We also propose a similar artist recommendation system which recommends similar artists based on acoustic features of the artists{'} music, online text descriptions of the artists and social media data. We use supervised machine learning techniques over all our features and compare our recommendation results to those produced by a popular similar artist recommendation website. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1312/ |
| https://www.aclweb.org/anthology/L16-1312 | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-based-music-retrieval-and |
| Repo | |
| Framework | |
Word embeddings and discourse information for Quality Estimation
| Title | Word embeddings and discourse information for Quality Estimation |
| Authors | Carolina Scarton, Daniel Beck, Kashif Shah, Karin Sim Smith, Lucia Specia |
| Abstract | |
| Tasks | Feature Engineering, Machine Translation, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2391/ |
| https://www.aclweb.org/anthology/W16-2391 | |
| PWC | https://paperswithcode.com/paper/word-embeddings-and-discourse-information-for |
| Repo | |
| Framework | |
papago: A Machine Translation Service with Word Sense Disambiguation and Currency Conversion
| Title | papago: A Machine Translation Service with Word Sense Disambiguation and Currency Conversion |
| Authors | Hyoung-Gyu Lee, Jun-Seok Kim, Joong-Hwi Shin, Jaesong Lee, Ying-Xiu Quan, Young-Seob Jeong |
| Abstract | In this paper, we introduce papago - a translator for mobile device which is equipped with new features that can provide convenience for users. The first feature is word sense disambiguation based on user feedback. By using the feature, users can select one among multiple meanings of a homograph and obtain the corrected translation with the user-selected sense. The second feature is the instant currency conversion of money expressions contained in a translation result with current exchange rate. Users can be quickly and precisely provided the amount of money converted as local currency when they travel abroad. |
| Tasks | Machine Translation, Optical Character Recognition, Speech Recognition, Speech Synthesis, Word Sense Disambiguation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2039/ |
| https://www.aclweb.org/anthology/C16-2039 | |
| PWC | https://paperswithcode.com/paper/papago-a-machine-translation-service-with |
| Repo | |
| Framework | |
Discriminative Deep Random Walk for Network Classification
| Title | Discriminative Deep Random Walk for Network Classification |
| Authors | Juzheng Li, Jun Zhu, Bo Zhang |
| Abstract | |
| Tasks | Anomaly Detection, Link Prediction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1095/ |
| https://www.aclweb.org/anthology/P16-1095 | |
| PWC | https://paperswithcode.com/paper/discriminative-deep-random-walk-for-network |
| Repo | |
| Framework | |
Dual Space Gradient Descent for Online Learning
| Title | Dual Space Gradient Descent for Online Learning |
| Authors | Trung Le, Tu Nguyen, Vu Nguyen, Dinh Phung |
| Abstract | One crucial goal in kernel online learning is to bound the model size. Common approaches employ budget maintenance procedures to restrict the model sizes using removal, projection, or merging strategies. Although projection and merging, in the literature, are known to be the most effective strategies, they demand extensive computation whilst removal strategy fails to retain information of the removed vectors. An alternative way to address the model size problem is to apply random features to approximate the kernel function. This allows the model to be maintained directly in the random feature space, hence effectively resolve the curse of kernelization. However, this approach still suffers from a serious shortcoming as it needs to use a high dimensional random feature space to achieve a sufficiently accurate kernel approximation. Consequently, it leads to a significant increase in the computational cost. To address all of these aforementioned challenges, we present in this paper the Dual Space Gradient Descent (DualSGD), a novel framework that utilizes random features as an auxiliary space to maintain information from data points removed during budget maintenance. Consequently, our approach permits the budget to be maintained in a simple, direct and elegant way while simultaneously mitigating the impact of the dimensionality issue on learning performance. We further provide convergence analysis and extensively conduct experiments on five real-world datasets to demonstrate the predictive performance and scalability of our proposed method in comparison with the state-of-the-art baselines. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6560-dual-space-gradient-descent-for-online-learning |
| http://papers.nips.cc/paper/6560-dual-space-gradient-descent-for-online-learning.pdf | |
| PWC | https://paperswithcode.com/paper/dual-space-gradient-descent-for-online |
| Repo | |
| Framework | |
An Efficient Streaming Algorithm for the Submodular Cover Problem
| Title | An Efficient Streaming Algorithm for the Submodular Cover Problem |
| Authors | Ashkan Norouzi-Fard, Abbas Bazzi, Ilija Bogunovic, Marwa El Halabi, Ya-Ping Hsieh, Volkan Cevher |
| Abstract | We initiate the study of the classical Submodular Cover (SC) problem in the data streaming model which we refer to as the Streaming Submodular Cover (SSC). We show that any single pass streaming algorithm using sublinear memory in the size of the stream will fail to provide any non-trivial approximation guarantees for SSC. Hence, we consider a relaxed version of SSC, where we only seek to find a partial cover. We design the first Efficient bicriteria Submodular Cover Streaming (ESC-Streaming) algorithm for this problem, and provide theoretical guarantees for its performance supported by numerical evidence. Our algorithm finds solutions that are competitive with the near-optimal offline greedy algorithm despite requiring only a single pass over the data stream. In our numerical experiments, we evaluate the performance of ESC-Streaming on active set selection and large-scale graph cover problems. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6175-an-efficient-streaming-algorithm-for-the-submodular-cover-problem |
| http://papers.nips.cc/paper/6175-an-efficient-streaming-algorithm-for-the-submodular-cover-problem.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-streaming-algorithm-for-the |
| Repo | |
| Framework | |
Comparison of Annotating Methods for Named Entity Corpora
| Title | Comparison of Annotating Methods for Named Entity Corpora |
| Authors | Kanako Komiya, Masaya Suzuki, Tomoya Iwakura, Minoru Sasaki, Hiroyuki Shinnou |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1708/ |
| https://www.aclweb.org/anthology/W16-1708 | |
| PWC | https://paperswithcode.com/paper/comparison-of-annotating-methods-for-named |
| Repo | |
| Framework | |
Book Review: Sentiment Analysis: Mining Opinions, Sentiments, and Emotions by Bing Liu
| Title | Book Review: Sentiment Analysis: Mining Opinions, Sentiments, and Emotions by Bing Liu |
| Authors | Jun Zhao, Kang Liu, Liheng Xu |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/J16-3008/ |
| https://www.aclweb.org/anthology/J16-3008 | |
| PWC | https://paperswithcode.com/paper/book-review-sentiment-analysis-mining |
| Repo | |
| Framework | |
The Role of Wikipedia in Text Analysis and Retrieval
| Title | The Role of Wikipedia in Text Analysis and Retrieval |
| Authors | Marius Pa{\c{s}}ca |
| Abstract | This tutorial examines the characteristics, advantages and limitations of Wikipedia relative to other existing, human-curated resources of knowledge; derivative resources, created by converting semi-structured content in Wikipedia into structured data; the role of Wikipedia and its derivatives in text analysis; and the role of Wikipedia and its derivatives in enhancing information retrieval. |
| Tasks | Coreference Resolution, Information Retrieval |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-3007/ |
| https://www.aclweb.org/anthology/C16-3007 | |
| PWC | https://paperswithcode.com/paper/the-role-of-wikipedia-in-text-analysis-and |
| Repo | |
| Framework | |
Intersecting Word Vectors to Take Figurative Language to New Heights
| Title | Intersecting Word Vectors to Take Figurative Language to New Heights |
| Authors | Andrea Gagliano, Emily Paul, Kyle Booten, Marti A. Hearst |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0203/ |
| https://www.aclweb.org/anthology/W16-0203 | |
| PWC | https://paperswithcode.com/paper/intersecting-word-vectors-to-take-figurative |
| Repo | |
| Framework | |
Multi-Granularity Chinese Word Embedding
| Title | Multi-Granularity Chinese Word Embedding |
| Authors | Rongchao Yin, Quan Wang, Peng Li, Rui Li, Bin Wang |
| Abstract | |
| Tasks | Learning Word Embeddings, Word Embeddings |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1100/ |
| https://www.aclweb.org/anthology/D16-1100 | |
| PWC | https://paperswithcode.com/paper/multi-granularity-chinese-word-embedding |
| Repo | |
| Framework | |
Pivoting Methods and Data for Czech-Vietnamese Translation via English
| Title | Pivoting Methods and Data for Czech-Vietnamese Translation via English |
| Authors | Duc Tam Hoang, Ondrej Bojar |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3408/ |
| https://www.aclweb.org/anthology/W16-3408 | |
| PWC | https://paperswithcode.com/paper/pivoting-methods-and-data-for-czech |
| Repo | |
| Framework | |
