Paper Group NANR 160
Fast Collocation-Based Bayesian HMM Word Alignment. Linggle Knows: A Search Engine Tells How People Write. CAMR at SemEval-2016 Task 8: An Extended Transition-based AMR Parser. Deep Learning Games. Gulf Arabic Linguistic Resource Building for Sentiment Analysis. Deep iris representation with applications in iris recognition and cross-sensor iris re …
Fast Collocation-Based Bayesian HMM Word Alignment
| Title | Fast Collocation-Based Bayesian HMM Word Alignment |
| Authors | Philip Schulz, Wilker Aziz |
| Abstract | We present a new Bayesian HMM word alignment model for statistical machine translation. The model is a mixture of an alignment model and a language model. The alignment component is a Bayesian extension of the standard HMM. The language model component is responsible for the generation of words needed for source fluency reasons from source language context. This allows for untranslatable source words to remain unaligned and at the same time avoids the introduction of artificial NULL words which introduces unusually long alignment jumps. Existing Bayesian word alignment models are unpractically slow because they consider each target position when resampling a given alignment link. The sampling complexity therefore grows linearly in the target sentence length. In order to make our model useful in practice, we devise an auxiliary variable Gibbs sampler that allows us to resample alignment links in constant time independently of the target sentence length. This leads to considerable speed improvements. Experimental results show that our model performs as well as existing word alignment toolkits in terms of resulting BLEU score. |
| Tasks | Language Modelling, Machine Translation, Word Alignment |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1296/ |
| https://www.aclweb.org/anthology/C16-1296 | |
| PWC | https://paperswithcode.com/paper/fast-collocation-based-bayesian-hmm-word |
| Repo | |
| Framework | |
Linggle Knows: A Search Engine Tells How People Write
| Title | Linggle Knows: A Search Engine Tells How People Write |
| Authors | Jhih-Jie Chen, Hao-Chun Peng, Mei-Cih Yeh, Peng-Yu Chen, Jason Chang |
| Abstract | This paper shows the great potential of incorporating different approaches to help writing. Not only did they solve different kinds of writing problems, but also they complement and reinforce each other to be a complete and effective solution. Despite the extensive and multifaceted feedback and suggestion, writing is not all about syntactically or lexically well-written. It involves contents, structure, the certain understanding of the background, and many other factors to compose a rich, organized and sophisticated text. (e.g., conventional structure and idioms in academic writing). There is still a long way to go to accomplish the ultimate goal. We envision the future of writing to be a joyful experience with the help of instantaneous suggestion and constructive feedback. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2035/ |
| https://www.aclweb.org/anthology/C16-2035 | |
| PWC | https://paperswithcode.com/paper/linggle-knows-a-search-engine-tells-how |
| Repo | |
| Framework | |
CAMR at SemEval-2016 Task 8: An Extended Transition-based AMR Parser
| Title | CAMR at SemEval-2016 Task 8: An Extended Transition-based AMR Parser |
| Authors | Chuan Wang, Sameer Pradhan, Xiaoman Pan, Heng Ji, Nianwen Xue |
| Abstract | |
| Tasks | Amr Parsing, Dependency Parsing, Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1181/ |
| https://www.aclweb.org/anthology/S16-1181 | |
| PWC | https://paperswithcode.com/paper/camr-at-semeval-2016-task-8-an-extended |
| Repo | |
| Framework | |
Deep Learning Games
| Title | Deep Learning Games |
| Authors | Dale Schuurmans, Martin A. Zinkevich |
| Abstract | We investigate a reduction of supervised learning to game playing that reveals new connections and learning methods. For convex one-layer problems, we demonstrate an equivalence between global minimizers of the training problem and Nash equilibria in a simple game. We then show how the game can be extended to general acyclic neural networks with differentiable convex gates, establishing a bijection between the Nash equilibria and critical (or KKT) points of the deep learning problem. Based on these connections we investigate alternative learning methods, and find that regret matching can achieve competitive training performance while producing sparser models than current deep learning approaches. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6315-deep-learning-games |
| http://papers.nips.cc/paper/6315-deep-learning-games.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-games |
| Repo | |
| Framework | |
Gulf Arabic Linguistic Resource Building for Sentiment Analysis
| Title | Gulf Arabic Linguistic Resource Building for Sentiment Analysis |
| Authors | Wafia Adouane, Richard Johansson |
| Abstract | This paper deals with building linguistic resources for Gulf Arabic, one of the Arabic variations, for sentiment analysis task using machine learning. To our knowledge, no previous works were done for Gulf Arabic sentiment analysis despite the fact that it is present in different online platforms. Hence, the first challenge is the absence of annotated data and sentiment lexicons. To fill this gap, we created these two main linguistic resources. Then we conducted different experiments: use Naive Bayes classifier without any lexicon; add a sentiment lexicon designed basically for MSA; use only the compiled Gulf Arabic sentiment lexicon and finally use both MSA and Gulf Arabic sentiment lexicons. The Gulf Arabic lexicon gives a good improvement of the classifier accuracy (90.54 {%}) over a baseline that does not use the lexicon (82.81{%}), while the MSA lexicon causes the accuracy to drop to (76.83{%}). Moreover, mixing MSA and Gulf Arabic lexicons causes the accuracy to drop to (84.94{%}) compared to using only Gulf Arabic lexicon. This indicates that it is useless to use MSA resources to deal with Gulf Arabic due to the considerable differences and conflicting structures between these two languages. |
| Tasks | Arabic Sentiment Analysis, Sentiment Analysis |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1430/ |
| https://www.aclweb.org/anthology/L16-1430 | |
| PWC | https://paperswithcode.com/paper/gulf-arabic-linguistic-resource-building-for |
| Repo | |
| Framework | |
Deep iris representation with applications in iris recognition and cross-sensor iris recognition
| Title | Deep iris representation with applications in iris recognition and cross-sensor iris recognition |
| Authors | abhishek, akanksha |
| Abstract | Despite significant advances in iris recognition (IR), the efficient and robust IR at scale and in non-ideal conditions presents serious performance issues and is still ongoing research topic. Deep Convolution Neural Networks (DCNN) are powerful visual models that have reported state-of-theart performance in several domains. In this paper, we propose deep learning based method termed as DeepIrisNet for iris representation. The proposed approach bases on very deep architecture and various tricks from recent successful CNNs. Experimental analysis reveal that proposed DeepIrisNet can model the micro-structures of iris very effectively and provides robust, discriminative, compact, and very easy-to-implement iris representation that obtains state-of-the-art accuracy. Furthermore, we evaluate our iris representation for cross-sensor IR. The experimental results demonstrate that DeepIrisNet models obtain a significant improvement in cross-sensor recognition accuracy too. |
| Tasks | Iris Recognition |
| Published | 2016-09-25 |
| URL | http://apps.webofknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=4&SID=8DMTkMpwgZDXBYO5ilS&page=1&doc=1 |
| http://apps.webofknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=4&SID=8DMTkMpwgZDXBYO5ilS&page=1&doc=1 | |
| PWC | https://paperswithcode.com/paper/deep-iris-representation-with-applications-in |
| Repo | |
| Framework | |
A Tool for Efficient Content Compilation
| Title | A Tool for Efficient Content Compilation |
| Authors | Boris Galitsky |
| Abstract | We build a tool to assist in content creation by mining the web for information relevant to a given topic. This tool imitates the process of essay writing by humans: searching for topics on the web, selecting content frag-ments from the found document, and then compiling these fragments to obtain a coherent text. The process of writing starts with automated building of a table of content by obtaining the list of key entities for the given topic extracted from web resources such as Wikipedia. Once a table of content is formed, each item forms a seed for web mining. The tool builds a full-featured structured Word document with table of content, section structure, images and captions and web references for all mined text fragments. Two linguistic technologies are employed: for relevance verification, we use similarity computed as a tree similarity between parse trees for a seed and candidate text fragment. For text coherence, we use a measure of agreement between a given and consecutive paragraph by tree kernel learning of their discourse trees. The tool is available at \url{http://animatronica.io/submit.html}. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2042/ |
| https://www.aclweb.org/anthology/C16-2042 | |
| PWC | https://paperswithcode.com/paper/a-tool-for-efficient-content-compilation |
| Repo | |
| Framework | |
Botta: An Arabic Dialect Chatbot
| Title | Botta: An Arabic Dialect Chatbot |
| Authors | Dana Abu Ali, Nizar Habash |
| Abstract | This paper presents BOTTA, the first Arabic dialect chatbot. We explore the challenges of creating a conversational agent that aims to simulate friendly conversations using the Egyptian Arabic dialect. We present a number of solutions and describe the different components of the BOTTA chatbot. The BOTTA database files are publicly available for researchers working on Arabic chatbot technologies. The BOTTA chatbot is also publicly available for any users who want to chat with it online. |
| Tasks | Chatbot |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2044/ |
| https://www.aclweb.org/anthology/C16-2044 | |
| PWC | https://paperswithcode.com/paper/botta-an-arabic-dialect-chatbot |
| Repo | |
| Framework | |
What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation
| Title | What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation |
| Authors | Ivan Habernal, Iryna Gurevych |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1129/ |
| https://www.aclweb.org/anthology/D16-1129 | |
| PWC | https://paperswithcode.com/paper/what-makes-a-convincing-argument-empirical |
| Repo | |
| Framework | |
A Neural Model for Language Identification in Code-Switched Tweets
| Title | A Neural Model for Language Identification in Code-Switched Tweets |
| Authors | Aaron Jaech, George Mulcaire, Mari Ostendorf, Noah A. Smith |
| Abstract | |
| Tasks | Language Identification, Language Modelling, Machine Translation, Semantic Parsing |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5807/ |
| https://www.aclweb.org/anthology/W16-5807 | |
| PWC | https://paperswithcode.com/paper/a-neural-model-for-language-identification-in |
| Repo | |
| Framework | |
The Role of Intrinsic Motivation in Artificial Language Emergence: a Case Study on Colour
| Title | The Role of Intrinsic Motivation in Artificial Language Emergence: a Case Study on Colour |
| Authors | Miquel Cornudella, Thierry Poibeau, Remi van Trijp |
| Abstract | Human languages have multiple strategies that allow us to discriminate objects in a vast variety of contexts. Colours have been extensively studied from this point of view. In particular, previous research in artificial language evolution has shown how artificial languages may emerge based on specific strategies to distinguish colours. Still, it has not been shown how several strategies of diverse complexity can be autonomously managed by artificial agents . We propose an intrinsic motivation system that allows agents in a population to create a shared artificial language and progressively increase its expressive power. Our results show that with such a system agents successfully regulate their language development, which indicates a relation between population size and consistency in the emergent communicative systems. |
| Tasks | Artificial Life |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1155/ |
| https://www.aclweb.org/anthology/C16-1155 | |
| PWC | https://paperswithcode.com/paper/the-role-of-intrinsic-motivation-in |
| Repo | |
| Framework | |
Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems
| Title | Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems |
| Authors | Shyam Upadhyay, Ming-Wei Chang, Kai-Wei Chang, Wen-tau Yih |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1029/ |
| https://www.aclweb.org/anthology/D16-1029 | |
| PWC | https://paperswithcode.com/paper/learning-from-explicit-and-implicit |
| Repo | |
| Framework | |
Threshold Bandits, With and Without Censored Feedback
| Title | Threshold Bandits, With and Without Censored Feedback |
| Authors | Jacob D. Abernethy, Kareem Amin, Ruihao Zhu |
| Abstract | We consider the \emph{Threshold Bandit} setting, a variant of the classical multi-armed bandit problem in which the reward on each round depends on a piece of side information known as a \emph{threshold value}. The learner selects one of $K$ actions (arms), this action generates a random sample from a fixed distribution, and the action then receives a unit payoff in the event that this sample exceeds the threshold value. We consider two versions of this problem, the \emph{uncensored} and \emph{censored} case, that determine whether the sample is always observed or only when the threshold is not met. Using new tools to understand the popular UCB algorithm, we show that the uncensored case is essentially no more difficult than the classical multi-armed bandit setting. Finally we show that the censored case exhibits more challenges, but we give guarantees in the event that the sequence of threshold values is generated optimistically. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6149-threshold-bandits-with-and-without-censored-feedback |
| http://papers.nips.cc/paper/6149-threshold-bandits-with-and-without-censored-feedback.pdf | |
| PWC | https://paperswithcode.com/paper/threshold-bandits-with-and-without-censored |
| Repo | |
| Framework | |
Proceedings of the ACL 2016 Student Research Workshop
| Title | Proceedings of the ACL 2016 Student Research Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-3000/ |
| https://www.aclweb.org/anthology/P16-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-acl-2016-student-research |
| Repo | |
| Framework | |
Learning to Represent Review with Tensor Decomposition for Spam Detection
| Title | Learning to Represent Review with Tensor Decomposition for Spam Detection |
| Authors | Xuepeng Wang, Kang Liu, Shizhu He, Jun Zhao |
| Abstract | |
| Tasks | Opinion Mining |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1083/ |
| https://www.aclweb.org/anthology/D16-1083 | |
| PWC | https://paperswithcode.com/paper/learning-to-represent-review-with-tensor |
| Repo | |
| Framework | |
