Paper Group NANR 179
NITMZ-JU at IJCNLP-2017 Task 4: Customer Feedback Analysis. YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations. Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems. YNU-HPCC at IJCNLP-2017 Task 5: Multi-choice Question Answering in Exams Using an Attenti …
NITMZ-JU at IJCNLP-2017 Task 4: Customer Feedback Analysis
| Title | NITMZ-JU at IJCNLP-2017 Task 4: Customer Feedback Analysis |
| Authors | Somnath Banerjee, Partha Pakray, Riyanka Manna, Dipankar Das, Alex Gelbukh, er |
| Abstract | In this paper, we describe a deep learning framework for analyzing the customer feedback as part of our participation in the shared task on Customer Feedback Analysis at the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017). A Convolutional Neural Network (CNN) based deep neural network model was employed for the customer feedback task. The proposed system was evaluated on two languages, namely, English and French. |
| Tasks | Text Classification |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4030/ |
| https://www.aclweb.org/anthology/I17-4030 | |
| PWC | https://paperswithcode.com/paper/nitmz-ju-at-ijcnlp-2017-task-4-customer |
| Repo | |
| Framework | |
YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations
| Title | YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations |
| Authors | Min Wang, Qingxun Liu, Peng Ding, Yongbin Li, Xiaobing Zhou |
| Abstract | In this paper, we perform convolutional neural networks (CNN) to learn the joint representations of question-answer pairs first, then use the joint representations as the inputs of the long short-term memory (LSTM) with attention to learn the answer sequence of a question for labeling the matching quality of each answer. We also incorporating external knowledge by training Word2Vec on Flashcards data, thus we get more compact embedding. Experimental results show that our method achieves better or comparable performance compared with the baseline system. The proposed approach achieves the accuracy of 0.39, 0.42 in English valid set, test set, respectively. |
| Tasks | Question Answering |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4032/ |
| https://www.aclweb.org/anthology/I17-4032 | |
| PWC | https://paperswithcode.com/paper/ynudlg-at-ijcnlp-2017-task-5-a-cnn-lstm-model |
| Repo | |
| Framework | |
Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems
| Title | Expectation Propagation with Stochastic Kinetic Model in Complex Interaction Systems |
| Authors | Le Fang, Fan Yang, Wen Dong, Tong Guan, Chunming Qiao |
| Abstract | Technological breakthroughs allow us to collect data with increasing spatio-temporal resolution from complex interaction systems. The combination of high-resolution observations, expressive dynamic models, and efficient machine learning algorithms can lead to crucial insights into complex interaction dynamics and the functions of these systems. In this paper, we formulate the dynamics of a complex interacting network as a stochastic process driven by a sequence of events, and develop expectation propagation algorithms to make inferences from noisy observations. To avoid getting stuck at a local optimum, we formulate the problem of minimizing Bethe free energy as a constrained primal problem and take advantage of the concavity of dual problem in the feasible domain of dual variables guaranteed by duality theorem. Our expectation propagation algorithms demonstrate better performance in inferring the interaction dynamics in complex transportation networks than competing models such as particle filter, extended Kalman filter, and deep neural networks. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6798-expectation-propagation-with-stochastic-kinetic-model-in-complex-interaction-systems |
| http://papers.nips.cc/paper/6798-expectation-propagation-with-stochastic-kinetic-model-in-complex-interaction-systems.pdf | |
| PWC | https://paperswithcode.com/paper/expectation-propagation-with-stochastic |
| Repo | |
| Framework | |
YNU-HPCC at IJCNLP-2017 Task 5: Multi-choice Question Answering in Exams Using an Attention-based LSTM Model
| Title | YNU-HPCC at IJCNLP-2017 Task 5: Multi-choice Question Answering in Exams Using an Attention-based LSTM Model |
| Authors | Hang Yuan, You Zhang, Jin Wang, Xuejie Zhang |
| Abstract | A shared task is a typical question answering task that aims to test how accurately the participants can answer the questions in exams. Typically, for each question, there are four candidate answers, and only one of the answers is correct. The existing methods for such a task usually implement a recurrent neural network (RNN) or long short-term memory (LSTM). However, both RNN and LSTM are biased models in which the words in the tail of a sentence are more dominant than the words in the header. In this paper, we propose the use of an attention-based LSTM (AT-LSTM) model for these tasks. By adding an attention mechanism to the standard LSTM, this model can more easily capture long contextual information. |
| Tasks | Information Retrieval, Question Answering, Word Embeddings |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4035/ |
| https://www.aclweb.org/anthology/I17-4035 | |
| PWC | https://paperswithcode.com/paper/ynu-hpcc-at-ijcnlp-2017-task-5-multi-choice |
| Repo | |
| Framework | |
Zap Q-Learning
| Title | Zap Q-Learning |
| Authors | Adithya M Devraj, Sean Meyn |
| Abstract | The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins’ original algorithm and recent competitors in several respects. It is a matrix-gain algorithm designed so that its asymptotic variance is optimal. Moreover, an ODE analysis suggests that the transient behavior is a close match to a deterministic Newton-Raphson implementation. This is made possible by a two time-scale update equation for the matrix gain sequence. The analysis suggests that the approach will lead to stable and efficient computation even for non-ideal parameterized settings. Numerical experiments confirm the quick convergence, even in such non-ideal cases. |
| Tasks | Q-Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6818-zap-q-learning |
| http://papers.nips.cc/paper/6818-zap-q-learning.pdf | |
| PWC | https://paperswithcode.com/paper/zap-q-learning |
| Repo | |
| Framework | |
Alternative Objective Functions for Training MT Evaluation Metrics
| Title | Alternative Objective Functions for Training MT Evaluation Metrics |
| Authors | Milo{\v{s}} Stanojevi{'c}, Khalil Sima{'}an |
| Abstract | MT evaluation metrics are tested for correlation with human judgments either at the sentence- or the corpus-level. Trained metrics ignore corpus-level judgments and are trained for high sentence-level correlation only. We show that training only for one objective (sentence or corpus level), can not only harm the performance on the other objective, but it can also be suboptimal for the objective being optimized. To this end we present a metric trained for corpus-level and show empirical comparison against a metric trained for sentence-level exemplifying how their performance may vary per language pair, type and level of judgment. Subsequently we propose a model trained to optimize both objectives simultaneously and show that it is far more stable than{–}and on average outperforms{–}both models on both objectives. |
| Tasks | Learning-To-Rank, Machine Translation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2004/ |
| https://www.aclweb.org/anthology/P17-2004 | |
| PWC | https://paperswithcode.com/paper/alternative-objective-functions-for-training |
| Repo | |
| Framework | |
JU NITM at IJCNLP-2017 Task 5: A Classification Approach for Answer Selection in Multi-choice Question Answering System
| Title | JU NITM at IJCNLP-2017 Task 5: A Classification Approach for Answer Selection in Multi-choice Question Answering System |
| Authors | S Sarkar, ip, Dipankar Das, Partha Pakray |
| Abstract | This paper describes the participation of the JU NITM team in IJCNLP-2017 Task 5: {``}Multi-choice Question Answering in Examinations{''}. The main aim of this shared task is to choose the correct option for each multi-choice question. Our proposed model includes vector representations as feature and machine learning for classification. At first we represent question and answer in vector space and after that find the cosine similarity between those two vectors. Finally we apply classification approach to find the correct answer. Our system was only developed for the English language, and it obtained an accuracy of 40.07{%} for test dataset and 40.06{%} for valid dataset. | |
| Tasks | Answer Selection, Community Question Answering, Information Retrieval, Language Modelling, Question Answering |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4036/ |
| https://www.aclweb.org/anthology/I17-4036 | |
| PWC | https://paperswithcode.com/paper/ju-nitm-at-ijcnlp-2017-task-5-a |
| Repo | |
| Framework | |
Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
| Title | Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2200/ |
| https://www.aclweb.org/anthology/W17-2200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-joint-sighum-workshop-on |
| Repo | |
| Framework | |
Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs
| Title | Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs |
| Authors | Rowan Mcallister, Carl Edward Rasmussen |
| Abstract | We present a data-efficient reinforcement learning method for continuous state-action systems under significant observation noise. Data-efficient solutions under small noise exist, such as PILCO which learns the cartpole swing-up task in 30s. PILCO evaluates policies by planning state-trajectories using a dynamics model. However, PILCO applies policies to the observed state, therefore planning in observation space. We extend PILCO with filtering to instead plan in belief space, consistent with partially observable Markov decisions process (POMDP) planning. This enables data-efficient learning under significant observation noise, outperforming more naive methods such as post-hoc application of a filter to policies optimised by the original (unfiltered) PILCO algorithm. We test our method on the cartpole swing-up task, which involves nonlinear dynamics and requires nonlinear control. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6799-data-efficient-reinforcement-learning-in-continuous-state-action-gaussian-pomdps |
| http://papers.nips.cc/paper/6799-data-efficient-reinforcement-learning-in-continuous-state-action-gaussian-pomdps.pdf | |
| PWC | https://paperswithcode.com/paper/data-efficient-reinforcement-learning-in |
| Repo | |
| Framework | |
Morphological Analysis without Expert Annotation
| Title | Morphological Analysis without Expert Annotation |
| Authors | Garrett Nicolai, Grzegorz Kondrak |
| Abstract | The task of morphological analysis is to produce a complete list of lemma+tag analyses for a given word-form. We propose a discriminative string transduction approach which exploits plain inflection tables and raw text corpora, thus obviating the need for expert annotation. Experiments on four languages demonstrate that our system has much higher coverage than a hand-engineered FST analyzer, and is more accurate than a state-of-the-art morphological tagger. |
| Tasks | Morphological Analysis, Morphological Tagging |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2034/ |
| https://www.aclweb.org/anthology/E17-2034 | |
| PWC | https://paperswithcode.com/paper/morphological-analysis-without-expert |
| Repo | |
| Framework | |
Olelo: A Question Answering Application for Biomedicine
| Title | Olelo: A Question Answering Application for Biomedicine |
| Authors | Mariana Neves, Hendrik Folkerts, Marcel Jankrift, Julian Niedermeier, Toni Stachewicz, S{"o}ren Tietb{"o}hl, Milena Kraus, Matthias Uflacker |
| Abstract | |
| Tasks | Information Retrieval, Named Entity Recognition, Question Answering, Tokenization |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4011/ |
| https://www.aclweb.org/anthology/P17-4011 | |
| PWC | https://paperswithcode.com/paper/olelo-a-question-answering-application-for |
| Repo | |
| Framework | |
The Challenge of Composition in Distributional and Formal Semantics
| Title | The Challenge of Composition in Distributional and Formal Semantics |
| Authors | Ran Tian, Koji Mineshima, Pascual Mart{'\i}nez-G{'o}mez |
| Abstract | This is tutorial proposal. Abstract is as follows: The principle of compositionality states that the meaning of a complete sentence must be explained in terms of the meanings of its subsentential parts; in other words, each syntactic operation should have a corresponding semantic operation. In recent years, it has been increasingly evident that distributional and formal semantics are complementary in addressing composition; while the distributional/vector-based approach can naturally measure semantic similarity (Mitchell and Lapata, 2010), the formal/symbolic approach has a long tradition within logic-based semantic frameworks (Montague, 1974) and can readily be connected to theorem provers or databases to perform complicated tasks. In this tutorial, we will cover recent efforts in extending word vectors to account for composition and reasoning, the various challenging phenomena observed in composition and addressed by formal semantics, and a hybrid approach that combines merits of the two. Outline and introduction to instructors are found in the submission. Ran Tian has taught a tutorial at the Annual Meeting of the Association for Natural Language Processing in Japan, 2015. The estimated audience size was about one hundred. Only a limited part of the contents in this tutorial is drawn from the previous one. Koji Mineshima has taught a one-week course at the 28th European Summer School in Logic, Language and Information (ESSLLI2016), together with Prof. Daisuke Bekki. Only a few contents are the same with this tutorial. Tutorials on {}CCG Semantic Parsing{''} have been given in ACL2013, EMNLP2014, and AAAI2015. A coming tutorial on {}Deep Learning for Semantic Composition{''} will be given in ACL2017. Contents in these tutorials are somehow related to but not overlapping with our proposal. |
| Tasks | Natural Language Inference, Semantic Composition, Semantic Parsing, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-5006/ |
| https://www.aclweb.org/anthology/I17-5006 | |
| PWC | https://paperswithcode.com/paper/the-challenge-of-composition-in |
| Repo | |
| Framework | |
An Ensemble Method with Sentiment Features and Clustering Support
| Title | An Ensemble Method with Sentiment Features and Clustering Support |
| Authors | Huy Tien Nguyen, Minh Le Nguyen |
| Abstract | Deep learning models have recently been applied successfully in natural language processing, especially sentiment analysis. Each deep learning model has a particular advantage, but it is difficult to combine these advantages into one model, especially in the area of sentiment analysis. In our approach, Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) were utilized to learn sentiment-specific features in a freezing scheme. This scenario provides a novel and efficient way for integrating advantages of deep learning models. In addition, we also grouped documents into clusters by their similarity and applied the prediction score of Naive Bayes SVM (NBSVM) method to boost the classification accuracy of each group. The experiments show that our method achieves the state-of-the-art performance on two well-known datasets: IMDB large movie reviews for document level and Pang {&} Lee movie reviews for sentence level. |
| Tasks | Information Retrieval, Sentiment Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1065/ |
| https://www.aclweb.org/anthology/I17-1065 | |
| PWC | https://paperswithcode.com/paper/an-ensemble-method-with-sentiment-features |
| Repo | |
| Framework | |
Toward an NLG System for Bantu languages: first steps with Runyankore (demo)
| Title | Toward an NLG System for Bantu languages: first steps with Runyankore (demo) |
| Authors | Joan Byamugisha, C. Maria Keet, Brian DeRenzi |
| Abstract | There are many domain-specific and language-specific NLG systems, of which it may be possible to adapt to related domains and languages. The languages in the Bantu language family have their own set of features distinct from other major groups, which therefore severely limits the options to bootstrap an NLG system from existing ones. We present here our first proof-of-concept application for knowledge-to-text NLG as a plugin to the Protege 5.x ontology development system, tailored to Runyankore, a Bantu language indigenous to Uganda. It comprises a basic annotation model for linguistic information such as noun class, an implementation of existing verbalisation rules and a CFG for verbs, and a basic interface for data entry. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3523/ |
| https://www.aclweb.org/anthology/W17-3523 | |
| PWC | https://paperswithcode.com/paper/toward-an-nlg-system-for-bantu-languages |
| Repo | |
| Framework | |
An Insight Extraction System on BioMedical Literature with Deep Neural Networks
| Title | An Insight Extraction System on BioMedical Literature with Deep Neural Networks |
| Authors | Hua He, Kris Ganjam, Navendu Jain, Jessica Lundin, Ryen White, Jimmy Lin |
| Abstract | Mining biomedical text offers an opportunity to automatically discover important facts and infer associations among them. As new scientific findings appear across a large collection of biomedical publications, our aim is to tap into this literature to automate biomedical knowledge extraction and identify important insights from them. Towards that goal, we develop a system with novel deep neural networks to extract insights on biomedical literature. Evaluation shows our system is able to provide insights with competitive accuracy of human acceptance and its relation extraction component outperforms previous work. |
| Tasks | Relation Extraction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1285/ |
| https://www.aclweb.org/anthology/D17-1285 | |
| PWC | https://paperswithcode.com/paper/an-insight-extraction-system-on-biomedical |
| Repo | |
| Framework | |
