Paper Group NANR 9
Evaluating Preprocessing Strategies for Time Series Prediction Using Deep Learning Architectures. Character Based Pattern Mining for Neology Detection. Automatic identification of head movements in video-recorded conversations: can words help?. Technical Report for E2E NLG Challenge. Textmining at EmoInt-2017: A Deep Learning Approach to Sentiment …
Evaluating Preprocessing Strategies for Time Series Prediction Using Deep Learning Architectures
| Title | Evaluating Preprocessing Strategies for Time Series Prediction Using Deep Learning Architectures |
| Authors | Sajitha Naduvil-Vadukootu, Rafal A. Angryk, Pete Riley |
| Abstract | We propose a novel approach to combine state-of-the-art time series data processing methods, such as symbolic aggregate approximation (SAX), with very recently developed deep neural network architectures, such as deep recurrent neural networks (DRNN), for time series data modeling and prediction. Time series data appear extensively in various scientific domains and industrial applications, yet the challenges in accurate modeling and prediction from such data remain open. Deep recurrent neural networks (DRNN) have been proposed as promising approaches to sequence prediction. We extend this research to the new challenge of the time series prediction space, building a system that effectively combines recurrent neural networks (RNN) with time series specific preprocessing techniques. Our experiments show comparisons of model performance with various data preprocessing techniques. We demonstrate that preprocessed inputs can steer us towards simpler (and therefore more computationally efficient) architectures of neural networks (when compared to original inputs). |
| Tasks | Time Series, Time Series Prediction |
| Published | 2017-01-01 |
| URL | https://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/download/15475/14995 |
| https://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/download/15475/14995 | |
| PWC | https://paperswithcode.com/paper/evaluating-preprocessing-strategies-for-time |
| Repo | |
| Framework | |
Character Based Pattern Mining for Neology Detection
| Title | Character Based Pattern Mining for Neology Detection |
| Authors | Ga{"e}l Lejeune, Emmanuel Cartier |
| Abstract | Detecting neologisms is essential in real-time natural language processing applications. Not only can it enable to follow the lexical evolution of languages, but it is also essential for updating linguistic resources and parsers. In this paper, neology detection is considered as a classification task where a system has to assess whether a given lexical item is an actual neologism or not. We propose a combination of an unsupervised data mining technique and a supervised machine learning approach. It is inspired by current researches in stylometry and on token-level and character-level patterns. We train and evaluate our system on a manually designed reference dataset in French and Russian. We show that this approach is able to largely outperform state-of-the-art neology detection systems. Furthermore, character-level patterns exhibit good properties for multilingual extensions of the system. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4103/ |
| https://www.aclweb.org/anthology/W17-4103 | |
| PWC | https://paperswithcode.com/paper/character-based-pattern-mining-for-neology |
| Repo | |
| Framework | |
Automatic identification of head movements in video-recorded conversations: can words help?
| Title | Automatic identification of head movements in video-recorded conversations: can words help? |
| Authors | Patrizia Paggio, Costanza Navarretta, Bart Jongejan |
| Abstract | We present an approach where an SVM classifier learns to classify head movements based on measurements of velocity, acceleration, and the third derivative of position with respect to time, jerk. Consequently, annotations of head movements are added to new video data. The results of the automatic annotation are evaluated against manual annotations in the same data and show an accuracy of 68{%} with respect to these. The results also show that using jerk improves accuracy. We then conduct an investigation of the overlap between temporal sequences classified as either movement or non-movement and the speech stream of the person performing the gesture. The statistics derived from this analysis show that using word features may help increase the accuracy of the model. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-2006/ |
| https://www.aclweb.org/anthology/W17-2006 | |
| PWC | https://paperswithcode.com/paper/automatic-identification-of-head-movements-in |
| Repo | |
| Framework | |
Technical Report for E2E NLG Challenge
| Title | Technical Report for E2E NLG Challenge |
| Authors | Heng Gong |
| Abstract | This paper describes the primary system submitted by the author to the E2E NLG Challenge on the E2E Dataset (Novikova et al. (2017)). Based on the baseline system called TGen (Dusek and Jurcicek (2016)), the primary system uses REINFORCE to utilize multiple reference for single Meaning Representation during training, while the baseline model treated them as individual training instances. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2017-12-19 |
| URL | http://www.macs.hw.ac.uk/InteractionLab/E2E/final_papers/E2E-Gong.pdf |
| http://www.macs.hw.ac.uk/InteractionLab/E2E/final_papers/E2E-Gong.pdf | |
| PWC | https://paperswithcode.com/paper/technical-report-for-e2e-nlg-challenge |
| Repo | |
| Framework | |
Textmining at EmoInt-2017: A Deep Learning Approach to Sentiment Intensity Scoring of English Tweets
| Title | Textmining at EmoInt-2017: A Deep Learning Approach to Sentiment Intensity Scoring of English Tweets |
| Authors | Hardik Meisheri, Rupsa Saha, Priyanka Sinha, Lipika Dey |
| Abstract | This paper describes our approach to the Emotion Intensity shared task. A parallel architecture of Convolutional Neural Network (CNN) and Long short term memory networks (LSTM) alongwith two sets of features are extracted which aid the network in judging emotion intensity. Experiments on different models and various features sets are described and analysis on results has also been presented. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5226/ |
| https://www.aclweb.org/anthology/W17-5226 | |
| PWC | https://paperswithcode.com/paper/textmining-at-emoint-2017-a-deep-learning |
| Repo | |
| Framework | |
AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine
| Title | AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine |
| Authors | Minghui Qiu, Feng-Lin Li, Siyu Wang, Xing Gao, Yan Chen, Weipeng Zhao, Haiqing Chen, Jun Huang, Wei Chu |
| Abstract | We propose AliMe Chat, an open-domain chatbot engine that integrates the joint results of Information Retrieval (IR) and Sequence to Sequence (Seq2Seq) based generation models. AliMe Chat uses an attentive Seq2Seq based rerank model to optimize the joint results. Extensive experiments show our engine outperforms both IR and generation based models. We launch AliMe Chat for a real-world industrial application and observe better results than another public chatbot. |
| Tasks | Chatbot, Information Retrieval |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2079/ |
| https://www.aclweb.org/anthology/P17-2079 | |
| PWC | https://paperswithcode.com/paper/alime-chat-a-sequence-to-sequence-and-rerank |
| Repo | |
| Framework | |
A Question Answering Approach for Emotion Cause Extraction
| Title | A Question Answering Approach for Emotion Cause Extraction |
| Authors | Lin Gui, Jiannan Hu, Yulan He, Ruifeng Xu, Qin Lu, Jiachen Du |
| Abstract | Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is a much more difficult task compared to emotion classification. Inspired by recent advances in using deep memory networks for question answering (QA), we propose a new approach which considers emotion cause identification as a reading comprehension task in QA. Inspired by convolutional neural networks, we propose a new mechanism to store relevant context in different memory slots to model context information. Our proposed approach can extract both word level sequence features and lexical features. Performance evaluation shows that our method achieves the state-of-the-art performance on a recently released emotion cause dataset, outperforming a number of competitive baselines by at least 3.01{%} in F-measure. |
| Tasks | Emotion Classification, Emotion Recognition, Question Answering, Reading Comprehension, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1167/ |
| https://www.aclweb.org/anthology/D17-1167 | |
| PWC | https://paperswithcode.com/paper/a-question-answering-approach-for-emotion |
| Repo | |
| Framework | |
MoodSwipe: A Soft Keyboard that Suggests MessageBased on User-Specified Emotions
| Title | MoodSwipe: A Soft Keyboard that Suggests MessageBased on User-Specified Emotions |
| Authors | Chieh-Yang Huang, Tristan Labetoulle, Ting-Hao Huang, Yi-Pei Chen, Hung-Chen Chen, Vallari Srivastava, Lun-Wei Ku |
| Abstract | We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data. The aim of MoodSwipe is to create a convenient user interface to enjoy the technology of emotion classification and text suggestion, and at the same time to collect labeled data automatically for developing more advanced technologies. While users select the MoodSwipe keyboard, they can type as usual but sense the emotion conveyed by their text and receive suggestions for their message as a benefit. In MoodSwipe, the detected emotions serve as the medium for suggested texts, where viewing the latter is the incentive to correcting the former. We conduct several experiments to show the superiority of the emotion classification models trained on the dialog data, and further to verify good emotion cues are important context for text suggestion. |
| Tasks | Emotion Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-2013/ |
| https://www.aclweb.org/anthology/D17-2013 | |
| PWC | https://paperswithcode.com/paper/moodswipe-a-soft-keyboard-that-suggests |
| Repo | |
| Framework | |
DMGroup at EmoInt-2017: Emotion Intensity Using Ensemble Method
| Title | DMGroup at EmoInt-2017: Emotion Intensity Using Ensemble Method |
| Authors | Song Jiang, Xiaotian Han |
| Abstract | In this paper, we present a novel ensemble learning architecture for emotion intensity analysis, particularly a novel framework of ensemble method. The ensemble method has two stages and each stage includes several single machine learning models. In stage1, we employ both linear and nonlinear regression models to obtain a more diverse emotion intensity representation. In stage2, we use two regression models including linear regression and XGBoost. The result of stage1 serves as the input of stage2, so the two different type models (linear and non-linear) in stage2 can describe the input in two opposite aspects. We also added a method for analyzing and splitting multi-words hashtags and appending them to the emotion intensity corpus before feeding it to our model. Our model achieves 0.571 Pearson-measure for the average of four emotions. |
| Tasks | Emotion Classification, Emotion Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5234/ |
| https://www.aclweb.org/anthology/W17-5234 | |
| PWC | https://paperswithcode.com/paper/dmgroup-at-emoint-2017-emotion-intensity |
| Repo | |
| Framework | |
Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations
| Title | Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations |
| Authors | Geert Heyman, Ivan Vuli{'c}, Marie-Francine Moens |
| Abstract | We study the problem of bilingual lexicon induction (BLI) in a setting where some translation resources are available, but unknown translations are sought for certain, possibly domain-specific terminology. We frame BLI as a classification problem for which we design a neural network based classification architecture composed of recurrent long short-term memory and deep feed forward networks. The results show that word- and character-level representations each improve state-of-the-art results for BLI, and the best results are obtained by exploiting the synergy between these word- and character-level representations in the classification model. |
| Tasks | Cross-Lingual Entity Linking, Dependency Parsing, Entity Linking, Information Retrieval, Machine Translation, Representation Learning, Semantic Role Labeling, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1102/ |
| https://www.aclweb.org/anthology/E17-1102 | |
| PWC | https://paperswithcode.com/paper/bilingual-lexicon-induction-by-learning-to |
| Repo | |
| Framework | |
Predicting Pronouns with a Convolutional Network and an N-gram Model
| Title | Predicting Pronouns with a Convolutional Network and an N-gram Model |
| Authors | Christian Hardmeier |
| Abstract | This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model. |
| Tasks | Language Modelling, Machine Translation, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4807/ |
| https://www.aclweb.org/anthology/W17-4807 | |
| PWC | https://paperswithcode.com/paper/predicting-pronouns-with-a-convolutional |
| Repo | |
| Framework | |
On the Creation of a Security-Related Event Corpus
| Title | On the Creation of a Security-Related Event Corpus |
| Authors | Martin Atkinson, Jakub Piskorski, Hristo Tanev, Vanni Zavarella |
| Abstract | This paper reports on an effort of creating a corpus of structured information on security-related events automatically extracted from on-line news, part of which has been manually curated. The main motivation behind this effort is to provide material to the NLP community working on event extraction that could be used both for training and evaluation purposes. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2709/ |
| https://www.aclweb.org/anthology/W17-2709 | |
| PWC | https://paperswithcode.com/paper/on-the-creation-of-a-security-related-event |
| Repo | |
| Framework | |
A conceptual ontology in the water domain of knowledge to bridge the lexical semantics of stratified discursive strata
| Title | A conceptual ontology in the water domain of knowledge to bridge the lexical semantics of stratified discursive strata |
| Authors | Jean-Louis Janin, Henri Portine |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7003/ |
| https://www.aclweb.org/anthology/W17-7003 | |
| PWC | https://paperswithcode.com/paper/a-conceptual-ontology-in-the-water-domain-of |
| Repo | |
| Framework | |
WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition
| Title | WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition |
| Authors | Abbas Ghaddar, Phillippe Langlais |
| Abstract | We revisit the idea of mining Wikipedia in order to generate named-entity annotations. We propose a new methodology that we applied to English Wikipedia to build WiNER, a large, high quality, annotated corpus. We evaluate its usefulness on 6 NER tasks, comparing 4 popular state-of-the art approaches. We show that LSTM-CRF is the approach that benefits the most from our corpus. We report impressive gains with this model when using a small portion of WiNER on top of the CONLL training material. Last, we propose a simple but efficient method for exploiting the full range of WiNER, leading to further improvements. |
| Tasks | Named Entity Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1042/ |
| https://www.aclweb.org/anthology/I17-1042 | |
| PWC | https://paperswithcode.com/paper/winer-a-wikipedia-annotated-corpus-for-named |
| Repo | |
| Framework | |
Shortest-Path Graph Kernels for Document Similarity
| Title | Shortest-Path Graph Kernels for Document Similarity |
| Authors | Giannis Nikolentzos, Polykarpos Meladianos, Fran{\c{c}}ois Rousseau, Yannis Stavrakas, Michalis Vazirgiannis |
| Abstract | In this paper, we present a novel document similarity measure based on the definition of a graph kernel between pairs of documents. The proposed measure takes into account both the terms contained in the documents and the relationships between them. By representing each document as a graph-of-words, we are able to model these relationships and then determine how similar two documents are by using a modified shortest-path graph kernel. We evaluate our approach on two tasks and compare it against several baseline approaches using various performance metrics such as DET curves and macro-average F1-score. Experimental results on a range of datasets showed that our proposed approach outperforms traditional techniques and is capable of measuring more accurately the similarity between two documents. |
| Tasks | Information Retrieval, Text Categorization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1202/ |
| https://www.aclweb.org/anthology/D17-1202 | |
| PWC | https://paperswithcode.com/paper/shortest-path-graph-kernels-for-document |
| Repo | |
| Framework | |
