Paper Group NANR 35
Comparison of Paragram and GloVe Results for Similarity Benchmarks. A Unified Neural Network Model for Geolocating Twitter Users. Browsing the Terminological Structure of a Specialized Domain: A Method Based on Lexical Functions and their Classification. Taking Apart Autoencoders: How do They Encode Geometric Shapes ?. Classification of Closely Rel …
Comparison of Paragram and GloVe Results for Similarity Benchmarks
| Title | Comparison of Paragram and GloVe Results for Similarity Benchmarks |
| Authors | Jakub Dutkiewicz, Czesław Jędrzejek |
| Abstract | Distributional Semantics Models(DSM) derive word space from linguistic items in context. Meaning is obtained by defining a distance measure between vectors corresponding to lexical entities. Such vectors present several problems. This work concentrates on quality of word embeddings, improvement of word embedding vectors, applicability of a novel similarity metric used ‘on top’ of the word embeddings. In this paper we provide comparison between two methods for post process improvements to the baseline DSM vectors. The counter-fitting method which enforces antonymy and synonymy constraints into the Paragram vector space representations recently showed improvement in the vectors’ capability for judging semantic similarity. The second method is our novel RESM method applied to GloVe baseline vectors. By applying the hubness reduction method, implementing relational knowledge into the model by retrofitting synonyms and providing a new ranking similarity definition RESM that gives maximum weight to the top vector component values we equal the results for the ESL and TOEFL sets in comparison with our calculations using the Paragram and Paragram + Counter-fitting methods. For SIMLEX-999 gold standard since we cannot use the RESM the results using GloVe and PPDB are significantly worse compared to Paragram. Apparently, counter-fitting corrects hubness. The Paragram or our cosine retrofitting method are state-of-the-art results for the SIMLEX-999 gold standard. They are 0.2 better for SIMLEX-999 than word2vec with sense de-conflation (that was announced to be state-of the-art method for less reliable gold standards). Apparently relational knowledge and counter-fitting is more important for judging semantic similarity than sense determination for words. It is to be mentioned, though that Paragram hyperparameters are fitted to SIMLEX-999 results. The lesson is that many corrections to word embeddings are necessary and methods with more parameters and hyperparameters perform better. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyHmGyZCZ |
| https://openreview.net/pdf?id=HyHmGyZCZ | |
| PWC | https://paperswithcode.com/paper/comparison-of-paragram-and-glove-results-for |
| Repo | |
| Framework | |
A Unified Neural Network Model for Geolocating Twitter Users
| Title | A Unified Neural Network Model for Geolocating Twitter Users |
| Authors | Mohammad Ebrahimi, Elaheh ShafieiBavani, Raymond Wong, Fang Chen |
| Abstract | Locations of social media users are important to many applications such as rapid disaster response, targeted advertisement, and news recommendation. However, many users do not share their exact geographical coordinates due to reasons such as privacy concerns. The lack of explicit location information has motivated a growing body of research in recent years looking at different automatic ways of determining the user{'}s primary location. In this paper, we propose a unified user geolocation method which relies on a fusion of neural networks. Our joint model incorporates different types of available information including tweet text, user network, and metadata to predict users{'} locations. Moreover, we utilize a bidirectional LSTM network augmented with an attention mechanism to identify the most location indicative words in textual content of tweets. The experiments demonstrate that our approach achieves state-of-the-art performance over two Twitter benchmark geolocation datasets. We also conduct an ablation study to evaluate the contribution of each type of information in user geolocation performance. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1005/ |
| https://www.aclweb.org/anthology/K18-1005 | |
| PWC | https://paperswithcode.com/paper/a-unified-neural-network-model-for |
| Repo | |
| Framework | |
Browsing the Terminological Structure of a Specialized Domain: A Method Based on Lexical Functions and their Classification
| Title | Browsing the Terminological Structure of a Specialized Domain: A Method Based on Lexical Functions and their Classification |
| Authors | Marie-Claude L{'}Homme, Beno{^\i}t Robichaud, Nathalie Pr{'e}vil |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1487/ |
| https://www.aclweb.org/anthology/L18-1487 | |
| PWC | https://paperswithcode.com/paper/browsing-the-terminological-structure-of-a |
| Repo | |
| Framework | |
Taking Apart Autoencoders: How do They Encode Geometric Shapes ?
| Title | Taking Apart Autoencoders: How do They Encode Geometric Shapes ? |
| Authors | Alasdair Newson, Andres Almansa, Yann Gousseau, Said Ladjal |
| Abstract | We study the precise mechanisms which allow autoencoders to encode and decode a simple geometric shape, the disk. In this carefully controlled setting, we are able to describe the specific form of the optimal solution to the minimisation problem of the training step. We show that the autoencoder indeed approximates this solution during training. Secondly, we identify a clear failure in the generalisation capacity of the autoencoder, namely its inability to interpolate data. Finally, we explore several regularisation schemes to resolve the generalisation problem. Given the great attention that has been recently given to the generative capacity of neural networks, we believe that studying in depth simple geometric cases sheds some light on the generation process and can provide a minimal requirement experimental setup for more complex architectures. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r111KtCp- |
| https://openreview.net/pdf?id=r111KtCp- | |
| PWC | https://paperswithcode.com/paper/taking-apart-autoencoders-how-do-they-encode |
| Repo | |
| Framework | |
Classification of Closely Related Sub-dialects of Arabic Using Support-Vector Machines
| Title | Classification of Closely Related Sub-dialects of Arabic Using Support-Vector Machines |
| Authors | Samantha Wray |
| Abstract | |
| Tasks | Language Identification, Speech Recognition, Text Classification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1580/ |
| https://www.aclweb.org/anthology/L18-1580 | |
| PWC | https://paperswithcode.com/paper/classification-of-closely-related-sub |
| Repo | |
| Framework | |
Chinese Grammatical Error Diagnosis using Statistical and Prior Knowledge driven Features with Probabilistic Ensemble Enhancement
| Title | Chinese Grammatical Error Diagnosis using Statistical and Prior Knowledge driven Features with Probabilistic Ensemble Enhancement |
| Authors | Ruiji Fu, Zhengqi Pei, Jiefu Gong, Wei Song, Dechuan Teng, Wanxiang Che, Shijin Wang, Guoping Hu, Ting Liu |
| Abstract | This paper describes our system at NLPTEA-2018 Task {#}1: Chinese Grammatical Error Diagnosis. Grammatical Error Diagnosis is one of the most challenging NLP tasks, which is to locate grammar errors and tell error types. Our system is built on the model of bidirectional Long Short-Term Memory with a conditional random field layer (BiLSTM-CRF) but integrates with several new features. First, richer features are considered in the BiLSTM-CRF model; second, a probabilistic ensemble approach is adopted; third, Template Matcher are used during a post-processing to bring in human knowledge. In official evaluation, our system obtains the highest F1 scores at identifying error types and locating error positions, the second highest F1 score at sentence level error detection. We also recommend error corrections for specific error types and achieve the best F1 performance among all participants. |
| Tasks | Information Retrieval |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3707/ |
| https://www.aclweb.org/anthology/W18-3707 | |
| PWC | https://paperswithcode.com/paper/chinese-grammatical-error-diagnosis-using |
| Repo | |
| Framework | |
Sound Signal Processing with Seq2Tree Network
| Title | Sound Signal Processing with Seq2Tree Network |
| Authors | Weicheng Ma, Kai Cao, Zhaoheng Ni, Peter Chin, Xiang Li |
| Abstract | |
| Tasks | Speech Separation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1494/ |
| https://www.aclweb.org/anthology/L18-1494 | |
| PWC | https://paperswithcode.com/paper/sound-signal-processing-with-seq2tree-network |
| Repo | |
| Framework | |
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data
| Title | GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data |
| Authors | Bayu Distiawan Trisedya, Jianzhong Qi, Rui Zhang, Wei Wang |
| Abstract | A knowledge base is a large repository of facts that are mainly represented as RDF triples, each of which consists of a subject, a predicate (relationship), and an object. The RDF triple representation offers a simple interface for applications to access the facts. However, this representation is not in a natural language form, which is difficult for humans to understand. We address this problem by proposing a system to translate a set of RDF triples into natural sentences based on an encoder-decoder framework. To preserve as much information from RDF triples as possible, we propose a novel graph-based triple encoder. The proposed encoder encodes not only the elements of the triples but also the relationships both within a triple and between the triples. Experimental results show that the proposed encoder achieves a consistent improvement over the baseline models by up to 17.6{%}, 6.0{%}, and 16.4{%} in three common metrics BLEU, METEOR, and TER, respectively. |
| Tasks | Question Answering, Recommendation Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1151/ |
| https://www.aclweb.org/anthology/P18-1151 | |
| PWC | https://paperswithcode.com/paper/gtr-lstm-a-triple-encoder-for-sentence |
| Repo | |
| Framework | |
A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation
| Title | A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation |
| Authors | Riccardo Roveri, Lukas Rahmann, Cengiz Oztireli, Markus Gross |
| Abstract | We propose a novel neural network architecture for point cloud classification. Our key idea is to automatically transform the 3D unordered input data into a set of useful 2D depth images, and classify them by exploiting well performing image classification CNNs. We present new differentiable module designs to generate depth images from a point cloud. These modules can be combined with any network architecture for processing point clouds. We utilize them in combination with state-of-the-art classification networks, and get results competitive with the state of the art in point cloud classification. Furthermore, our architecture automatically produces informative images representing the input point cloud, which could be used for further applications such as point cloud visualization. |
| Tasks | Image Classification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Roveri_A_Network_Architecture_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Roveri_A_Network_Architecture_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-network-architecture-for-point-cloud |
| Repo | |
| Framework | |
Speech Rate Calculations with Short Utterances: A Study from a Speech-to-Speech, Machine Translation Mediated Map Task
| Title | Speech Rate Calculations with Short Utterances: A Study from a Speech-to-Speech, Machine Translation Mediated Map Task |
| Authors | Akira Hayakawa, Carl Vogel, Saturnino Luz, Nick Campbell |
| Abstract | |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1502/ |
| https://www.aclweb.org/anthology/L18-1502 | |
| PWC | https://paperswithcode.com/paper/speech-rate-calculations-with-short |
| Repo | |
| Framework | |
A Workbench for Rapid Generation of Cross-Lingual Summaries
| Title | A Workbench for Rapid Generation of Cross-Lingual Summaries |
| Authors | Nisarg Jhaveri, Manish Gupta, Vasudeva Varma |
| Abstract | |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1507/ |
| https://www.aclweb.org/anthology/L18-1507 | |
| PWC | https://paperswithcode.com/paper/a-workbench-for-rapid-generation-of-cross |
| Repo | |
| Framework | |
Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning
| Title | Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning |
| Authors | Xing Yan, Weizhong Zhang, Lin Ma, Wei Liu, Qi Wu |
| Abstract | We propose a parsimonious quantile regression framework to learn the dynamic tail behaviors of financial asset returns. Our model captures well both the time-varying characteristic and the asymmetrical heavy-tail property of financial time series. It combines the merits of a popular sequential neural network model, i.e., LSTM, with a novel parametric quantile function that we construct to represent the conditional distribution of asset returns. Our model also captures individually the serial dependences of higher moments, rather than just the volatility. Across a wide range of asset classes, the out-of-sample forecasts of conditional quantiles or VaR of our model outperform the GARCH family. Further, the proposed approach does not suffer from the issue of quantile crossing, nor does it expose to the ill-posedness comparing to the parametric probability density function approach. |
| Tasks | Time Series |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7430-parsimonious-quantile-regression-of-financial-asset-tail-dynamics-via-sequential-learning |
| http://papers.nips.cc/paper/7430-parsimonious-quantile-regression-of-financial-asset-tail-dynamics-via-sequential-learning.pdf | |
| PWC | https://paperswithcode.com/paper/parsimonious-quantile-regression-of-financial |
| Repo | |
| Framework | |
Grounding Gradable Adjectives through Crowdsourcing
| Title | Grounding Gradable Adjectives through Crowdsourcing |
| Authors | Rebecca Sharp, Mithun Paul, Ajay Nagesh, Dane Bell, Mihai Surdeanu |
| Abstract | |
| Tasks | Reading Comprehension |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1529/ |
| https://www.aclweb.org/anthology/L18-1529 | |
| PWC | https://paperswithcode.com/paper/grounding-gradable-adjectives-through |
| Repo | |
| Framework | |
New directions in ELRA activities
| Title | New directions in ELRA activities |
| Authors | Val{'e}rie Mapelli, Victoria Arranz, H{'e}l{`e}ne Mazo, Pawel Kamocki, Vladimir Popescu |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1517/ |
| https://www.aclweb.org/anthology/L18-1517 | |
| PWC | https://paperswithcode.com/paper/new-directions-in-elra-activities |
| Repo | |
| Framework | |
EMR Coding with Semi-Parametric Multi-Head Matching Networks
| Title | EMR Coding with Semi-Parametric Multi-Head Matching Networks |
| Authors | Anthony Rios, Ramakanth Kavuluru |
| Abstract | Coding EMRs with diagnosis and procedure codes is an indispensable task for billing, secondary data analyses, and monitoring health trends. Both speed and accuracy of coding are critical. While coding errors could lead to more patient-side financial burden and misinterpretation of a patient{'}s well-being, timely coding is also needed to avoid backlogs and additional costs for the healthcare facility. In this paper, we present a new neural network architecture that combines ideas from few-shot learning matching networks, multi-label loss functions, and convolutional neural networks for text classification to significantly outperform other state-of-the-art models. Our evaluations are conducted using a well known de-identified EMR dataset (MIMIC) with a variety of multi-label performance measures. |
| Tasks | Few-Shot Learning, Multi-Label Classification, Multi-Label Text Classification, Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1189/ |
| https://www.aclweb.org/anthology/N18-1189 | |
| PWC | https://paperswithcode.com/paper/emr-coding-with-semi-parametric-multi-head |
| Repo | |
| Framework | |
