Paper Group NANR 234
Data Collection for Dialogue System: A Startup Perspective. Ex ante coordination and collusion in zero-sum multi-player extensive-form games. Learning Efficient Tensor Representations with Ring Structure Networks. Transfer of Frames from English FrameNet to Construct Chinese FrameNet: A Bilingual Corpus-Based Approach. Identifying Risk Factors For …
Data Collection for Dialogue System: A Startup Perspective
| Title | Data Collection for Dialogue System: A Startup Perspective |
| Authors | Yiping Kang, Yunqi Zhang, Jonathan K. Kummerfeld, Lingjia Tang, Jason Mars |
| Abstract | Industrial dialogue systems such as Apple Siri and Google Now rely on large scale diverse and robust training data to enable their sophisticated conversation capability. Crowdsourcing provides a scalable and inexpensive way of data collection but collecting high quality data efficiently requires thoughtful orchestration of the crowdsourcing jobs. Prior study of this topic have focused on tasks only in the academia settings with limited scope or only provide intrinsic dataset analysis, lacking indication on how it affects the trained model performance. In this paper, we present a study of crowdsourcing methods for a user intent classification task in our deployed dialogue system. Our task requires classification of 47 possible user intents and contains many intent pairs with subtle differences. We consider different crowdsourcing job types and job prompts and analyze quantitatively the quality of the collected data and the downstream model performance on a test set of real user queries from production logs. Our observation provides insights into designing efficient crowdsourcing jobs and provide recommendations for future dialogue system data collection process. |
| Tasks | Intent Classification, Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-3005/ |
| https://www.aclweb.org/anthology/N18-3005 | |
| PWC | https://paperswithcode.com/paper/data-collection-for-dialogue-system-a-startup |
| Repo | |
| Framework | |
Ex ante coordination and collusion in zero-sum multi-player extensive-form games
| Title | Ex ante coordination and collusion in zero-sum multi-player extensive-form games |
| Authors | Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm |
| Abstract | Recent milestones in equilibrium computation, such as the success of Libratus, show that it is possible to compute strong solutions to two-player zero-sum games in theory and practice. This is not the case for games with more than two players, which remain one of the main open challenges in computational game theory. This paper focuses on zero-sum games where a team of players faces an opponent, as is the case, for example, in Bridge, collusion in poker, and many non-recreational applications such as war, where the colluders do not have time or means of communicating during battle, collusion in bidding, where communication during the auction is illegal, and coordinated swindling in public. The possibility for the team members to communicate before game play—that is, coordinate their strategies ex ante—makes the use of behavioral strategies unsatisfactory. The reasons for this are closely related to the fact that the team can be represented as a single player with imperfect recall. We propose a new game representation, the realization form, that generalizes the sequence form but can also be applied to imperfect-recall games. Then, we use it to derive an auxiliary game that is equivalent to the original one. It provides a sound way to map the problem of finding an optimal ex-ante-correlated strategy for the team to the well-understood Nash equilibrium-finding problem in a (larger) two-player zero-sum perfect-recall game. By reasoning over the auxiliary game, we devise an anytime algorithm, fictitious team-play, that is guaranteed to converge to an optimal coordinated strategy for the team against an optimal opponent, and that is dramatically faster than the prior state-of-the-art algorithm for this problem. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8172-ex-ante-coordination-and-collusion-in-zero-sum-multi-player-extensive-form-games |
| http://papers.nips.cc/paper/8172-ex-ante-coordination-and-collusion-in-zero-sum-multi-player-extensive-form-games.pdf | |
| PWC | https://paperswithcode.com/paper/ex-ante-coordination-and-collusion-in-zero |
| Repo | |
| Framework | |
Learning Efficient Tensor Representations with Ring Structure Networks
| Title | Learning Efficient Tensor Representations with Ring Structure Networks |
| Authors | Qibin Zhao, Masashi Sugiyama, Longhao Yuan, Andrzej Cichocki |
| Abstract | \emph{Tensor train (TT) decomposition} is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. In this paper, we propose a more generalized tensor decomposition with ring structure network by employing circular multilinear products over a sequence of lower-order core tensors, which is termed as TR representation. Several learning algorithms including blockwise ALS with adaptive tensor ranks and SGD with high scalability are presented. Furthermore, the mathematical properties are investigated, which enables us to perform basic algebra operations in a computationally efficiently way by using TR representations. Experimental results on synthetic signals and real-world datasets demonstrate the effectiveness of TR model and the learning algorithms. In particular, we show that the structure information and high-order correlations within a 2D image can be captured efficiently by employing tensorization and TR representation. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HkGJUXb0- |
| https://openreview.net/pdf?id=HkGJUXb0- | |
| PWC | https://paperswithcode.com/paper/learning-efficient-tensor-representations |
| Repo | |
| Framework | |
Transfer of Frames from English FrameNet to Construct Chinese FrameNet: A Bilingual Corpus-Based Approach
| Title | Transfer of Frames from English FrameNet to Construct Chinese FrameNet: A Bilingual Corpus-Based Approach |
| Authors | Tsung-Han Yang, Hen-Hsen Huang, An-Zi Yen, Hsin-Hsi Chen |
| Abstract | |
| Tasks | Semantic Role Labeling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1139/ |
| https://www.aclweb.org/anthology/L18-1139 | |
| PWC | https://paperswithcode.com/paper/transfer-of-frames-from-english-framenet-to |
| Repo | |
| Framework | |
Identifying Risk Factors For Heart Disease in Electronic Medical Records: A Deep Learning Approach
| Title | Identifying Risk Factors For Heart Disease in Electronic Medical Records: A Deep Learning Approach |
| Authors | Thanat Chokwijitkul, Anthony Nguyen, Hamed Hassanzadeh, Siegfried Perez |
| Abstract | Automatic identification of heart disease risk factors in clinical narratives can expedite disease progression modelling and support clinical decisions. Existing practical solutions for cardiovascular risk detection are mostly hybrid systems entailing the integration of knowledge-driven and data-driven methods, relying on dictionaries, rules and machine learning methods that require a substantial amount of human effort. This paper proposes a comparative analysis on the applicability of deep learning, a re-emerged data-driven technique, in the context of clinical text classification. Various deep learning architectures were devised and evaluated for extracting heart disease risk factors from clinical documents. The data provided for the 2014 i2b2/UTHealth shared task focusing on identifying risk factors for heart disease was used for system development and evaluation. Results have shown that a relatively simple deep learning model can achieve a high micro-averaged F-measure of 0.9081, which is comparable to the best systems from the shared task. This is highly encouraging given the simplicity of the deep learning approach compared to the heavily feature-engineered hybrid approaches that were required to achieve state-of-the-art performances. |
| Tasks | Clinical Concept Extraction, Feature Engineering, Text Classification |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2303/ |
| https://www.aclweb.org/anthology/W18-2303 | |
| PWC | https://paperswithcode.com/paper/identifying-risk-factors-for-heart-disease-in |
| Repo | |
| Framework | |
Improving Domain Independent Question Parsing with Synthetic Treebanks
| Title | Improving Domain Independent Question Parsing with Synthetic Treebanks |
| Authors | Halim-Antoine Boukaram, Nizar Habash, Micheline Ziadee, Majd Sakr |
| Abstract | Automatic syntactic parsing for question constructions is a challenging task due to the paucity of training examples in most treebanks. The near absence of question constructions is due to the dominance of the news domain in treebanking efforts. In this paper, we compare two synthetic low-cost question treebank creation methods with a conventional manual high-cost annotation method in the context of three domains (news questions, political talk shows, and chatbots) for Modern Standard Arabic, a language with relatively low resources and rich morphology. Our results show that synthetic methods can be effective at significantly reducing parsing errors for a target domain without having to invest large resources on manual annotation; and the combination of manual and synthetic methods is our best domain-independent performer. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4924/ |
| https://www.aclweb.org/anthology/W18-4924 | |
| PWC | https://paperswithcode.com/paper/improving-domain-independent-question-parsing |
| Repo | |
| Framework | |
Results of the WMT18 Metrics Shared Task: Both characters and embeddings achieve good performance
| Title | Results of the WMT18 Metrics Shared Task: Both characters and embeddings achieve good performance |
| Authors | Qingsong Ma, Ond{\v{r}}ej Bojar, Yvette Graham |
| Abstract | This paper presents the results of the WMT18 Metrics Shared Task. We asked participants of this task to score the outputs of the MT systems involved in the WMT18 News Translation Task with automatic metrics. We collected scores of 10 metrics and 8 research groups. In addition to that, we computed scores of 8 standard metrics (BLEU, SentBLEU, chrF, NIST, WER, PER, TER and CDER) as baselines. The collected scores were evaluated in terms of system-level correlation (how well each metric{'}s scores correlate with WMT18 official manual ranking of systems) and in terms of segment-level correlation (how often a metric agrees with humans in judging the quality of a particular sentence relative to alternate outputs). This year, we employ a single kind of manual evaluation: direct assessment (DA). |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6450/ |
| https://www.aclweb.org/anthology/W18-6450 | |
| PWC | https://paperswithcode.com/paper/results-of-the-wmt18-metrics-shared-task-both |
| Repo | |
| Framework | |
Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates
| Title | Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates |
| Authors | Leslie N. Smith, Nicholay Topin |
| Abstract | In this paper, we show a phenomenon, which we named ``super-convergence’', where residual networks can be trained using an order of magnitude fewer iterations than is used with standard training methods. The existence of super-convergence is relevant to understanding why deep networks generalize well. One of the key elements of super-convergence is training with cyclical learning rates and a large maximum learning rate. Furthermore, we present evidence that training with large learning rates improves performance by regularizing the network. In addition, we show that super-convergence provides a greater boost in performance relative to standard training when the amount of labeled training data is limited. We also derive a simplification of the Hessian Free optimization method to compute an estimate of the optimal learning rate. The architectures to replicate this work will be made available upon publication. | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1A5ztj3b |
| https://openreview.net/pdf?id=H1A5ztj3b | |
| PWC | https://paperswithcode.com/paper/super-convergence-very-fast-training-of |
| Repo | |
| Framework | |
MOCCA: Measure of Confidence for Corpus Analysis - Automatic Reliability Check of Transcript and Automatic Segmentation
| Title | MOCCA: Measure of Confidence for Corpus Analysis - Automatic Reliability Check of Transcript and Automatic Segmentation |
| Authors | Thomas Kisler, Florian Schiel |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1281/ |
| https://www.aclweb.org/anthology/L18-1281 | |
| PWC | https://paperswithcode.com/paper/mocca-measure-of-confidence-for-corpus |
| Repo | |
| Framework | |
Learning Facial Action Units From Web Images With Scalable Weakly Supervised Clustering
| Title | Learning Facial Action Units From Web Images With Scalable Weakly Supervised Clustering |
| Authors | Kaili Zhao, Wen-Sheng Chu, Aleix M. Martinez |
| Abstract | We present a scalable weakly supervised clustering approach to learn facial action units (AUs) from large, freely available web images. Unlike most existing methods (e.g., CNNs) that rely on fully annotated data, our method exploits web images with inaccurate annotations. Specifically, we derive a weakly-supervised spectral algorithm that learns an embedding space to couple image appearance and semantics. The algorithm has efficient gradient update, and scales up to large quantities of images with a stochastic extension. With the learned embedding space, we adopt rank-order clustering to identify groups of visually and semantically similar images, and re-annotate these groups for training AU classifiers. Evaluation on the 1 millon EmotioNet dataset demonstrates the effectiveness of our approach: (1) our learned annotations reach on average 91.3% agreement with human annotations on 7 common AUs, (2) classifiers trained with re-annotated images perform comparably to, sometimes even better than, its supervised CNN-based counterpart, and (3) our method offers intuitive outlier/noise pruning instead of forcing one annotation to every image. Code is available. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhao_Learning_Facial_Action_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhao_Learning_Facial_Action_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-facial-action-units-from-web-images |
| Repo | |
| Framework | |
A Distributional and Orthographic Aggregation Model for English Derivational Morphology
| Title | A Distributional and Orthographic Aggregation Model for English Derivational Morphology |
| Authors | Daniel Deutsch, John Hewitt, Dan Roth |
| Abstract | Modeling derivational morphology to generate words with particular semantics is useful in many text generation tasks, such as machine translation or abstractive question answering. In this work, we tackle the task of derived word generation. That is, we attempt to generate the word {}runner{''} for {}someone who runs.{''} We identify two key problems in generating derived words from root words and transformations. We contribute a novel aggregation model of derived word generation that learns derivational transformations both as orthographic functions using sequence-to-sequence models and as functions in distributional word embedding space. The model then learns to choose between the hypothesis of each system. We also present two ways of incorporating corpus information into derived word generation. |
| Tasks | Machine Translation, Question Answering, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1180/ |
| https://www.aclweb.org/anthology/P18-1180 | |
| PWC | https://paperswithcode.com/paper/a-distributional-and-orthographic-aggregation |
| Repo | |
| Framework | |
Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention
| Title | Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention |
| Authors | Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, Jiajun Chen |
| Abstract | Natural language sentences, being hierarchical, can be represented at different levels of granularity, like words, subwords, or characters. But most neural machine translation systems require the sentence to be represented as a sequence at a single level of granularity. It can be difficult to determine which granularity is better for a particular translation task. In this paper, we improve the model by incorporating multiple levels of granularity. Specifically, we propose (1) an encoder with character attention which augments the (sub)word-level representation with character-level information; (2) a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively. Experiments on three translation tasks demonstrate that our proposed models outperform the standard word-based model, the subword-based model, and a strong character-based model. |
| Tasks | Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1116/ |
| https://www.aclweb.org/anthology/N18-1116 | |
| PWC | https://paperswithcode.com/paper/combining-character-and-word-information-in |
| Repo | |
| Framework | |
Improving Low Resource Machine Translation using Morphological Glosses (Non-archival Extended Abstract)
| Title | Improving Low Resource Machine Translation using Morphological Glosses (Non-archival Extended Abstract) |
| Authors | Steven Shearing, Christo Kirov, Huda Khayrallah, David Yarowsky |
| Abstract | |
| Tasks | Data Augmentation, Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1813/ |
| https://www.aclweb.org/anthology/W18-1813 | |
| PWC | https://paperswithcode.com/paper/improving-low-resource-machine-translation |
| Repo | |
| Framework | |
Fine-Grained Temporal Orientation and its Relationship with Psycho-Demographic Correlates
| Title | Fine-Grained Temporal Orientation and its Relationship with Psycho-Demographic Correlates |
| Authors | Sabyasachi Kamila, Mohammed Hasanuzzaman, Asif Ekbal, Pushpak Bhattacharyya, Andy Way |
| Abstract | Temporal orientation refers to an individual{'}s tendency to connect to the psychological concepts of past, present or future, and it affects personality, motivation, emotion, decision making and stress coping processes. The study of the social media users{'} psycho-demographic attributes from the perspective of human temporal orientation can be of utmost interest and importance to the business and administrative decision makers as it can provide an extra precious information for them to make informed decisions. In this paper, we propose a very first study to demonstrate the association between the sentiment view of the temporal orientation of the users and their different psycho-demographic attributes by analyzing their tweets. We first create a temporal orientation classifier in a minimally supervised way which classifies each tweet of the users in one of the three temporal categories, namely past, present, and future. A deep Bi-directional Long Short Term Memory (BLSTM) is used for the tweet classification task. Our tweet classifier achieves an accuracy of 78.27{%} when tested on a manually created test set. We then determine the users{'} overall temporal orientation based on their tweets on the social media. The sentiment is added to the tweets at the fine-grained level where each temporal tweet is given a sentiment with either of the positive, negative or neutral. Our experiment reveals that depending upon the sentiment view of temporal orientation, a user{'}s attributes vary. We finally measure the correlation between the users{'} sentiment view of temporal orientation and their different psycho-demographic factors using regression. |
| Tasks | Decision Making |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1061/ |
| https://www.aclweb.org/anthology/N18-1061 | |
| PWC | https://paperswithcode.com/paper/fine-grained-temporal-orientation-and-its |
| Repo | |
| Framework | |
The Effects of Unimodal Representation Choices on Multimodal Learning
| Title | The Effects of Unimodal Representation Choices on Multimodal Learning |
| Authors | Fern Ito, o Tadao, Helena de Medeiros Caseli, J Moreira, er |
| Abstract | |
| Tasks | Image Classification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1334/ |
| https://www.aclweb.org/anthology/L18-1334 | |
| PWC | https://paperswithcode.com/paper/the-effects-of-unimodal-representation |
| Repo | |
| Framework | |
