Paper Group NANR 148
The ADELE Corpus of Dyadic Social Text Conversations:Dialog Act Annotation with ISO 24617-2. Authorship Identification for Literary Book Recommendations. Towards faithfully visualizing global linguistic diversity. CRVI: Convex Relaxation for Variational Inference. Cooperating Tools for MWE Lexicon Management and Corpus Annotation. Compositional Mor …
The ADELE Corpus of Dyadic Social Text Conversations:Dialog Act Annotation with ISO 24617-2
| Title | The ADELE Corpus of Dyadic Social Text Conversations:Dialog Act Annotation with ISO 24617-2 |
| Authors | Emer Gilmartin, Christian Saam, Brendan Spillane, Maria O{'}Reilly, Ketong Su, Arturo Calvo, Loredana Cerrato, Killian Levacher, Nick Campbell, Vincent Wade |
| Abstract | |
| Tasks | Chatbot |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1633/ |
| https://www.aclweb.org/anthology/L18-1633 | |
| PWC | https://paperswithcode.com/paper/the-adele-corpus-of-dyadic-social-text |
| Repo | |
| Framework | |
Authorship Identification for Literary Book Recommendations
| Title | Authorship Identification for Literary Book Recommendations |
| Authors | Haifa Alharthi, Diana Inkpen, Stan Szpakowicz |
| Abstract | Book recommender systems can help promote the practice of reading for pleasure, which has been declining in recent years. One factor that influences reading preferences is writing style. We propose a system that recommends books after learning their authors{'} style. To our knowledge, this is the first work that applies the information learned by an author-identification model to book recommendations. We evaluated the system according to a top-k recommendation scenario. Our system gives better accuracy when compared with many state-of-the-art methods. We also conducted a qualitative analysis by checking if similar books/authors were annotated similarly by experts. |
| Tasks | Recommendation Systems |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1033/ |
| https://www.aclweb.org/anthology/C18-1033 | |
| PWC | https://paperswithcode.com/paper/authorship-identification-for-literary-book |
| Repo | |
| Framework | |
Towards faithfully visualizing global linguistic diversity
| Title | Towards faithfully visualizing global linguistic diversity |
| Authors | Garl McNew, , Curdin Derungs, Steven Moran |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1129/ |
| https://www.aclweb.org/anthology/L18-1129 | |
| PWC | https://paperswithcode.com/paper/towards-faithfully-visualizing-global |
| Repo | |
| Framework | |
CRVI: Convex Relaxation for Variational Inference
| Title | CRVI: Convex Relaxation for Variational Inference |
| Authors | Ghazal Fazelnia, John Paisley |
| Abstract | We present a new technique for solving non-convex variational inference optimization problems. Variational inference is a widely used method for posterior approximation in which the inference problem is transformed into an optimization problem. For most models, this optimization is highly non-convex and so hard to solve. In this paper, we introduce a new approach to solving the variational inference optimization based on convex relaxation and semidefinite programming. Our theoretical results guarantee very tight relaxation bounds that get nearer to the global optimal solution than traditional coordinate ascent. We evaluate the performance of our approach on regression and sparse coding. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2175 |
| http://proceedings.mlr.press/v80/fazelnia18a/fazelnia18a.pdf | |
| PWC | https://paperswithcode.com/paper/crvi-convex-relaxation-for-variational |
| Repo | |
| Framework | |
Cooperating Tools for MWE Lexicon Management and Corpus Annotation
| Title | Cooperating Tools for MWE Lexicon Management and Corpus Annotation |
| Authors | Yuji Matsumoto, Akihiko Kato, Hiroyuki Shindo, Toshio Morita |
| Abstract | We present tools for lexicon and corpus management that offer cooperating functionality in corpus annotation. The former, named Cradle, stores a set of words and expressions where multi-word expressions are defined with their own part-of-speech information and internal syntactic structures. The latter, named ChaKi, manages text corpora with part-of-speech (POS) and syntactic dependency structure annotations. Those two tools cooperate so that the words and multi-word expressions stored in Cradle are directly referred to by ChaKi in conducting corpus annotation, and the words and expressions annotated in ChaKi can be output as a list of lexical entities that are to be stored in Cradle. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4922/ |
| https://www.aclweb.org/anthology/W18-4922 | |
| PWC | https://paperswithcode.com/paper/cooperating-tools-for-mwe-lexicon-management |
| Repo | |
| Framework | |
Compositional Morpheme Embeddings with Affixes as Functions and Stems as Arguments
| Title | Compositional Morpheme Embeddings with Affixes as Functions and Stems as Arguments |
| Authors | Daniel Edmiston, Karl Stratos |
| Abstract | This work introduces a novel, linguistically motivated architecture for composing morphemes to derive word embeddings. The principal novelty in the work is to treat stems as vectors and affixes as functions over vectors. In this way, our model{'}s architecture more closely resembles the compositionality of morphemes in natural language. Such a model stands in opposition to models which treat morphemes uniformly, making no distinction between stem and affix. We run this new architecture on a dependency parsing task in Korean{—}a language rich in derivational morphology{—}and compare it against a lexical baseline,along with other sub-word architectures. StAffNet, the name of our architecture, shows competitive performance with the state-of-the-art on this task. |
| Tasks | Dependency Parsing, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2901/ |
| https://www.aclweb.org/anthology/W18-2901 | |
| PWC | https://paperswithcode.com/paper/compositional-morpheme-embeddings-with |
| Repo | |
| Framework | |
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator
| Title | SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator |
| Authors | Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang |
| Abstract | In this paper, we propose a new technique named \textit{Stochastic Path-Integrated Differential EstimatoR} (SPIDER), which can be used to track many deterministic quantities of interests with significantly reduced computational cost. Combining SPIDER with the method of normalized gradient descent, we propose SPIDER-SFO that solve non-convex stochastic optimization problems using stochastic gradients only. We provide a few error-bound results on its convergence rates. Specially, we prove that the SPIDER-SFO algorithm achieves a gradient computation cost of $\mathcal{O}\left( \min( n^{1/2} \epsilon^{-2}, \epsilon^{-3} ) \right)$ to find an $\epsilon$-approximate first-order stationary point. In addition, we prove that SPIDER-SFO nearly matches the algorithmic lower bound for finding stationary point under the gradient Lipschitz assumption in the finite-sum setting. Our SPIDER technique can be further applied to find an $(\epsilon, \mathcal{O}(\ep^{0.5}))$-approximate second-order stationary point at a gradient computation cost of $\tilde{\mathcal{O}}\left( \min( n^{1/2} \epsilon^{-2}+\epsilon^{-2.5}, \epsilon^{-3} ) \right)$. |
| Tasks | Stochastic Optimization |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7349-spider-near-optimal-non-convex-optimization-via-stochastic-path-integrated-differential-estimator |
| http://papers.nips.cc/paper/7349-spider-near-optimal-non-convex-optimization-via-stochastic-path-integrated-differential-estimator.pdf | |
| PWC | https://paperswithcode.com/paper/spider-near-optimal-non-convex-optimization |
| Repo | |
| Framework | |
Building an English Vocabulary Knowledge Dataset of Japanese English-as-a-Second-Language Learners Using Crowdsourcing
| Title | Building an English Vocabulary Knowledge Dataset of Japanese English-as-a-Second-Language Learners Using Crowdsourcing |
| Authors | Yo Ehara |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1076/ |
| https://www.aclweb.org/anthology/L18-1076 | |
| PWC | https://paperswithcode.com/paper/building-an-english-vocabulary-knowledge |
| Repo | |
| Framework | |
A Teacher-Student Framework for Maintainable Dialog Manager
| Title | A Teacher-Student Framework for Maintainable Dialog Manager |
| Authors | Weikang Wang, Jiajun Zhang, Han Zhang, Mei-Yuh Hwang, Chengqing Zong, Zhifei Li |
| Abstract | Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems. However, extending RL-based systems to handle new intents and slots requires a system redesign. The high maintenance cost makes it difficult to apply RL methods to practical systems on a large scale. To address this issue, we propose a practical teacher-student framework to extend RL-based dialog systems without retraining from scratch. Specifically, the {}student{''} is an extended dialog manager based on a new ontology, and the {}teacher{''} is existing resources used for guiding the learning process of the {}student{''}. By specifying constraints held in the new dialog manager, we transfer knowledge of the {}teacher{''} to the {``}student{''} without additional resources. Experiments show that the performance of the extended system is comparable to the system trained from scratch. More importantly, the proposed framework makes no assumption about the unsupported intents and slots, which makes it possible to improve RL-based systems incrementally. | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1415/ |
| https://www.aclweb.org/anthology/D18-1415 | |
| PWC | https://paperswithcode.com/paper/a-teacher-student-framework-for-maintainable |
| Repo | |
| Framework | |
IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018
| Title | IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018 |
| Authors | Divyanshu Gupta, Gourav Dhakad, Jayprakash Gupta, Anil Kumar Singh |
| Abstract | Text language Identification is a Natural Language Processing task of identifying and recognizing a given language out of many different languages from a piece of text. This paper describes our submission to the ILI 2018 shared-task, which includes the identification of 5 closely related Indo-Aryan languages. We developed a word-level LSTM(Long Short-term Memory) model, a specific type of Recurrent Neural Network model, for this task. Given a sentence, our model embeds each word of the sentence and convert into its trainable word embedding, feeds them into our LSTM network and finally predict the language. We obtained an F1 macro score of 0.836, ranking 5th in the task. |
| Tasks | Language Identification, Machine Translation, Named Entity Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3921/ |
| https://www.aclweb.org/anthology/W18-3921 | |
| PWC | https://paperswithcode.com/paper/iit-bhu-system-for-indo-aryan-language |
| Repo | |
| Framework | |
Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States
| Title | Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States |
| Authors | Guosheng Hu, Li Liu, Yang Yuan, Zehao Yu, Yang Hua, Zhihong Zhang, Fumin Shen, Ling Shao, Timothy Hospedales, Neil Robertson, Yongxin Yang |
| Abstract | Facial expression recognition is a topical task. However, very little research investigates subtle expression recognition, which is important for mental activity analysis, deception detection, etc. We address subtle expression recognition through convolutional neural networks (CNNs) by developing multi-task learning (MTL) to effectively leverage a side task: facial landmark detection. Existing MTL methods follow a design pattern of shared bottom CNN layers and task-specific top layers. However, the sharing architecture is usually heuristically chosen, as it is difficult to decide which layers should be shared. Our approach is composed of (1) a novel MTL framework that automatically learns which layers to share through optimisation under tensor trace norm regularisation and (2) an invariant representation learning approach that allows the CNN to leverage tasks defined on disjoint datasets without suffering from dataset distribution shift. To advance subtle expression recognition, we contribute a Large-scale Subtle Emotions and Mental States in the Wild database (LSEMSW). LSEMSW includes a variety of cognitive states as well as basic emotions. It contains 176K images, manually annotated with 13 emotions, and thus provides the first subtle expression dataset large enough for training deep CNNs. Evaluations on LSEMSW and 300-W (landmark) databases show the effectiveness of the proposed methods. In addition, we investigate transferring knowledge learned from LSEMSW database to traditional (non-subtle) expression recognition. We achieve very competitive performance on Oulu-Casia NIR&Vis and CK+ databases via transfer learning. |
| Tasks | Deception Detection, Facial Expression Recognition, Facial Landmark Detection, Multi-Task Learning, Representation Learning, Transfer Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Guosheng_Hu_Deep_Multi-Task_Learning_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Guosheng_Hu_Deep_Multi-Task_Learning_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-task-learning-to-recognise-subtle |
| Repo | |
| Framework | |
Deep Cross-Modal Projection Learning for Image-Text Matching
| Title | Deep Cross-Modal Projection Learning for Image-Text Matching |
| Authors | Ying Zhang, Huchuan Lu |
| Abstract | The key point of image-text matching is how to accurately measure the similarity between visual and textual inputs. Despite the great progress of associating the deep cross-modal embeddings with the bi-directional ranking loss, developing the strategies for mining useful triplets and selecting appropriate margins remains a challenge in real applications. In this paper, we propose a cross-modal projection matching (CMPM) loss and a cross-modal projection classification (CMPC) loss for learning discriminative image-text embeddings. The CMPM loss minimizes the KL divergence between the projection compatibility distributions and the normalized matching distributions defined with all the positive and negative samples in a mini-batch. The CMPC loss attempts to categorize the vector projection of representations from one modality onto another with the improved norm-softmax loss, for further enhancing the feature compactness of each class. Extensive analysis and experiments on multiple datasets demonstrate the superiority of the proposed approach. |
| Tasks | Text Matching |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ying_Zhang_Deep_Cross-Modal_Projection_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ying_Zhang_Deep_Cross-Modal_Projection_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-cross-modal-projection-learning-for |
| Repo | |
| Framework | |
Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach
| Title | Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach |
| Authors | Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee |
| Abstract | Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms. Typically, such information includes an estimate of the optimal value function and is often provided by a human expert or other sources of domain knowledge. However, this information is often biased or inaccurate and can mislead many reinforcement learning algorithms. In this paper, we apply Bayesian Model Combination with multiple experts in a way that learns to trust a good combination of experts as training progresses. This approach is both computationally efficient and general, and is shown numerically to improve convergence across discrete and continuous domains and different reinforcement learning algorithms. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8162-reinforcement-learning-with-multiple-experts-a-bayesian-model-combination-approach |
| http://papers.nips.cc/paper/8162-reinforcement-learning-with-multiple-experts-a-bayesian-model-combination-approach.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-with-multiple-experts |
| Repo | |
| Framework | |
MYCanCor: A Video Corpus of spoken Malaysian Cantonese
| Title | MYCanCor: A Video Corpus of spoken Malaysian Cantonese |
| Authors | Andreas Liesenfeld |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1122/ |
| https://www.aclweb.org/anthology/L18-1122 | |
| PWC | https://paperswithcode.com/paper/mycancor-a-video-corpus-of-spoken-malaysian |
| Repo | |
| Framework | |
Bridging Languages through Images with Deep Partial Canonical Correlation Analysis
| Title | Bridging Languages through Images with Deep Partial Canonical Correlation Analysis |
| Authors | Guy Rotman, Ivan Vuli{'c}, Roi Reichart |
| Abstract | We present a deep neural network that leverages images to improve bilingual text embeddings. Relying on bilingual image tags and descriptions, our approach conditions text embedding induction on the shared visual information for both languages, producing highly correlated bilingual embeddings. In particular, we propose a novel model based on Partial Canonical Correlation Analysis (PCCA). While the original PCCA finds linear projections of two views in order to maximize their canonical correlation conditioned on a shared third variable, we introduce a non-linear Deep PCCA (DPCCA) model, and develop a new stochastic iterative algorithm for its optimization. We evaluate PCCA and DPCCA on multilingual word similarity and cross-lingual image description retrieval. Our models outperform a large variety of previous methods, despite not having access to any visual signal during test time inference. |
| Tasks | Image Retrieval, Question Answering, Representation Learning, Visual Question Answering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1084/ |
| https://www.aclweb.org/anthology/P18-1084 | |
| PWC | https://paperswithcode.com/paper/bridging-languages-through-images-with-deep |
| Repo | |
| Framework | |
