Paper Group NANR 106
A New Concept of Deep Reinforcement Learning based Augmented General Tagging System. Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures. Automation and Optimisation of Humor Trait Generation in a Vocal Dialogue System. Better Generalization by Efficient Trust Region Method. Integration complexity and the order of cosi …
A New Concept of Deep Reinforcement Learning based Augmented General Tagging System
| Title | A New Concept of Deep Reinforcement Learning based Augmented General Tagging System |
| Authors | Yu Wang, Abhishek Patel, Hongxia Jin |
| Abstract | In this paper, a new deep reinforcement learning based augmented general tagging system is proposed. The new system contains two parts: a deep neural network (DNN) based sequence labeling model and a deep reinforcement learning (DRL) based augmented tagger. The augmented tagger helps improve system performance by modeling the data with minority tags. The new system is evaluated on SLU and NLU sequence labeling tasks using ATIS and CoNLL-2003 benchmark datasets, to demonstrate the new system{'}s outstanding performance on general tagging tasks. Evaluated by F1 scores, it shows that the new system outperforms the current state-of-the-art model on ATIS dataset by 1.9{%} and that on CoNLL-2003 dataset by 1.4{%}. |
| Tasks | Named Entity Recognition, Slot Filling, Spoken Language Understanding |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1143/ |
| https://www.aclweb.org/anthology/C18-1143 | |
| PWC | https://paperswithcode.com/paper/a-new-concept-of-deep-reinforcement-learning-1 |
| Repo | |
| Framework | |
Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures
| Title | Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures |
| Authors | Danilo Croce, Daniele Rossini, Roberto Basili |
| Abstract | Nonlinear methods such as deep neural networks achieve state-of-the-art performances in several semantic NLP tasks. However epistemologically transparent decisions are not provided as for the limited interpretability of the underlying acquired neural models. In neural-based semantic inference tasks epistemological transparency corresponds to the ability of tracing back causal connections between the linguistic properties of a input instance and the produced classification output. In this paper, we propose the use of a methodology, called \textit{Layerwise Relevance Propagation}, over linguistically motivated neural architectures, namely \textit{Kernel-based Deep Architectures} (KDA), to guide argumentations and explanation inferences. In such a way, each decision provided by a KDA can be linked to real examples, linguistically related to the input instance: these can be used to motivate the network output. Quantitative analysis shows that richer explanations about the semantic and syntagmatic structures of the examples characterize more convincing arguments in two tasks, i.e. question classification and semantic role labeling. |
| Tasks | Image Classification, Question Answering, Semantic Role Labeling |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5403/ |
| https://www.aclweb.org/anthology/W18-5403 | |
| PWC | https://paperswithcode.com/paper/explaining-non-linear-classifier-decisions |
| Repo | |
| Framework | |
Automation and Optimisation of Humor Trait Generation in a Vocal Dialogue System
| Title | Automation and Optimisation of Humor Trait Generation in a Vocal Dialogue System |
| Authors | Matthieu Riou, St{'e}phane Huet, Bassam Jabaian, Fabrice Lef{`e}vre |
| Abstract | |
| Tasks | Dialogue Management, Spoken Dialogue Systems, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6703/ |
| https://www.aclweb.org/anthology/W18-6703 | |
| PWC | https://paperswithcode.com/paper/automation-and-optimisation-of-humor-trait |
| Repo | |
| Framework | |
Better Generalization by Efficient Trust Region Method
| Title | Better Generalization by Efficient Trust Region Method |
| Authors | Xuanqing Liu, Jason D. Lee, Cho-Jui Hsieh |
| Abstract | In this paper, we develop a trust region method for training deep neural networks. At each iteration, trust region method computes the search direction by solving a non-convex subproblem. Solving this subproblem is non-trivial—existing methods have only sub-linear convergence rate. In the first part, we show that a simple modification of gradient descent algorithm can converge to a global minimizer of the subproblem with an asymptotic linear convergence rate. Moreover, our method only requires Hessian-vector products, which can be computed efficiently by back-propagation in neural networks. In the second part, we apply our algorithm to train large-scale convolutional neural networks, such as VGG and MobileNets. Although trust region method is about 3 times slower than SGD in terms of running time, we observe it finds a model that has lower generalization (test) error than SGD, and this difference is even more significant in large batch training. We conduct several interesting experiments to support our conjecture that the trust region method can avoid sharp local minimas. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJjePwx0- |
| https://openreview.net/pdf?id=HJjePwx0- | |
| PWC | https://paperswithcode.com/paper/better-generalization-by-efficient-trust |
| Repo | |
| Framework | |
Integration complexity and the order of cosisters
| Title | Integration complexity and the order of cosisters |
| Authors | William Dyer |
| Abstract | The cost of integrating dependent constituents to their heads is thought to involve the distance between dependent and head and the complexity of the integration (Gibson, 1998). The former has been convincingly addressed by Dependency Distance Minimization (DDM) (cf. Liu et al., 2017). The current study addresses the latter by proposing a novel theory of integration complexity derived from the entropy of the probability distribution of a dependent{'}s heads. An analysis of Universal Dependency corpora provides empirical evidence regarding the preferred order of isomorphic cosisters{—}sister constituents of the same syntactic form on the same side of their head{—}such as the adjectives in \textit{pretty blue fish}. Integration complexity, alongside DDM, allows for a general theory of constituent order based on integration cost. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6007/ |
| https://www.aclweb.org/anthology/W18-6007 | |
| PWC | https://paperswithcode.com/paper/integration-complexity-and-the-order-of |
| Repo | |
| Framework | |
Probabilistic Verb Selection for Data-to-Text Generation
| Title | Probabilistic Verb Selection for Data-to-Text Generation |
| Authors | Dell Zhang, Jiahao Yuan, Xiaoling Wang, Adam Foster |
| Abstract | In data-to-text Natural Language Generation (NLG) systems, computers need to find the right words to describe phenomena seen in the data. This paper focuses on the problem of choosing appropriate verbs to express the direction and magnitude of a percentage change (e.g., in stock prices). Rather than simply using the same verbs again and again, we present a principled data-driven approach to this problem based on Shannon{'}s noisy-channel model so as to bring variation and naturalness into the generated text. Our experiments on three large-scale real-world news corpora demonstrate that the proposed probabilistic model can be learned to accurately imitate human authors{'} pattern of usage around verbs, outperforming the state-of-the-art method significantly. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/Q18-1038/ |
| https://www.aclweb.org/anthology/Q18-1038 | |
| PWC | https://paperswithcode.com/paper/probabilistic-verb-selection-for-data-to-text |
| Repo | |
| Framework | |
A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers
| Title | A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers |
| Authors | Omer Ben-Porat, Moshe Tennenholtz |
| Abstract | We introduce a game-theoretic approach to the study of recommendation systems with strategic content providers. Such systems should be fair and stable. Showing that traditional approaches fail to satisfy these requirements, we propose the Shapley mediator. We show that the Shapley mediator satisfies the fairness and stability requirements, runs in linear time, and is the only economically efficient mechanism satisfying these properties. |
| Tasks | Recommendation Systems |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7388-a-game-theoretic-approach-to-recommendation-systems-with-strategic-content-providers |
| http://papers.nips.cc/paper/7388-a-game-theoretic-approach-to-recommendation-systems-with-strategic-content-providers.pdf | |
| PWC | https://paperswithcode.com/paper/a-game-theoretic-approach-to-recommendation |
| Repo | |
| Framework | |
Shami: A Corpus of Levantine Arabic Dialects
| Title | Shami: A Corpus of Levantine Arabic Dialects |
| Authors | Kathrein Abu Kwaik, Motaz Saad, Stergios Chatzikyriakidis, Simon Dobnik |
| Abstract | |
| Tasks | Language Identification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1576/ |
| https://www.aclweb.org/anthology/L18-1576 | |
| PWC | https://paperswithcode.com/paper/shami-a-corpus-of-levantine-arabic-dialects |
| Repo | |
| Framework | |
UPS: optimizing Undirected Positive Sparse graph for neural graph filtering
| Title | UPS: optimizing Undirected Positive Sparse graph for neural graph filtering |
| Authors | Mikhail Yurochkin, Dung Thai, Hung Hai Bui, XuanLong Nguyen |
| Abstract | In this work we propose a novel approach for learning graph representation of the data using gradients obtained via backpropagation. Next we build a neural network architecture compatible with our optimization approach and motivated by graph filtering in the vertex domain. We demonstrate that the learned graph has richer structure than often used nearest neighbors graphs constructed based on features similarity. Our experiments demonstrate that we can improve prediction quality for several convolution on graphs architectures, while others appeared to be insensitive to the input graph. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HklZOfW0W |
| https://openreview.net/pdf?id=HklZOfW0W | |
| PWC | https://paperswithcode.com/paper/ups-optimizing-undirected-positive-sparse |
| Repo | |
| Framework | |
S2SPMN: A Simple and Effective Framework for Response Generation with Relevant Information
| Title | S2SPMN: A Simple and Effective Framework for Response Generation with Relevant Information |
| Authors | Jiaxin Pei, Chenliang Li |
| Abstract | How to generate relevant and informative responses is one of the core topics in response generation area. Following the task formulation of machine translation, previous works mainly consider response generation task as a mapping from a source sentence to a target sentence. To realize this mapping, existing works tend to design intuitive but complex models. However, the relevant information existed in large dialogue corpus is mainly overlooked. In this paper, we propose Sequence to Sequence with Prototype Memory Network (S2SPMN) to exploit the relevant information provided by the large dialogue corpus to enhance response generation. Specifically, we devise two simple approaches in S2SPMN to select the relevant information (named prototypes) from the dialogue corpus. These prototypes are then saved into prototype memory network (PMN). Furthermore, a hierarchical attention mechanism is devised to extract the semantic information from the PMN to assist the response generation process. Empirical studies reveal the advantage of our model over several classical and strong baselines. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1082/ |
| https://www.aclweb.org/anthology/D18-1082 | |
| PWC | https://paperswithcode.com/paper/s2spmn-a-simple-and-effective-framework-for |
| Repo | |
| Framework | |
Knowledge Base Question Answering via Encoding of Complex Query Graphs
| Title | Knowledge Base Question Answering via Encoding of Complex Query Graphs |
| Authors | Kangqi Luo, Fengli Lin, Xusheng Luo, Kenny Zhu |
| Abstract | Answering complex questions that involve multiple entities and multiple relations using a standard knowledge base is an open and challenging task. Most existing KBQA approaches focus on simpler questions and do not work very well on complex questions because they were not able to simultaneously represent the question and the corresponding complex query structure. In this work, we encode such complex query structure into a uniform vector representation, and thus successfully capture the interactions between individual semantic components within a complex question. This approach consistently outperforms existing methods on complex questions while staying competitive on simple questions. |
| Tasks | Knowledge Base Question Answering, Question Answering, Semantic Parsing |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1242/ |
| https://www.aclweb.org/anthology/D18-1242 | |
| PWC | https://paperswithcode.com/paper/knowledge-base-question-answering-via |
| Repo | |
| Framework | |
WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition
| Title | WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition |
| Authors | Yufeng Diao, Hongfei Lin, Di Wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang |
| Abstract | Homographic puns have a long history in human writing, widely used in written and spoken literature, which usually occur in a certain syntactic or stylistic structure. How to recognize homographic puns is an important research. However, homographic pun recognition does not solve very well in existing work. In this work, we first use WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and then propose a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns. Our experiments on the SemEval2017 Task7 and Pun of the Day demonstrate that the proposed model is able to distinguish between homographic pun and non-homographic pun texts. We show the effectiveness of the model to present the capability of choosing qualitatively informative words. The results show that our model achieves the state-of-the-art performance on homographic puns recognition. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1272/ |
| https://www.aclweb.org/anthology/D18-1272 | |
| PWC | https://paperswithcode.com/paper/wecai14a-wordnet-encoded-collocation |
| Repo | |
| Framework | |
Enhancing Universal Dependencies for Korean
| Title | Enhancing Universal Dependencies for Korean |
| Authors | Youngbin Noh, Jiyoon Han, Tae Hwan Oh, Hansaem Kim |
| Abstract | In this paper, for the purpose of enhancing Universal Dependencies for the Korean language, we propose a modified method for mapping Korean Part-of-Speech(POS) tagset in relation to Universal Part-of-Speech (UPOS) tagset in order to enhance the Universal Dependencies for the Korean Language. Previous studies suggest that UPOS reflects several issues that influence dependency annotation by using the POS of Korean predicates, particularly the distinctiveness in using verb, adjective, and copula. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6013/ |
| https://www.aclweb.org/anthology/W18-6013 | |
| PWC | https://paperswithcode.com/paper/enhancing-universal-dependencies-for-korean |
| Repo | |
| Framework | |
A Memory-Sensitive Classification Model of Errors in Early Second Language Learning
| Title | A Memory-Sensitive Classification Model of Errors in Early Second Language Learning |
| Authors | Brendan Tomoschuk, Jarrett Lovelett |
| Abstract | In this paper, we explore a variety of linguistic and cognitive features to better understand second language acquisition in early users of the language learning app Duolingo. With these features, we trained a random forest classifier to predict errors in early learners of French, Spanish, and English. Of particular note was our finding that mean and variance in error for each user and token can be a memory efficient replacement for their respective dummy-encoded categorical variables. At test, these models improved over the baseline model with AUROC values of 0.803 for English, 0.823 for French, and 0.829 for Spanish. |
| Tasks | Language Acquisition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0527/ |
| https://www.aclweb.org/anthology/W18-0527 | |
| PWC | https://paperswithcode.com/paper/a-memory-sensitive-classification-model-of |
| Repo | |
| Framework | |
SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions
| Title | SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions |
| Authors | Chandrajit Bajaj, Tingran Gao, Zihang He, Qixing Huang, Zhenxiao Liang |
| Abstract | We introduce a principled approach for simultaneous mapping and clustering (SMAC) for establishing consistent maps across heterogeneous object collections (e.g., 2D images or 3D shapes). Our approach takes as input a heterogeneous object collection and a set of maps computed between some pairs of objects, and outputs a homogeneous object clustering together with a new set of maps possessing optimal intra- and inter-cluster consistency. Our approach is based on the spectral decomposition of a data matrix storing all pairwise maps in its blocks. We additionally provide tight theoretical guarantees on the exactness of SMAC under established noise models. We also demonstrate the usefulness of the approach on synthetic and real datasets. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1899 |
| http://proceedings.mlr.press/v80/bajaj18a/bajaj18a.pdf | |
| PWC | https://paperswithcode.com/paper/smac-simultaneous-mapping-and-clustering |
| Repo | |
| Framework | |
