Paper Group NANR 126
Neural Response Generation for Customer Service based on Personality Traits. The Rich Event Ontology. Neural Networks and Spelling Features for Native Language Identification. A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data. Domain Specific Automatic Question Generation from Text. Constructive Language in News Comments. Robu …
Neural Response Generation for Customer Service based on Personality Traits
| Title | Neural Response Generation for Customer Service based on Personality Traits |
| Authors | Jonathan Herzig, Michal Shmueli-Scheuer, S, Tommy bank, David Konopnicki |
| Abstract | We present a neural response generation model that generates responses conditioned on a target personality. The model learns high level features based on the target personality, and uses them to update its hidden state. Our model achieves performance improvements in both perplexity and BLEU scores over a baseline sequence-to-sequence model, and is validated by human judges. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3541/ |
| https://www.aclweb.org/anthology/W17-3541 | |
| PWC | https://paperswithcode.com/paper/neural-response-generation-for-customer |
| Repo | |
| Framework | |
The Rich Event Ontology
| Title | The Rich Event Ontology |
| Authors | Susan Brown, Claire Bonial, Leo Obrst, Martha Palmer |
| Abstract | In this paper we describe a new lexical semantic resource, The Rich Event On-tology, which provides an independent conceptual backbone to unify existing semantic role labeling (SRL) schemas and augment them with event-to-event causal and temporal relations. By unifying the FrameNet, VerbNet, Automatic Content Extraction, and Rich Entities, Relations and Events resources, the ontology serves as a shared hub for the disparate annotation schemas and therefore enables the combination of SRL training data into a larger, more diverse corpus. By adding temporal and causal relational information not found in any of the independent resources, the ontology facilitates reasoning on and across documents, revealing relationships between events that come together in temporal and causal chains to build more complex scenarios. We envision the open resource serving as a valuable tool for both moving from the ontology to text to query for event types and scenarios of interest, and for moving from text to the ontology to access interpretations of events using the combined semantic information housed there. |
| Tasks | Question Answering, Semantic Role Labeling |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2712/ |
| https://www.aclweb.org/anthology/W17-2712 | |
| PWC | https://paperswithcode.com/paper/the-rich-event-ontology |
| Repo | |
| Framework | |
Neural Networks and Spelling Features for Native Language Identification
| Title | Neural Networks and Spelling Features for Native Language Identification |
| Authors | Johannes Bjerva, Gintar{.e} Grigonyt{.e}, Robert {"O}stling, Barbara Plank |
| Abstract | We present the RUG-SU team{'}s submission at the Native Language Identification Shared Task 2017. We combine several approaches into an ensemble, based on spelling error features, a simple neural network using word representations, a deep residual network using word and character features, and a system based on a recurrent neural network. Our best system is an ensemble of neural networks, reaching an F1 score of 0.8323. Although our system is not the highest ranking one, we do outperform the baseline by far. |
| Tasks | Language Identification, Native Language Identification, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5025/ |
| https://www.aclweb.org/anthology/W17-5025 | |
| PWC | https://paperswithcode.com/paper/neural-networks-and-spelling-features-for |
| Repo | |
| Framework | |
A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data
| Title | A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data |
| Authors | Qiaolin Xia, Lei Sha, Baobao Chang, Zhifang Sui |
| Abstract | Previous studies on Chinese semantic role labeling (SRL) have concentrated on a single semantically annotated corpus. But the training data of single corpus is often limited. Whereas the other existing semantically annotated corpora for Chinese SRL are scattered across different annotation frameworks. But still, Data sparsity remains a bottleneck. This situation calls for larger training datasets, or effective approaches which can take advantage of highly heterogeneous data. In this paper, we focus mainly on the latter, that is, to improve Chinese SRL by using heterogeneous corpora together. We propose a novel progressive learning model which augments the Progressive Neural Network with Gated Recurrent Adapters. The model can accommodate heterogeneous inputs and effectively transfer knowledge between them. We also release a new corpus, Chinese SemBank, for Chinese SRL. Experiments on CPB 1.0 show that our model outperforms state-of-the-art methods. |
| Tasks | Machine Translation, Semantic Role Labeling, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1189/ |
| https://www.aclweb.org/anthology/P17-1189 | |
| PWC | https://paperswithcode.com/paper/a-progressive-learning-approach-to-chinese |
| Repo | |
| Framework | |
Domain Specific Automatic Question Generation from Text
| Title | Domain Specific Automatic Question Generation from Text |
| Authors | Katira Soleymanzadeh |
| Abstract | |
| Tasks | Dependency Parsing, Question Generation, Semantic Parsing, Semantic Role Labeling |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3014/ |
| https://www.aclweb.org/anthology/P17-3014 | |
| PWC | https://paperswithcode.com/paper/domain-specific-automatic-question-generation |
| Repo | |
| Framework | |
Constructive Language in News Comments
| Title | Constructive Language in News Comments |
| Authors | Varada Kolhatkar, Maite Taboada |
| Abstract | We discuss the characteristics of constructive news comments, and present methods to identify them. First, we define the notion of constructiveness. Second, we annotate a corpus for constructiveness. Third, we explore whether available argumentation corpora can be useful to identify constructiveness in news comments. Our model trained on argumentation corpora achieves a top accuracy of 72.59{%} (baseline=49.44{%}) on our crowd-annotated test data. Finally, we examine the relation between constructiveness and toxicity. In our crowd-annotated data, 21.42{%} of the non-constructive comments and 17.89{%} of the constructive comments are toxic, suggesting that non-constructive comments are not much more toxic than constructive comments. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3002/ |
| https://www.aclweb.org/anthology/W17-3002 | |
| PWC | https://paperswithcode.com/paper/constructive-language-in-news-comments |
| Repo | |
| Framework | |
Robust Structured Estimation with Single-Index Models
| Title | Robust Structured Estimation with Single-Index Models |
| Authors | Sheng Chen, Arindam Banerjee |
| Abstract | In this paper, we investigate general single-index models (SIMs) in high dimensions. Based on U-statistics, we propose two types of robust estimators for the recovery of model parameters, which can be viewed as generalizations of several existing algorithms for one-bit compressed sensing (1-bit CS). With minimal assumption on noise, the statistical guarantees are established for the generalized estimators under suitable conditions, which allow general structures of underlying parameter. Moreover, the proposed estimator is novelly instantiated for SIMs with monotone transfer function, and the obtained estimator can better leverage the monotonicity. Experimental results are provided to support our theoretical analyses. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=828 |
| http://proceedings.mlr.press/v70/chen17a/chen17a.pdf | |
| PWC | https://paperswithcode.com/paper/robust-structured-estimation-with-single |
| Repo | |
| Framework | |
Using Serious Games to Correct French Dictations: Proposal for a New Unity3D/NooJ Connector
| Title | Using Serious Games to Correct French Dictations: Proposal for a New Unity3D/NooJ Connector |
| Authors | Ikram Bououd, Rania Fafi |
| Abstract | |
| Tasks | Active Learning, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3808/ |
| https://www.aclweb.org/anthology/W17-3808 | |
| PWC | https://paperswithcode.com/paper/using-serious-games-to-correct-french |
| Repo | |
| Framework | |
Proceedings of the Workshop on Computational Creativity in Natural Language Generation (CC-NLG 2017)
| Title | Proceedings of the Workshop on Computational Creativity in Natural Language Generation (CC-NLG 2017) |
| Authors | |
| Abstract | |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3900/ |
| https://www.aclweb.org/anthology/W17-3900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-computational-10 |
| Repo | |
| Framework | |
Synthetic Literature: Writing Science Fiction in a Co-Creative Process
| Title | Synthetic Literature: Writing Science Fiction in a Co-Creative Process |
| Authors | Enrique Manjavacas, Folgert Karsdorp, Ben Burtenshaw, Mike Kestemont |
| Abstract | |
| Tasks | Language Modelling, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3904/ |
| https://www.aclweb.org/anthology/W17-3904 | |
| PWC | https://paperswithcode.com/paper/synthetic-literature-writing-science-fiction |
| Repo | |
| Framework | |
A FST Description of Noun and Verb Morphology of Azarbaijani Turkish
| Title | A FST Description of Noun and Verb Morphology of Azarbaijani Turkish |
| Authors | Razieh Ehsani, Berke {"O}zen{\c{c}}, Ercan Solak |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4008/ |
| https://www.aclweb.org/anthology/W17-4008 | |
| PWC | https://paperswithcode.com/paper/a-fst-description-of-noun-and-verb-morphology |
| Repo | |
| Framework | |
Proceedings of the Student Research Workshop Associated with {RANLP} 2017
| Title | Proceedings of the Student Research Workshop Associated with {RANLP} 2017 |
| Authors | Venelin Kovatchev, Irina Temnikova, Pepa Gencheva, Yasen Kiprov, Ivelina Nikolova |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/papers/R/R17/R17-2000/ |
| https://doi.org/10.26615/issn.1314-9156.2017_ | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-student-research-workshop-9 |
| Repo | |
| Framework | |
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
| Title | PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs |
| Authors | Yunbo Wang, Mingsheng Long, Jianmin Wang, Zhifeng Gao, Philip S. Yu |
| Abstract | The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures. This paper models these structures by presenting a predictive recurrent neural network (PredRNN). This architecture is enlightened by the idea that spatiotemporal predictive learning should memorize both spatial appearances and temporal variations in a unified memory pool. Concretely, memory states are no longer constrained inside each LSTM unit. Instead, they are allowed to zigzag in two directions: across stacked RNN layers vertically and through all RNN states horizontally. The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously. PredRNN achieves the state-of-the-art prediction performance on three video prediction datasets and is a more general framework, that can be easily extended to other predictive learning tasks by integrating with other architectures. |
| Tasks | Video Prediction |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6689-predrnn-recurrent-neural-networks-for-predictive-learning-using-spatiotemporal-lstms |
| http://papers.nips.cc/paper/6689-predrnn-recurrent-neural-networks-for-predictive-learning-using-spatiotemporal-lstms.pdf | |
| PWC | https://paperswithcode.com/paper/predrnn-recurrent-neural-networks-for |
| Repo | |
| Framework | |
Building an Argument Search Engine for the Web
| Title | Building an Argument Search Engine for the Web |
| Authors | Henning Wachsmuth, Martin Potthast, Khalid Al-Khatib, Yamen Ajjour, Jana Puschmann, Jiani Qu, Jonas Dorsch, Viorel Morari, Janek Bevendorff, Benno Stein |
| Abstract | Computational argumentation is expected to play a critical role in the future of web search. To make this happen, many search-related questions must be revisited, such as how people query for arguments, how to mine arguments from the web, or how to rank them. In this paper, we develop an argument search framework for studying these and further questions. The framework allows for the composition of approaches to acquiring, mining, assessing, indexing, querying, retrieving, ranking, and presenting arguments while relying on standard infrastructure and interfaces. Based on the framework, we build a prototype search engine, called args, that relies on an initial, freely accessible index of nearly 300k arguments crawled from reliable web resources. The framework and the argument search engine are intended as an environment for collaborative research on computational argumentation and its practical evaluation. |
| Tasks | Argument Mining, Decision Making |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5106/ |
| https://www.aclweb.org/anthology/W17-5106 | |
| PWC | https://paperswithcode.com/paper/building-an-argument-search-engine-for-the |
| Repo | |
| Framework | |
Dual Tensor Model for Detecting Asymmetric Lexico-Semantic Relations
| Title | Dual Tensor Model for Detecting Asymmetric Lexico-Semantic Relations |
| Authors | Goran Glava{\v{s}}, Simone Paolo Ponzetto |
| Abstract | Detection of lexico-semantic relations is one of the central tasks of computational semantics. Although some fundamental relations (e.g., hypernymy) are asymmetric, most existing models account for asymmetry only implicitly and use the same concept representations to support detection of symmetric and asymmetric relations alike. In this work, we propose the Dual Tensor model, a neural architecture with which we explicitly model the asymmetry and capture the translation between unspecialized and specialized word embeddings via a pair of tensors. Although our Dual Tensor model needs only unspecialized embeddings as input, our experiments on hypernymy and meronymy detection suggest that it can outperform more complex and resource-intensive models. We further demonstrate that the model can account for polysemy and that it exhibits stable performance across languages. |
| Tasks | Semantic Textual Similarity, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1185/ |
| https://www.aclweb.org/anthology/D17-1185 | |
| PWC | https://paperswithcode.com/paper/dual-tensor-model-for-detecting-asymmetric |
| Repo | |
| Framework | |
