Paper Group NANR 210
Relevant and Informative Response Generation using Pointwise Mutual Information. Learning Relational Representations by Analogy using Hierarchical Siamese Networks. Abstract Graphs and Abstract Paths for Knowledge Graph Completion. Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study. Synchronously Generating Two Languages wit …
Relevant and Informative Response Generation using Pointwise Mutual Information
| Title | Relevant and Informative Response Generation using Pointwise Mutual Information |
| Authors | Junya Takayama, Yuki Arase |
| Abstract | A sequence-to-sequence model tends to generate generic responses with little information for input utterances. To solve this problem, we propose a neural model that generates relevant and informative responses. Our model has simple architecture to enable easy application to existing neural dialogue models. Specifically, using positive pointwise mutual information, it first identifies keywords that frequently co-occur in responses given an utterance. Then, the model encourages the decoder to use the keywords for response generation. Experiment results demonstrate that our model successfully diversifies responses relative to previous models. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4115/ |
| https://www.aclweb.org/anthology/W19-4115 | |
| PWC | https://paperswithcode.com/paper/relevant-and-informative-response-generation |
| Repo | |
| Framework | |
Learning Relational Representations by Analogy using Hierarchical Siamese Networks
| Title | Learning Relational Representations by Analogy using Hierarchical Siamese Networks |
| Authors | Gaetano Rossiello, Alfio Gliozzo, Robert Farrell, Nicolas Fauceglia, Michael Glass |
| Abstract | We address relation extraction as an analogy problem by proposing a novel approach to learn representations of relations expressed by their textual mentions. In our assumption, if two pairs of entities belong to the same relation, then those two pairs are analogous. Following this idea, we collect a large set of analogous pairs by matching triples in knowledge bases with web-scale corpora through distant supervision. We leverage this dataset to train a hierarchical siamese network in order to learn entity-entity embeddings which encode relational information through the different linguistic paraphrasing expressing the same relation. We evaluate our model in a one-shot learning task by showing a promising generalization capability in order to classify unseen relation types, which makes this approach suitable to perform automatic knowledge base population with minimal supervision. Moreover, the model can be used to generate pre-trained embeddings which provide a valuable signal when integrated into an existing neural-based model by outperforming the state-of-the-art methods on a downstream relation extraction task. |
| Tasks | Entity Embeddings, Knowledge Base Population, One-Shot Learning, Relation Extraction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1327/ |
| https://www.aclweb.org/anthology/N19-1327 | |
| PWC | https://paperswithcode.com/paper/learning-relational-representations-by |
| Repo | |
| Framework | |
Abstract Graphs and Abstract Paths for Knowledge Graph Completion
| Title | Abstract Graphs and Abstract Paths for Knowledge Graph Completion |
| Authors | Vivi Nastase, Bhushan Kotnis |
| Abstract | Knowledge graphs, which provide numerous facts in a machine-friendly format, are incomplete. Information that we induce from such graphs {–} e.g. entity embeddings, relation representations or patterns {–} will be affected by the imbalance in the information captured in the graph {–} by biasing representations, or causing us to miss potential patterns. To partially compensate for this situation we describe a method for representing knowledge graphs that capture an intensional representation of the original extensional information. This representation is very compact, and it abstracts away from individual links, allowing us to find better path candidates, as shown by the results of link prediction using this information. |
| Tasks | Entity Embeddings, Knowledge Graph Completion, Knowledge Graphs, Link Prediction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1016/ |
| https://www.aclweb.org/anthology/S19-1016 | |
| PWC | https://paperswithcode.com/paper/abstract-graphs-and-abstract-paths-for |
| Repo | |
| Framework | |
Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study
| Title | Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study |
| Authors | Erion {\c{C}}ano, Ond{\v{r}}ej Bojar |
| Abstract | Using data-driven models for solving text summarization or similar tasks has become very common in the last years. Yet most of the studies report basic accuracy scores only, and nothing is known about the ability of the proposed models to improve when trained on more data. In this paper, we define and propose three data efficiency metrics: data score efficiency, data time deficiency and overall data efficiency. We also propose a simple scheme that uses those metrics and apply it for a more comprehensive evaluation of popular methods on text summarization and title generation tasks. For the latter task, we process and release a huge collection of 35 million abstract-title pairs from scientific articles. Our results reveal that among the tested models, the Transformer is the most efficient on both tasks. |
| Tasks | Text Summarization |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8630/ |
| https://www.aclweb.org/anthology/W19-8630 | |
| PWC | https://paperswithcode.com/paper/efficiency-metrics-for-data-driven-models-a-1 |
| Repo | |
| Framework | |
Synchronously Generating Two Languages with Interactive Decoding
| Title | Synchronously Generating Two Languages with Interactive Decoding |
| Authors | Yining Wang, Jiajun Zhang, Long Zhou, Yuchen Liu, Chengqing Zong |
| Abstract | In this paper, we introduce a novel interactive approach to translate a source language into two different languages simultaneously and interactively. Specifically, the generation of one language relies on not only previously generated outputs by itself, but also the outputs predicted in the other language. Experimental results on IWSLT and WMT datasets demonstrate that our method can obtain significant improvements over both conventional Neural Machine Translation (NMT) model and multilingual NMT model. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1330/ |
| https://www.aclweb.org/anthology/D19-1330 | |
| PWC | https://paperswithcode.com/paper/synchronously-generating-two-languages-with |
| Repo | |
| Framework | |
NRC Parallel Corpus Filtering System for WMT 2019
| Title | NRC Parallel Corpus Filtering System for WMT 2019 |
| Authors | Gabriel Bernier-Colborne, Chi-kiu Lo |
| Abstract | We describe the National Research Council Canada team{'}s submissions to the parallel corpus filtering task at the Fourth Conference on Machine Translation. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5434/ |
| https://www.aclweb.org/anthology/W19-5434 | |
| PWC | https://paperswithcode.com/paper/nrc-parallel-corpus-filtering-system-for-wmt |
| Repo | |
| Framework | |
Visceral Machines: Reinforcement Learning with Intrinsic Physiological Rewards
| Title | Visceral Machines: Reinforcement Learning with Intrinsic Physiological Rewards |
| Authors | Daniel McDuff, Ashish Kapoor |
| Abstract | The human autonomic nervous system has evolved over millions of years and is essential for survival and responding to threats. As people learn to navigate the world, ``fight or flight’’ responses provide intrinsic feedback about the potential consequence of action choices (e.g., becoming nervous when close to a cliff edge or driving fast around a bend.) Physiological changes are correlated with these biological preparations to protect one-self from danger. We present a novel approach to reinforcement learning that leverages a task-independent intrinsic reward function trained on peripheral pulse measurements that are correlated with human autonomic nervous system responses. Our hypothesis is that such reward functions can circumvent the challenges associated with sparse and skewed rewards in reinforcement learning settings and can help improve sample efficiency. We test this in a simulated driving environment and show that it can increase the speed of learning and reduce the number of collisions during the learning stage. | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyNvti09KQ |
| https://openreview.net/pdf?id=SyNvti09KQ | |
| PWC | https://paperswithcode.com/paper/visceral-machines-reinforcement-learning-with-1 |
| Repo | |
| Framework | |
COCO-GAN: Conditional Coordinate Generative Adversarial Network
| Title | COCO-GAN: Conditional Coordinate Generative Adversarial Network |
| Authors | Chieh Hubert Lin, Chia-Che Chang, Yu-Sheng Chen, Da-Cheng Juan, Wei Wei, Hwann-Tzong Chen |
| Abstract | Recent advancements on Generative Adversarial Network (GAN) have inspired a wide range of works that generate synthetic images. However, the current processes have to generate an entire image at once, and therefore resolutions are limited by memory or computational constraints. In this work, we propose COnditional COordinate GAN (COCO-GAN), which generates a specific patch of an image conditioned on a spatial position rather than the entire image at a time. The generated patches are later combined together to form a globally coherent full-image. With this process, we show that the generated image can achieve competitive quality to state-of-the-arts and the generated patches are locally smooth between consecutive neighbors. One direct implication of the COCO-GAN is that it can be applied onto any coordinate systems including the cylindrical systems which makes it feasible for generating panorama images. The fact that the patch generation process is independent to each other inspires a wide range of new applications: firstly, “Patch-Inspired Image Generation” enables us to generate the entire image based on a single patch. Secondly, “Partial-Scene Generation” allows us to generate images within a customized target region. Finally, thanks to COCO-GAN’s patch generation and massive parallelism, which enables combining patches for generating a full-image with higher resolution than state-of-the-arts. |
| Tasks | Image Generation, Scene Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r14Aas09Y7 |
| https://openreview.net/pdf?id=r14Aas09Y7 | |
| PWC | https://paperswithcode.com/paper/coco-gan-conditional-coordinate-generative |
| Repo | |
| Framework | |
Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications
| Title | Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2600/ |
| https://www.aclweb.org/anthology/W19-2600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-extracting |
| Repo | |
| Framework | |
Towards Annotating and Creating Summary Highlights at Sub-sentence Level
| Title | Towards Annotating and Creating Summary Highlights at Sub-sentence Level |
| Authors | Kristjan Arumae, Parminder Bhatia, Fei Liu |
| Abstract | Highlighting is a powerful tool to pick out important content and emphasize. Creating summary highlights at the sub-sentence level is particularly desirable, because sub-sentences are more concise than whole sentences. They are also better suited than individual words and phrases that can potentially lead to disfluent, fragmented summaries. In this paper we seek to generate summary highlights by annotating summary-worthy sub-sentences and teaching classifiers to do the same. We frame the task as jointly selecting important sentences and identifying a single most informative textual unit from each sentence. This formulation dramatically reduces the task complexity involved in sentence compression. Our study provides new benchmarks and baselines for generating highlights at the sub-sentence level. |
| Tasks | Sentence Compression |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5408/ |
| https://www.aclweb.org/anthology/D19-5408 | |
| PWC | https://paperswithcode.com/paper/towards-annotating-and-creating-summary |
| Repo | |
| Framework | |
“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors
| Title | “Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors |
| Authors | Yosef Gandelsman, Assaf Shocher, Michal Irani |
| Abstract | Many seemingly unrelated computer vision tasks can be viewed as a special case of image decomposition into separate layers. For example, image segmentation (separation into foreground and background layers); transparent layer separation (into reflection and transmission layers); Image dehazing (separation into a clear image and a haze map), and more. In this paper we propose a unified framework for unsupervised layer decomposition of a single image, based on coupled “Deep-image-Prior” (DIP) networks. It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image. We show that coupling multiple such DIPs provides a powerful tool for decomposing images into their basic components, for a wide variety of applications. This capability stems from the fact that the internal statistics of a mixture of layers is more complex than the statistics of each of its individual components. We show the power of this approach for Image-Dehazing, Fg/Bg Segmentation, Watermark-Removal, Transparency Separation in images and video, and more. These capabilities are achieved in a totally unsupervised way, with no training examples other than the input image/video itself. |
| Tasks | Image Dehazing, Semantic Segmentation, Transparency Separation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Gandelsman_Double-DIP_Unsupervised_Image_Decomposition_via_Coupled_Deep-Image-Priors_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Gandelsman_Double-DIP_Unsupervised_Image_Decomposition_via_Coupled_Deep-Image-Priors_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/double-dip-unsupervised-image-decomposition-1 |
| Repo | |
| Framework | |
Autoencoder-based Music Translation
| Title | Autoencoder-based Music Translation |
| Authors | Noam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman |
| Abstract | We present a method for translating music across musical instruments and styles. This method is based on unsupervised training of a multi-domain wavenet autoencoder, with a shared encoder and a domain-independent latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the single encoder allows us to translate also from musical domains that were not seen during training. We evaluate our method on a dataset collected from professional musicians, and achieve convincing translations. We also study the properties of the obtained translation and demonstrate translating even from a whistle, potentially enabling the creation of instrumental music by untrained humans. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJGkisCcKm |
| https://openreview.net/pdf?id=HJGkisCcKm | |
| PWC | https://paperswithcode.com/paper/autoencoder-based-music-translation |
| Repo | |
| Framework | |
Team Ned Leeds at SemEval-2019 Task 4: Exploring Language Indicators of Hyperpartisan Reporting
| Title | Team Ned Leeds at SemEval-2019 Task 4: Exploring Language Indicators of Hyperpartisan Reporting |
| Authors | Bozhidar Stevanoski, Sonja Gievska |
| Abstract | This paper reports an experiment carried out to investigate the relevance of several syntactic, stylistic and pragmatic features on the task of distinguishing between mainstream and partisan news articles. The results of the evaluation of different feature sets and the extent to which various feature categories could affect the performance metrics are discussed and compared. Among different combinations of features and classifiers, Random Forest classifier using vector representations of the headline and the text of the report, with the inclusion of 8 readability scores and few stylistic features yielded best result, ranking our team at the 9th place at the SemEval 2019 Hyperpartisan News Detection challenge. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2179/ |
| https://www.aclweb.org/anthology/S19-2179 | |
| PWC | https://paperswithcode.com/paper/team-ned-leeds-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
Modeling Quantification and Scope in Abstract Meaning Representations
| Title | Modeling Quantification and Scope in Abstract Meaning Representations |
| Authors | James Pustejovsky, Ken Lai, Nianwen Xue |
| Abstract | In this paper, we propose an extension to Abstract Meaning Representations (AMRs) to encode scope information of quantifiers and negation, in a way that overcomes the semantic gaps of the schema while maintaining its cognitive simplicity. Specifically, we address three phenomena not previously part of the AMR specification: quantification, negation (generally), and modality. The resulting representation, which we call {}Uniform Meaning Representation{''} (UMR), adopts the predicative core of AMR and embeds it under a {}scope{''} graph when appropriate. UMR representations differ from other treatments of quantification and modal scope phenomena in two ways: (a) they are more transparent; and (b) they specify default scope when possible.{`} | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3303/ |
| https://www.aclweb.org/anthology/W19-3303 | |
| PWC | https://paperswithcode.com/paper/modeling-quantification-and-scope-in-abstract |
| Repo | |
| Framework | |
Optimising the Machine Translation Post-editing Workflow
| Title | Optimising the Machine Translation Post-editing Workflow |
| Authors | Anna Zaretskaya |
| Abstract | In this article, we describe how machine translation is used for post-editing at TransPerfect and the ways in which we optimise the workflow. This includes MT evaluation, MT engine customisation, leveraging MT suggestions compared to TM matches, and the lessons learnt from implementing MT at a large scale. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8718/ |
| https://www.aclweb.org/anthology/W19-8718 | |
| PWC | https://paperswithcode.com/paper/optimising-the-machine-translation-post |
| Repo | |
| Framework | |
