Paper Group NANR 217
CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark. Read, Attend and Comment: A Deep Architecture for Automatic NewsComment Generation. An Encoder with non-Sequential Dependency for Neural Data-to-Text Generation. A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG. Detecting Out-Of-Distribution Samples Using Lo …
CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark
| Title | CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark |
| Authors | Alan Lukezic, Ugur Kart, Jani Kapyla, Ahmed Durmush, Joni-Kristian Kamarainen, Jiri Matas, Matej Kristan |
| Abstract | We propose a new color-and-depth general visual object tracking benchmark (CDTB). CDTB is recorded by several passive and active RGB-D setups and contains indoor as well as outdoor sequences acquired in direct sunlight. The CDTB dataset is the largest and most diverse dataset in RGB-D tracking, with an order of magnitude larger number of frames than related datasets. The sequences have been carefully recorded to contain significant object pose change, clutter, occlusion, and periods of long-term target absence to enable tracker evaluation under realistic conditions. Sequences are per-frame annotated with 13 visual attributes for detailed analysis. Experiments with RGB and RGB-D trackers show that CDTB is more challenging than previous datasets. State-of-the-art RGB trackers outperform the recent RGB-D trackers, indicating a large gap between the two fields, which has not been previously detected by the prior benchmarks. Based on the results of the analysis we point out opportunities for future research in RGB-D tracker design. |
| Tasks | Object Tracking, Visual Object Tracking |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lukezic_CDTB_A_Color_and_Depth_Visual_Object_Tracking_Dataset_and_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lukezic_CDTB_A_Color_and_Depth_Visual_Object_Tracking_Dataset_and_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/cdtb-a-color-and-depth-visual-object-tracking-1 |
| Repo | |
| Framework | |
Read, Attend and Comment: A Deep Architecture for Automatic NewsComment Generation
| Title | Read, Attend and Comment: A Deep Architecture for Automatic NewsComment Generation |
| Authors | Ze Yang, Can Xu, Wei Wu, Zhoujun Li |
| Abstract | Automatic news comment generation is a new testbed for techniques of natural language generation. In this paper, we propose a “read-attend-comment” procedure for news comment generation and formalize the procedure with a reading network and a generation network. The reading network comprehends a news article and distills some important points from it, then the generation network creates a comment by attending to the extracted discrete points and the news title. We optimize the model in an end-to-end manner by maximizing a variational lower bound of the true objective using the back-propagation algorithm. Experimental results on two datasets indicate that our model can significantly outperform existing methods in terms of both automatic evaluation and human judgment. |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1909.11974 |
| https://arxiv.org/pdf/1909.11974.pdf | |
| PWC | https://paperswithcode.com/paper/read-attend-and-comment-a-deep-architecture-1 |
| Repo | |
| Framework | |
An Encoder with non-Sequential Dependency for Neural Data-to-Text Generation
| Title | An Encoder with non-Sequential Dependency for Neural Data-to-Text Generation |
| Authors | Feng Nie, Jinpeng Wang, Rong Pan, Chin-Yew Lin |
| Abstract | Data-to-text generation aims to generate descriptions given a structured input data (i.e., a table with multiple records). Existing neural methods for encoding input data can be divided into two categories: a) pooling based encoders which ignore dependencies between input records or b) recurrent encoders which model only sequential dependencies between input records. In our investigation, although the recurrent encoder generally outperforms the pooling based encoder by learning the sequential dependencies, it is sensitive to the order of the input records (i.e., performance decreases when injecting the random shuffling noise over input data). To overcome this problem, we propose to adopt the self-attention mechanism to learn dependencies between arbitrary input records. Experimental results show the proposed method achieves comparable results and remains stable under random shuffling over input data. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8619/ |
| https://www.aclweb.org/anthology/W19-8619 | |
| PWC | https://paperswithcode.com/paper/an-encoder-with-non-sequential-dependency-for |
| Repo | |
| Framework | |
A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG
| Title | A Closer Look at Recent Results of Verb Selection for Data-to-Text NLG |
| Authors | Guanyi Chen, Jin-Ge Yao |
| Abstract | Automatic natural language generation systems need to use the contextually-appropriate verbs when describing different kinds of facts or events, which has triggered research interest on verb selection for data-to-text generation. In this paper, we discuss a few limitations of the current task settings and the evaluation metrics. We also provide two simple, efficient, interpretable baseline approaches for statistical selection of trend verbs, which give a strong performance on both previously used evaluation metrics and our new evaluation. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8622/ |
| https://www.aclweb.org/anthology/W19-8622 | |
| PWC | https://paperswithcode.com/paper/a-closer-look-at-recent-results-of-verb |
| Repo | |
| Framework | |
Detecting Out-Of-Distribution Samples Using Low-Order Deep Features Statistics
| Title | Detecting Out-Of-Distribution Samples Using Low-Order Deep Features Statistics |
| Authors | Igor M. Quintanilha, Roberto de M. E. Filho, José Lezama, Mauricio Delbracio, Leonardo O. Nunes |
| Abstract | The ability to detect when an input sample was not drawn from the training distribution is an important desirable property of deep neural networks. In this paper, we show that a simple ensembling of first and second order deep feature statistics can be exploited to effectively differentiate in-distribution and out-of-distribution samples. Specifically, we observe that the mean and standard deviation within feature maps differs greatly between in-distribution and out-of-distribution samples. Based on this observation, we propose a simple and efficient plug-and-play detection procedure that does not require re-training, pre-processing or changes to the model. The proposed method outperforms the state-of-the-art by a large margin in all standard benchmarking tasks, while being much simpler to implement and execute. Notably, our method improves the true negative rate from 39.6% to 95.3% when 95% of in-distribution (CIFAR-100) are correctly detected using a DenseNet and the out-of-distribution dataset is TinyImageNet resize. The source code of our method will be made publicly available. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkgpCoRctm |
| https://openreview.net/pdf?id=rkgpCoRctm | |
| PWC | https://paperswithcode.com/paper/detecting-out-of-distribution-samples-using |
| Repo | |
| Framework | |
On the effect of the activation function on the distribution of hidden nodes in a deep network
| Title | On the effect of the activation function on the distribution of hidden nodes in a deep network |
| Authors | Philip M. Long and Hanie Sedghi |
| Abstract | We analyze the joint probability distribution on the lengths of the vectors of hidden variables in different layers of a fully connected deep network, when the weights and biases are chosen randomly according to Gaussian distributions, and the input is binary-valued. We show that, if the activation function satisfies a minimal set of assumptions, satisfied by all activation functions that we know that are used in practice, then, as the width of the network gets large, the ``length process’’ converges in probability to a length map that is determined as a simple function of the variances of the random weights and biases, and the activation function. We also show that this convergence may fail for activation functions that violate our assumptions. | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJej3s09Km |
| https://openreview.net/pdf?id=HJej3s09Km | |
| PWC | https://paperswithcode.com/paper/on-the-effect-of-the-activation-function-on-1 |
| Repo | |
| Framework | |
Neural News Recommendation with Long- and Short-term User Representations
| Title | Neural News Recommendation with Long- and Short-term User Representations |
| Authors | Mingxiao An, Fangzhao Wu, Chuhan Wu, Kun Zhang, Zheng Liu, Xing Xie |
| Abstract | Personalized news recommendation is important to help users find their interested news and improve reading experience. A key problem in news recommendation is learning accurate user representations to capture their interests. Users usually have both long-term preferences and short-term interests. However, existing news recommendation methods usually learn single representations of users, which may be insufficient. In this paper, we propose a neural news recommendation approach which can learn both long- and short-term user representations. The core of our approach is a news encoder and a user encoder. In the news encoder, we learn representations of news from their titles and topic categories, and use attention network to select important words. In the user encoder, we propose to learn long-term user representations from the embeddings of their IDs.In addition, we propose to learn short-term user representations from their recently browsed news via GRU network. Besides, we propose two methods to combine long-term and short-term user representations. The first one is using the long-term user representation to initialize the hidden state of the GRU network in short-term user representation. The second one is concatenating both long- and short-term user representations as a unified user vector. Extensive experiments on a real-world dataset show our approach can effectively improve the performance of neural news recommendation. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1033/ |
| https://www.aclweb.org/anthology/P19-1033 | |
| PWC | https://paperswithcode.com/paper/neural-news-recommendation-with-long-and |
| Repo | |
| Framework | |
Making Sense of Conflicting (Defeasible) Rules in the Controlled Natural Language ACE: Design of a System with Support for Existential Quantification Using Skolemization
| Title | Making Sense of Conflicting (Defeasible) Rules in the Controlled Natural Language ACE: Design of a System with Support for Existential Quantification Using Skolemization |
| Authors | Martin Diller, Adam Wyner, Hannes Strass |
| Abstract | We present the design of a system for making sense of conflicting rules expressed in a fragment of the prominent controlled natural language ACE, yet extended with means of expressing defeasible rules in the form of normality assumptions. The approach we describe is ultimately based on answer-set-programming (ASP); simulating existential quantification by using skolemization in a manner resembling a translation for ASP recently formalized in the context of ∃-ASP. We discuss the advantages of this approach to building on the existing ACE interface to rule-systems, ACERules. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0505/ |
| https://www.aclweb.org/anthology/W19-0505 | |
| PWC | https://paperswithcode.com/paper/making-sense-of-conflicting-defeasible-rules |
| Repo | |
| Framework | |
Annotation and Automatic Classification of Aspectual Categories
| Title | Annotation and Automatic Classification of Aspectual Categories |
| Authors | Markus Egg, Helena Prepens, Will Roberts |
| Abstract | We present the first annotated resource for the aspectual classification of German verb tokens in their clausal context. We use aspectual features compatible with the plurality of aspectual classifications in previous work and treat aspectual ambiguity systematically. We evaluate our corpus by using it to train supervised classifiers to automatically assign aspectual categories to verbs in context, permitting favourable comparisons to previous work. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1323/ |
| https://www.aclweb.org/anthology/P19-1323 | |
| PWC | https://paperswithcode.com/paper/annotation-and-automatic-classification-of |
| Repo | |
| Framework | |
Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection
| Title | Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection |
| Authors | Amit Moryossef, Roee Aharoni, Yoav Goldberg |
| Abstract | When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must {``}guess{''} this missing information, often leading to incorrect translations in the given context. We propose a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. We evaluate our method on an English to Hebrew translation task, and show that it is effective in injecting the gender and number information and that supplying the correct information improves the translation accuracy in up to 2.3 BLEU on a female-speaker test set for a state-of-the-art online black-box system. Finally, we perform a fine-grained syntactic analysis of the generated translations that shows the effectiveness of our method. | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3807/ |
| https://www.aclweb.org/anthology/W19-3807 | |
| PWC | https://paperswithcode.com/paper/filling-gender-number-gaps-in-neural-machine-1 |
| Repo | |
| Framework | |
English-Indonesian Neural Machine Translation for Spoken Language Domains
| Title | English-Indonesian Neural Machine Translation for Spoken Language Domains |
| Authors | Meisyarah Dwiastuti |
| Abstract | In this work, we conduct a study on Neural Machine Translation (NMT) for English-Indonesian (EN-ID) and Indonesian-English (ID-EN). We focus on spoken language domains, namely colloquial and speech languages. We build NMT systems using the Transformer model for both translation directions and implement domain adaptation, in which we train our pre-trained NMT systems on speech language (in-domain) data. Moreover, we conduct an evaluation on how the domain-adaptation method in our EN-ID system can result in more formal translation outputs. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2043/ |
| https://www.aclweb.org/anthology/P19-2043 | |
| PWC | https://paperswithcode.com/paper/english-indonesian-neural-machine-translation |
| Repo | |
| Framework | |
Knowledge Discovery and Hypothesis Generation from Online Patient Forums: A Research Proposal
| Title | Knowledge Discovery and Hypothesis Generation from Online Patient Forums: A Research Proposal |
| Authors | Anne Dirkson |
| Abstract | The unprompted patient experiences shared on patient forums contain a wealth of unexploited knowledge. Mining this knowledge and cross-linking it with biomedical literature, could expose novel insights, which could subsequently provide hypotheses for further clinical research. As of yet, automated methods for open knowledge discovery on patient forum text are lacking. Thus, in this research proposal, we outline future research into methods for mining, aggregating and cross-linking patient knowledge from online forums. Additionally, we aim to address how one could measure the credibility of this extracted knowledge. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2009/ |
| https://www.aclweb.org/anthology/P19-2009 | |
| PWC | https://paperswithcode.com/paper/knowledge-discovery-and-hypothesis-generation |
| Repo | |
| Framework | |
Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining
| Title | Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining |
| Authors | Xiaoman Pan, Thamme Gowda, Heng Ji, Jonathan May, Scott Miller |
| Abstract | Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages. We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia. We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise. A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities. Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking. Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1{%} absolute F-score gain for unsupervised cross-lingual entity linking. Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all (302, 2) language pairs in Wikipedia. |
| Tasks | Cross-Lingual Entity Linking, Entity Linking |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6107/ |
| https://www.aclweb.org/anthology/D19-6107 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-joint-entity-and-word-embedding |
| Repo | |
| Framework | |
Speaker-adapted neural-network-based fusion for multimodal reference resolution
| Title | Speaker-adapted neural-network-based fusion for multimodal reference resolution |
| Authors | Diana Kleingarn, Nima Nabizadeh, Martin Heckmann, Dorothea Kolossa |
| Abstract | Humans use a variety of approaches to reference objects in the external world, including verbal descriptions, hand and head gestures, eye gaze or any combination of them. The amount of useful information from each modality, however, may vary depending on the specific person and on several other factors. For this reason, it is important to learn the correct combination of inputs for inferring the best-fitting reference. In this paper, we investigate appropriate speaker-dependent and independent fusion strategies in a multimodal reference resolution task. We show that without any change in the modality models, only through an optimized fusion technique, it is possible to reduce the error rate of the system on a reference resolution task by more than 50{%}. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5925/ |
| https://www.aclweb.org/anthology/W19-5925 | |
| PWC | https://paperswithcode.com/paper/speaker-adapted-neural-network-based-fusion |
| Repo | |
| Framework | |
Honkling: In-Browser Personalization for Ubiquitous Keyword Spotting
| Title | Honkling: In-Browser Personalization for Ubiquitous Keyword Spotting |
| Authors | Jaejun Lee, Raphael Tang, Jimmy Lin |
| Abstract | Used for simple commands recognition on devices from smart speakers to mobile phones, keyword spotting systems are everywhere. Ubiquitous as well are web applications, which have grown in popularity and complexity over the last decade. However, despite their obvious advantages in natural language interaction, voice-enabled web applications are still few and far between. We attempt to bridge this gap with Honkling, a novel, JavaScript-based keyword spotting system. Purely client-side and cross-device compatible, Honkling can be deployed directly on user devices. Our in-browser implementation enables seamless personalization, which can greatly improve model quality; in the presence of underrepresented, non-American user accents, we can achieve up to an absolute 10{%} increase in accuracy in the personalized model with only a few examples. |
| Tasks | Keyword Spotting |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3016/ |
| https://www.aclweb.org/anthology/D19-3016 | |
| PWC | https://paperswithcode.com/paper/honkling-in-browser-personalization-for |
| Repo | |
| Framework | |
