目录
2. Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks [PDF] 摘要
摘要
1. Know thy corpus! Robust methods for digital curation of Web corpora [PDF] 返回目录
Serge Sharoff
Abstract: This paper proposes a novel framework for digital curation of Web corpora in order to provide robust estimation of their parameters, such as their composition and the lexicon. In recent years language models pre-trained on large corpora emerged as clear winners in numerous NLP tasks, but no proper analysis of the corpora which led to their success has been conducted. The paper presents a procedure for robust frequency estimation, which helps in establishing the core lexicon for a given corpus, as well as a procedure for estimating the corpus composition via unsupervised topic models and via supervised genre classification of Web pages. The results of the digital curation study applied to several Web-derived corpora demonstrate their considerable differences. First, this concerns different frequency bursts which impact the core lexicon obtained from each corpus. Second, this concerns the kinds of texts they contain. For example, OpenWebText contains considerably more topical news and political argumentation in comparison to ukWac or Wikipedia. The tools and the results of analysis have been released.
摘要：本文提出，以提供它们的参数，的稳健估计如它们的组成和词汇为Web语料库的数字策一种新颖的框架。近年来语言模型预先训练大语料库成为众多NLP任务明显的赢家，但导致他们成功的语料中没有适当的分析已经进行。本文提出了稳健的频率估计的过程，这有助于建立核心词汇对于给定的语料库，以及为通过无监督的主题模型，并通过网页的监督流派分类估计语料库组成的过程。适用于多个Web衍生语料库数字策展研究的结果表明其相当大的差异。第一，它的影响从每个语料库中得到的核心词汇此顾虑不同的频率脉冲串。其次，这涉及各种文本所包含。例如，OpenWebText包含相较于ukWac或维基百科相当多的花边新闻和政治论证。工具和分析的结果已经出炉。
Serge Sharoff
Abstract: This paper proposes a novel framework for digital curation of Web corpora in order to provide robust estimation of their parameters, such as their composition and the lexicon. In recent years language models pre-trained on large corpora emerged as clear winners in numerous NLP tasks, but no proper analysis of the corpora which led to their success has been conducted. The paper presents a procedure for robust frequency estimation, which helps in establishing the core lexicon for a given corpus, as well as a procedure for estimating the corpus composition via unsupervised topic models and via supervised genre classification of Web pages. The results of the digital curation study applied to several Web-derived corpora demonstrate their considerable differences. First, this concerns different frequency bursts which impact the core lexicon obtained from each corpus. Second, this concerns the kinds of texts they contain. For example, OpenWebText contains considerably more topical news and political argumentation in comparison to ukWac or Wikipedia. The tools and the results of analysis have been released.
摘要：本文提出，以提供它们的参数，的稳健估计如它们的组成和词汇为Web语料库的数字策一种新颖的框架。近年来语言模型预先训练大语料库成为众多NLP任务明显的赢家，但导致他们成功的语料中没有适当的分析已经进行。本文提出了稳健的频率估计的过程，这有助于建立核心词汇对于给定的语料库，以及为通过无监督的主题模型，并通过网页的监督流派分类估计语料库组成的过程。适用于多个Web衍生语料库数字策展研究的结果表明其相当大的差异。第一，它的影响从每个语料库中得到的核心词汇此顾虑不同的频率脉冲串。其次，这涉及各种文本所包含。例如，OpenWebText包含相较于ukWac或维基百科相当多的花边新闻和政治论证。工具和分析的结果已经出炉。
2. Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks [PDF] 返回目录
Yu Yuan, Serge Sharoff
Abstract: This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods for solving this task rely on manually engineered features and external knowledge. This paper presents an end-to-end neural model without feature engineering, incorporating a cross attention mechanism to detect which parts in sentence pairs are most relevant for assessing quality. Another contribution concerns of prediction of fine-grained scores for measuring different aspects of translation quality. Empirical results on a large human annotated dataset show that the neural model outperforms feature-based methods significantly. The dataset and the tools are available.
摘要：本文探讨了人的翻译质量自动评估采用深度学习方法。自动估计可以提供翻译教学，考试和质量控制有用的反馈。为解决这个任务的传统方法依赖于手工设计特征和外部知识。本文没有呈现的特征工程结束到终端的神经网络模型，合并交叉注意机制来检测这句话对部分是最相关的评估质量。细粒度的分数预测的另一个贡献担忧衡量翻译质量的不同方面。在一个大的人类注释的数据集显示，神经模型优于实证结果基于特征的方法显著。该数据集和工具可用。
Yu Yuan, Serge Sharoff
Abstract: This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods for solving this task rely on manually engineered features and external knowledge. This paper presents an end-to-end neural model without feature engineering, incorporating a cross attention mechanism to detect which parts in sentence pairs are most relevant for assessing quality. Another contribution concerns of prediction of fine-grained scores for measuring different aspects of translation quality. Empirical results on a large human annotated dataset show that the neural model outperforms feature-based methods significantly. The dataset and the tools are available.
摘要：本文探讨了人的翻译质量自动评估采用深度学习方法。自动估计可以提供翻译教学，考试和质量控制有用的反馈。为解决这个任务的传统方法依赖于手工设计特征和外部知识。本文没有呈现的特征工程结束到终端的神经网络模型，合并交叉注意机制来检测这句话对部分是最相关的评估质量。细粒度的分数预测的另一个贡献担忧衡量翻译质量的不同方面。在一个大的人类注释的数据集显示，神经模型优于实证结果基于特征的方法显著。该数据集和工具可用。
3. Using word embeddings to improve the discriminability of co-occurrence text networks [PDF] 返回目录
Laura V. C. Quispe, Jorge A. V. Tohalino, Diego R. Amancio
Abstract: Word co-occurrence networks have been employed to analyze texts both in the practical and theoretical scenarios. Despite the relative success in several applications, traditional co-occurrence networks fail in establishing links between similar words whenever they appear distant in the text. Here we investigate whether the use of word embeddings as a tool to create virtual links in co-occurrence networks may improve the quality of classification systems. Our results revealed that the discriminability in the stylometry task is improved when using Glove, Word2Vec and FastText. In addition, we found that optimized results are obtained when stopwords are not disregarded and a simple global thresholding strategy is used to establish virtual links. Because the proposed approach is able to improve the representation of texts as complex networks, we believe that it could be extended to study other natural language processing tasks. Likewise, theoretical languages studies could benefit from the adopted enriched representation of word co-occurrence networks.
摘要：字同现网络已被用来分析文本无论是在理论和实践的情况。尽管在一些应用中的相对成功，传统的共生网络无法建立时，他们出现在遥远的文本相似的词之间的联系。在这里，我们调查使用的嵌入一词作为工具是否创造共生网络的虚拟链路可以提高分类系统的质量。我们的研究结果表明，在stylometry任务量的辨别使用手套，Word2Vec和FastText时提高。此外，我们发现，当停用词不忽略，一个简单的全局阈值策略来建立虚拟链路优化的结果获得。由于该方法能够提高文本的复杂网络的表现，我们认为，它可以扩大到研究其他自然语言处理任务。同样，理论研究，语言可能受益于字共现网络的采用丰富的表示。
Laura V. C. Quispe, Jorge A. V. Tohalino, Diego R. Amancio
Abstract: Word co-occurrence networks have been employed to analyze texts both in the practical and theoretical scenarios. Despite the relative success in several applications, traditional co-occurrence networks fail in establishing links between similar words whenever they appear distant in the text. Here we investigate whether the use of word embeddings as a tool to create virtual links in co-occurrence networks may improve the quality of classification systems. Our results revealed that the discriminability in the stylometry task is improved when using Glove, Word2Vec and FastText. In addition, we found that optimized results are obtained when stopwords are not disregarded and a simple global thresholding strategy is used to establish virtual links. Because the proposed approach is able to improve the representation of texts as complex networks, we believe that it could be extended to study other natural language processing tasks. Likewise, theoretical languages studies could benefit from the adopted enriched representation of word co-occurrence networks.
摘要：字同现网络已被用来分析文本无论是在理论和实践的情况。尽管在一些应用中的相对成功，传统的共生网络无法建立时，他们出现在遥远的文本相似的词之间的联系。在这里，我们调查使用的嵌入一词作为工具是否创造共生网络的虚拟链路可以提高分类系统的质量。我们的研究结果表明，在stylometry任务量的辨别使用手套，Word2Vec和FastText时提高。此外，我们发现，当停用词不忽略，一个简单的全局阈值策略来建立虚拟链路优化的结果获得。由于该方法能够提高文本的复杂网络的表现，我们认为，它可以扩大到研究其他自然语言处理任务。同样，理论研究，语言可能受益于字共现网络的采用丰富的表示。
4. Review-guided Helpful Answer Identification in E-commerce [PDF] 返回目录
Wenxuan Zhang, Wai Lam, Yang Deng, Jing Ma
Abstract: Product-specific community question answering platforms can greatly help address the concerns of potential customers. However, the user-provided answers on such platforms often vary a lot in their qualities. Helpfulness votes from the community can indicate the overall quality of the answer, but they are often missing. Accurately predicting the helpfulness of an answer to a given question and thus identifying helpful answers is becoming a demanding need. Since the helpfulness of an answer depends on multiple perspectives instead of only topical relevance investigated in typical QA tasks, common answer selection algorithms are insufficient for tackling this task. In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers. Moreover, we tackle the task of determining opinion coherence as a language inference problem and explore the utilization of pre-training strategy to transfer the textual inference knowledge obtained from a specifically designed trained network. Extensive experiments conducted on real-world data across seven product categories show that our proposed model achieves superior performance on the prediction task.
摘要：针对特定产品的社区问答平台，可以极大地帮助处理潜在客户的顾虑。然而，在这样的平台用户提供的答案往往有很大的差异在他们的素质。从社区助人为乐票可以指示答案的整体质量，但他们往往缺少。准确地预测一个答案给定问题的乐于助人，从而识别有用的答案正在成为一个苛刻的需求。由于答案乐于助人取决于多种观点，而不是只在典型的QA任务研究主题相关，常见的答案选择算法是不足以解决这一任务。在本文中，我们提出了审查制导答案乐于助人预测（RAHP）模型，该模型不仅考虑QA对之间的相互作用，还调查了答案和群众的意见反映在审查，这是另一个重要因素之间的意见一致识别有用的答案。此外，我们将处理决定意见一致的语言推理问题的任务，并探索前培训战略的利用率传送从专门训练的网络中获得的文本推理知识。对在七个产品类别的真实数据进行了大量的实验表明，该模型实现了对预测任务性能优越。
Wenxuan Zhang, Wai Lam, Yang Deng, Jing Ma
Abstract: Product-specific community question answering platforms can greatly help address the concerns of potential customers. However, the user-provided answers on such platforms often vary a lot in their qualities. Helpfulness votes from the community can indicate the overall quality of the answer, but they are often missing. Accurately predicting the helpfulness of an answer to a given question and thus identifying helpful answers is becoming a demanding need. Since the helpfulness of an answer depends on multiple perspectives instead of only topical relevance investigated in typical QA tasks, common answer selection algorithms are insufficient for tackling this task. In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers. Moreover, we tackle the task of determining opinion coherence as a language inference problem and explore the utilization of pre-training strategy to transfer the textual inference knowledge obtained from a specifically designed trained network. Extensive experiments conducted on real-world data across seven product categories show that our proposed model achieves superior performance on the prediction task.
摘要：针对特定产品的社区问答平台，可以极大地帮助处理潜在客户的顾虑。然而，在这样的平台用户提供的答案往往有很大的差异在他们的素质。从社区助人为乐票可以指示答案的整体质量，但他们往往缺少。准确地预测一个答案给定问题的乐于助人，从而识别有用的答案正在成为一个苛刻的需求。由于答案乐于助人取决于多种观点，而不是只在典型的QA任务研究主题相关，常见的答案选择算法是不足以解决这一任务。在本文中，我们提出了审查制导答案乐于助人预测（RAHP）模型，该模型不仅考虑QA对之间的相互作用，还调查了答案和群众的意见反映在审查，这是另一个重要因素之间的意见一致识别有用的答案。此外，我们将处理决定意见一致的语言推理问题的任务，并探索前培训战略的利用率传送从专门训练的网络中获得的文本推理知识。对在七个产品类别的真实数据进行了大量的实验表明，该模型实现了对预测任务性能优越。
5. WAC: A Corpus of Wikipedia Conversations for Online Abuse Detection [PDF] 返回目录
Noé Cecillon, Vincent Labatut, Richard Dufour, Georges Linares
Abstract: With the spread of online social networks, it is more and more difficult to monitor all the user-generated content. Automating the moderation process of the inappropriate exchange content on Internet has thus become a priority task. Methods have been proposed for this purpose, but it can be challenging to find a suitable dataset to train and develop them. This issue is especially true for approaches based on information derived from the structure and the dynamic of the conversation. In this work, we propose an original framework, based on the Wikipedia Comment corpus, with comment-level abuse annotations of different types. The major contribution concerns the reconstruction of conversations, by comparison to existing corpora, which focus only on isolated messages (i.e. taken out of their conversational context). This large corpus of more than 380k annotated messages opens perspectives for online abuse detection and especially for context-based approaches. We also propose, in addition to this corpus, a complete benchmarking platform to stimulate and fairly compare scientific works around the problem of content abuse detection, trying to avoid the recurring problem of result replication. Finally, we apply two classification methods to our dataset to demonstrate its potential.
摘要：随着在线社交网络的普及，它越来越难以监控所有用户生成的内容。因此，自动化互联网上的交流不当内容的审核流程已成为当务之急。方法已经被提出用于此目的，但它可以挑战找到合适的数据集，以培养和发展他们。这个问题是基于从结构和对话的动态获取的信息的方法，尤其如此。在这项工作中，我们提出了一个原始框架的基础上，维基百科的评论文集，与不同类型的评论级滥用注解。的主要贡献的担忧会话的重建，通过比较现有语料库，其只注重分离消息（即取出他们的会话上下文）。这个大超过380K注释信息的胼打开网上滥用检测，尤其是对基于上下文的方法的观点。我们还建议，除了这个语料库，一个完整的基准平台，以促进公平和比较各地的内容滥用检测的问题的科学著作，试图避免的结果复制的经常性问题。最后，我们采用两种分类方法对我们的数据来证明它的潜力。
Noé Cecillon, Vincent Labatut, Richard Dufour, Georges Linares
Abstract: With the spread of online social networks, it is more and more difficult to monitor all the user-generated content. Automating the moderation process of the inappropriate exchange content on Internet has thus become a priority task. Methods have been proposed for this purpose, but it can be challenging to find a suitable dataset to train and develop them. This issue is especially true for approaches based on information derived from the structure and the dynamic of the conversation. In this work, we propose an original framework, based on the Wikipedia Comment corpus, with comment-level abuse annotations of different types. The major contribution concerns the reconstruction of conversations, by comparison to existing corpora, which focus only on isolated messages (i.e. taken out of their conversational context). This large corpus of more than 380k annotated messages opens perspectives for online abuse detection and especially for context-based approaches. We also propose, in addition to this corpus, a complete benchmarking platform to stimulate and fairly compare scientific works around the problem of content abuse detection, trying to avoid the recurring problem of result replication. Finally, we apply two classification methods to our dataset to demonstrate its potential.
摘要：随着在线社交网络的普及，它越来越难以监控所有用户生成的内容。因此，自动化互联网上的交流不当内容的审核流程已成为当务之急。方法已经被提出用于此目的，但它可以挑战找到合适的数据集，以培养和发展他们。这个问题是基于从结构和对话的动态获取的信息的方法，尤其如此。在这项工作中，我们提出了一个原始框架的基础上，维基百科的评论文集，与不同类型的评论级滥用注解。的主要贡献的担忧会话的重建，通过比较现有语料库，其只注重分离消息（即取出他们的会话上下文）。这个大超过380K注释信息的胼打开网上滥用检测，尤其是对基于上下文的方法的观点。我们还建议，除了这个语料库，一个完整的基准平台，以促进公平和比较各地的内容滥用检测的问题的科学著作，试图避免的结果复制的经常性问题。最后，我们采用两种分类方法对我们的数据来证明它的潜力。
6. MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space [PDF] 返回目录
Xiaoyuan Yi, Ruoyu Li, Cheng Yang, Wenhao Li, Maosong Sun
Abstract: As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity. Related literature researches show that different factors, such as life experience, historical background, etc., would influence composition styles of poets, which considerably contributes to the high diversity of human-authored poetry. Inspired by this, we propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity. Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training. In this way, the model learns a controllable latent variable to capture and mix generalized factor-related properties. Different factor mixtures lead to diverse styles and hence further differentiate generated poems from each other. Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models.
摘要：随着对计算机创造力的一个重要步骤，自动生成的诗歌得到了越来越多的关注，这些年。尽管最近的神经模式使诗歌质量的一些标准，突出的进步，产生的诗仍然遭受多样性差的问题。相关文献研究表明，不同的因素，如生活经验，历史背景等，将影响组合风格的诗人，这大大有助于提高人的创作诗歌的高度多样性。受此启发，我们提出MixPoet，吸收多种因素来创造各种风格和促进多样化的新颖模式。基于半监督变自动编码器，我们的模型理顺了那些纷繁的潜在空间为若干子空间，每个由对抗性训练一个影响因素制约。通过这种方式，模型学习可控潜变量，以捕捉和混合广义的因素相关的属性。不同因子的混合物导致不同的样式和从彼此因此进一步分化产生诗。对中国诗歌实验结果表明，MixPoet改善了多样性和质量对三名国家的最先进的车型。
Xiaoyuan Yi, Ruoyu Li, Cheng Yang, Wenhao Li, Maosong Sun
Abstract: As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity. Related literature researches show that different factors, such as life experience, historical background, etc., would influence composition styles of poets, which considerably contributes to the high diversity of human-authored poetry. Inspired by this, we propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity. Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training. In this way, the model learns a controllable latent variable to capture and mix generalized factor-related properties. Different factor mixtures lead to diverse styles and hence further differentiate generated poems from each other. Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models.
摘要：随着对计算机创造力的一个重要步骤，自动生成的诗歌得到了越来越多的关注，这些年。尽管最近的神经模式使诗歌质量的一些标准，突出的进步，产生的诗仍然遭受多样性差的问题。相关文献研究表明，不同的因素，如生活经验，历史背景等，将影响组合风格的诗人，这大大有助于提高人的创作诗歌的高度多样性。受此启发，我们提出MixPoet，吸收多种因素来创造各种风格和促进多样化的新颖模式。基于半监督变自动编码器，我们的模型理顺了那些纷繁的潜在空间为若干子空间，每个由对抗性训练一个影响因素制约。通过这种方式，模型学习可控潜变量，以捕捉和混合广义的因素相关的属性。不同因子的混合物导致不同的样式和从彼此因此进一步分化产生诗。对中国诗歌实验结果表明，MixPoet改善了多样性和质量对三名国家的最先进的车型。
7. Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition [PDF] 返回目录
Zhigang Dai, Jinhua Fu, Qile Zhu, Hengbin Cui, Xiaolong li, Yuan Qi
Abstract: Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical model based on self-attention to capture intra-sentence and inter-sentence information. We revise the attention distribution to focus on the local and contextual semantic information by incorporating the relative position information between utterances. Based on the found that the length of dialog affects the performance, we introduce a new dialog segmentation mechanism to analyze the effect of dialog length and context padding length under online and offline settings. The experiment shows that our method achieves promising performance on two datasets: Switchboard Dialogue Act and DailyDialog with the accuracy of 80.34\% and 85.81\% respectively. Visualization of the attention weights shows that our method can learn the context dependency between utterances explicitly.
摘要：对话行为识别是智能对话系统的基本任务。以往的工作模式在整个对话来预测对话的行为，可以从句子无关带来的噪音。在这项工作中，我们设计了一种基于自我注意捕捉内部句子和句子间信息的分层模型。我们修改注意分配通过将话语之间的相对位置信息，以专注于本地和上下文语义信息。基于该发现，对话的长度会影响性能，我们引入一个新的对话框分段机制来分析对话框长度和背景填充长度的下线上和线下设置的效果。实验表明，我们的方法实现对两个数据集有前途的性能：总机对话行为和DailyDialog与80.34 \％和85.81 \％分别准确性。注意权重表明，我们的方法可以学习话语之间的上下文相关性明确的可视化。
Zhigang Dai, Jinhua Fu, Qile Zhu, Hengbin Cui, Xiaolong li, Yuan Qi
Abstract: Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical model based on self-attention to capture intra-sentence and inter-sentence information. We revise the attention distribution to focus on the local and contextual semantic information by incorporating the relative position information between utterances. Based on the found that the length of dialog affects the performance, we introduce a new dialog segmentation mechanism to analyze the effect of dialog length and context padding length under online and offline settings. The experiment shows that our method achieves promising performance on two datasets: Switchboard Dialogue Act and DailyDialog with the accuracy of 80.34\% and 85.81\% respectively. Visualization of the attention weights shows that our method can learn the context dependency between utterances explicitly.
摘要：对话行为识别是智能对话系统的基本任务。以往的工作模式在整个对话来预测对话的行为，可以从句子无关带来的噪音。在这项工作中，我们设计了一种基于自我注意捕捉内部句子和句子间信息的分层模型。我们修改注意分配通过将话语之间的相对位置信息，以专注于本地和上下文语义信息。基于该发现，对话的长度会影响性能，我们引入一个新的对话框分段机制来分析对话框长度和背景填充长度的下线上和线下设置的效果。实验表明，我们的方法实现对两个数据集有前途的性能：总机对话行为和DailyDialog与80.34 \％和85.81 \％分别准确性。注意权重表明，我们的方法可以学习话语之间的上下文相关性明确的可视化。
8. Efficient Rule Learning with Template Saturation for Knowledge Graph Completion [PDF] 返回目录
Yulong Gu, Yu Guan, Paolo Missier
Abstract: The logic-based methods that learn first-order rules from knowledge graphs (KGs) for knowledge graph completion (KGC) task are desirable in that the learnt models are inductive, interpretable and transferable. The challenge in such rule learners is that the expressive rules are often buried in vast rule space, and the procedure of identifying expressive rules by measuring rule quality is costly to execute. Therefore, optimizations on rule generation and evaluation are in need. In this work, we propose a novel bottom-up probabilistic rule learner that features: 1.) a two-stage procedure for optimized rule generation where the system first generalizes paths sampled from a KG into template rules that contain no constants until a certain degree of template saturation is achieved and then specializes template rules into instantiated rules that contain constants; 2.) a grouping technique for optimized rule evaluation where structurally similar instantiated rules derived from the same template rules are put into the same groups and evaluated collectively over the groundings of the deriving template rules. Through extensive experiments over large benchmark datasets on KGC task, our algorithm demonstrates consistent and substantial performance improvements over all of the state-of-the-art baselines.
摘要：基于逻辑的方法是从学习知识图（KGS）知识图完成一阶规则（KGC）的任务是在学习模式是感性的，可解释的，可转让的合意。在这样的规则的学习者所面临的挑战是，表现规则通常埋在广阔的规则空间，并通过测量规则识别质量表现规则的过程是昂贵的执行。因此，规则生成和评估优化是需要的。在这项工作中，我们提出了一种新颖的自底向上的概率规则学习者，具有：1。）一个两阶段过程优化规则产生其中系统第一概括路径从KG采样成不包含常数直到一定程度的模板规则模板饱和的实现，然后专门模板规则到包含常数实例化规则; 2.），用于优化规则评估一个分组技术，其中从相同的模板规则衍生结构上相似的实例化规则被超过的模板导出规则的搁浅投入相同的基团和评价的统称。通过以上对KGC任务大标准数据集大量的实验，我们的算法表明在所有国家的最先进的基线一致和显着的性能改进。
Yulong Gu, Yu Guan, Paolo Missier
Abstract: The logic-based methods that learn first-order rules from knowledge graphs (KGs) for knowledge graph completion (KGC) task are desirable in that the learnt models are inductive, interpretable and transferable. The challenge in such rule learners is that the expressive rules are often buried in vast rule space, and the procedure of identifying expressive rules by measuring rule quality is costly to execute. Therefore, optimizations on rule generation and evaluation are in need. In this work, we propose a novel bottom-up probabilistic rule learner that features: 1.) a two-stage procedure for optimized rule generation where the system first generalizes paths sampled from a KG into template rules that contain no constants until a certain degree of template saturation is achieved and then specializes template rules into instantiated rules that contain constants; 2.) a grouping technique for optimized rule evaluation where structurally similar instantiated rules derived from the same template rules are put into the same groups and evaluated collectively over the groundings of the deriving template rules. Through extensive experiments over large benchmark datasets on KGC task, our algorithm demonstrates consistent and substantial performance improvements over all of the state-of-the-art baselines.
摘要：基于逻辑的方法是从学习知识图（KGS）知识图完成一阶规则（KGC）的任务是在学习模式是感性的，可解释的，可转让的合意。在这样的规则的学习者所面临的挑战是，表现规则通常埋在广阔的规则空间，并通过测量规则识别质量表现规则的过程是昂贵的执行。因此，规则生成和评估优化是需要的。在这项工作中，我们提出了一种新颖的自底向上的概率规则学习者，具有：1。）一个两阶段过程优化规则产生其中系统第一概括路径从KG采样成不包含常数直到一定程度的模板规则模板饱和的实现，然后专门模板规则到包含常数实例化规则; 2.），用于优化规则评估一个分组技术，其中从相同的模板规则衍生结构上相似的实例化规则被超过的模板导出规则的搁浅投入相同的基团和评价的统称。通过以上对KGC任务大标准数据集大量的实验，我们的算法表明在所有国家的最先进的基线一致和显着的性能改进。
9. Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning [PDF] 返回目录
Mandana Saebi, Steven Krieg, Chuxu Zhang, Meng Jiang, Nitesh Chawla
Abstract: Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems. In recent years, reinforcement learning (RL) has provided solutions that are more interpretable and explainable than other deep learning models. However, these solutions still face several challenges, including large action space for the RL agent and accurate representation of entity neighborhood structure. We address these problems by introducing a type-enhanced RL agent that uses the local neighborhood information for efficient path-based reasoning over knowledge graphs. Our solution uses graph neural network (GNN) for encoding the neighborhood information and utilizes entity types to prune the action space. Experiments on real-world dataset show that our method outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure.
摘要：在知识图基于路径的关系推理，已成为各种下游应用，如对话系统问题解答，其实预测和推荐系统越来越受欢迎所致。近年来，强化学习（RL）已经提供了更可解释比其他深学习模型解释的解决方案。然而，这些解决方案仍然面临一些挑战，包括为RL代理大动作空间和实体邻域结构的准确表示。我们解决通过引入用来对知识图表高效的基于路径的推理当地居委会信息的类型增强RL代理这些问题。我们的解决方案使用图表用于编码相邻信息，并利用实体类型修剪动作空间神经网络（GNN）。现实世界的数据集的实验表明我们的方法优于在训练过程中，国家的最先进的RL方法，并发现更多的新路径。
Mandana Saebi, Steven Krieg, Chuxu Zhang, Meng Jiang, Nitesh Chawla
Abstract: Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems. In recent years, reinforcement learning (RL) has provided solutions that are more interpretable and explainable than other deep learning models. However, these solutions still face several challenges, including large action space for the RL agent and accurate representation of entity neighborhood structure. We address these problems by introducing a type-enhanced RL agent that uses the local neighborhood information for efficient path-based reasoning over knowledge graphs. Our solution uses graph neural network (GNN) for encoding the neighborhood information and utilizes entity types to prune the action space. Experiments on real-world dataset show that our method outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure.
摘要：在知识图基于路径的关系推理，已成为各种下游应用，如对话系统问题解答，其实预测和推荐系统越来越受欢迎所致。近年来，强化学习（RL）已经提供了更可解释比其他深学习模型解释的解决方案。然而，这些解决方案仍然面临一些挑战，包括为RL代理大动作空间和实体邻域结构的准确表示。我们解决通过引入用来对知识图表高效的基于路径的推理当地居委会信息的类型增强RL代理这些问题。我们的解决方案使用图表用于编码相邻信息，并利用实体类型修剪动作空间神经网络（GNN）。现实世界的数据集的实验表明我们的方法优于在训练过程中，国家的最先进的RL方法，并发现更多的新路径。
10. CRWIZ: A Framework for Crowdsourcing Real-Time Wizard-of-Oz Dialogues [PDF] 返回目录
Francisco J. Chiyah Garcia, José Lopes, Xingkun Liu, Helen Hastie
Abstract: Large corpora of task-based and open-domain conversational dialogues are hugely valuable in the field of data-driven dialogue systems. Crowdsourcing platforms, such as Amazon Mechanical Turk, have been an effective method for collecting such large amounts of data. However, difficulties arise when task-based dialogues require expert domain knowledge or rapid access to domain-relevant information, such as databases for tourism. This will become even more prevalent as dialogue systems become increasingly ambitious, expanding into tasks with high levels of complexity that require collaboration and forward planning, such as in our domain of emergency response. In this paper, we propose CRWIZ: a framework for collecting real-time Wizard of Oz dialogues through crowdsourcing for collaborative, complex tasks. This framework uses semi-guided dialogue to avoid interactions that breach procedures and processes only known to experts, while enabling the capture of a wide variety of interactions. The framework is available at this https URL
摘要：基于任务和开放领域对话对话大语料库在数据驱动的对话系统领域的巨大价值。众包平台，如亚马逊土耳其机器人，已经用于收集如此大量的数据的有效方法。然而，当基于任务的对话需要专业领域的知识或快速访问域相关的信息，如旅游数据库出现困难。这将变得更加普遍的对话系统变得越来越野心勃勃，扩大到具有高层次的复杂性需要协作和前瞻性的规划，比如在我们的应急领域的任务。在本文中，我们提出CRWIZ：通过众包协同，复杂的任务，收集奥兹对话的实时向导的框架。该框架使用，以避免相互作用半导对话违反程序和流程只知道专家，同时实现各种各样的相互作用的捕获。该框架可在此HTTPS URL
Francisco J. Chiyah Garcia, José Lopes, Xingkun Liu, Helen Hastie
Abstract: Large corpora of task-based and open-domain conversational dialogues are hugely valuable in the field of data-driven dialogue systems. Crowdsourcing platforms, such as Amazon Mechanical Turk, have been an effective method for collecting such large amounts of data. However, difficulties arise when task-based dialogues require expert domain knowledge or rapid access to domain-relevant information, such as databases for tourism. This will become even more prevalent as dialogue systems become increasingly ambitious, expanding into tasks with high levels of complexity that require collaboration and forward planning, such as in our domain of emergency response. In this paper, we propose CRWIZ: a framework for collecting real-time Wizard of Oz dialogues through crowdsourcing for collaborative, complex tasks. This framework uses semi-guided dialogue to avoid interactions that breach procedures and processes only known to experts, while enabling the capture of a wide variety of interactions. The framework is available at this https URL
摘要：基于任务和开放领域对话对话大语料库在数据驱动的对话系统领域的巨大价值。众包平台，如亚马逊土耳其机器人，已经用于收集如此大量的数据的有效方法。然而，当基于任务的对话需要专业领域的知识或快速访问域相关的信息，如旅游数据库出现困难。这将变得更加普遍的对话系统变得越来越野心勃勃，扩大到具有高层次的复杂性需要协作和前瞻性的规划，比如在我们的应急领域的任务。在本文中，我们提出CRWIZ：通过众包协同，复杂的任务，收集奥兹对话的实时向导的框架。该框架使用，以避免相互作用半导对话违反程序和流程只知道专家，同时实现各种各样的相互作用的捕获。该框架可在此HTTPS URL
注：中文为机器翻译结果！