目录
2. An efficient automated data analytics approach to large scale computational comparative linguistics [PDF] 摘要
8. Augmenting Visual Question Answering with Semantic Frame Information in a Multitask Learning Approach [PDF] 摘要
10. Unwanted Advances in Higher Education: Uncovering Sexual Harassment Experiences in Academia with Text Mining [PDF] 摘要
摘要
1. Pretrained Transformers for Simple Question Answering over Knowledge Graphs [PDF] 返回目录
D. Lukovnikov, A. Fischer, J. Lehmann
Abstract: Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings. It was recently shown that finetuning pretrained transformer networks (e.g. BERT) can outperform previous approaches on various natural language processing tasks. In this work, we investigate how well BERT performs on SimpleQuestions and provide an evaluation of both BERT and BiLSTM-based models in datasparse scenarios.
摘要：在知识图回答简单的问题，在问答充分研究的问题。以前的方法完成这个任务建立在使用预训练字的嵌入复发和卷积神经网络基础架构。这是最近表明，微调预训练的变压器网络（例如BERT）可以超越各种自然语言处理任务，以前的方法。在这项工作中，我们探讨SimpleQuestions如何BERT执行和datasparse场景同时提供BERT和基于BiLSTM的模型的评估。
D. Lukovnikov, A. Fischer, J. Lehmann
Abstract: Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings. It was recently shown that finetuning pretrained transformer networks (e.g. BERT) can outperform previous approaches on various natural language processing tasks. In this work, we investigate how well BERT performs on SimpleQuestions and provide an evaluation of both BERT and BiLSTM-based models in datasparse scenarios.
摘要：在知识图回答简单的问题，在问答充分研究的问题。以前的方法完成这个任务建立在使用预训练字的嵌入复发和卷积神经网络基础架构。这是最近表明，微调预训练的变压器网络（例如BERT）可以超越各种自然语言处理任务，以前的方法。在这项工作中，我们探讨SimpleQuestions如何BERT执行和datasparse场景同时提供BERT和基于BiLSTM的模型的评估。
2. An efficient automated data analytics approach to large scale computational comparative linguistics [PDF] 返回目录
Gabija Mikulyte, David Gilbert
Abstract: This research project aimed to overcome the challenge of analysing human language relationships, facilitate the grouping of languages and formation of genealogical relationship between them by developing automated comparison techniques. Techniques were based on the phonetic representation of certain key words and concept. Example word sets included numbers 1-10 (curated), large database of numbers 1-10 and sheep counting numbers 1-10 (other sources), colours (curated), basic words (curated). To enable comparison within the sets the measure of Edit distance was calculated based on Levenshtein distance metric. This metric between two strings is the minimum number of single-character edits, operations including: insertions, deletions or substitutions. To explore which words exhibit more or less variation, which words are more preserved and examine how languages could be grouped based on linguistic distances within sets, several data analytics techniques were involved. Those included density evaluation, hierarchical clustering, silhouette, mean, standard deviation and Bhattacharya coefficient calculations. These techniques lead to the development of a workflow which was later implemented by combining Unix shell scripts, a developed R package and SWI Prolog. This proved to be computationally efficient and permitted the fast exploration of large language sets and their analysis.
摘要：本研究项目旨在克服分析人类语言的关系的挑战，通过开发自动比较技术促进语言和形成它们之间的关系家谱分组。技术是基于某些关键词和概念的语音表示。例如字组包括编号1-10（策划），大数据库编号1-10和羊计数编号1-10（其它来源），颜色（策划）的，基本字（策划）。为了使基于Levenshtein距离度量计算编辑距离的测量集合中的比较。两个字符串之间的度量是单字符编辑，操作，包括的最小数目：插入，缺失或取代。探讨其中的话表现出或多或少的变化，这词更保存和研究如何可以语言基于集内的语言距离进行分组，几个数据分析技术的参与。这些问题包括浓度评价，层次聚类，侧影，平均值，标准偏差和查亚系数的计算。这些技术导致后来被合并的Unix shell脚本，一个开发[R包，SWI Prolog的实现工作流的发展。事实证明，这是计算效率和许可的大型语言组和他们的分析快速探索。
Gabija Mikulyte, David Gilbert
Abstract: This research project aimed to overcome the challenge of analysing human language relationships, facilitate the grouping of languages and formation of genealogical relationship between them by developing automated comparison techniques. Techniques were based on the phonetic representation of certain key words and concept. Example word sets included numbers 1-10 (curated), large database of numbers 1-10 and sheep counting numbers 1-10 (other sources), colours (curated), basic words (curated). To enable comparison within the sets the measure of Edit distance was calculated based on Levenshtein distance metric. This metric between two strings is the minimum number of single-character edits, operations including: insertions, deletions or substitutions. To explore which words exhibit more or less variation, which words are more preserved and examine how languages could be grouped based on linguistic distances within sets, several data analytics techniques were involved. Those included density evaluation, hierarchical clustering, silhouette, mean, standard deviation and Bhattacharya coefficient calculations. These techniques lead to the development of a workflow which was later implemented by combining Unix shell scripts, a developed R package and SWI Prolog. This proved to be computationally efficient and permitted the fast exploration of large language sets and their analysis.
摘要：本研究项目旨在克服分析人类语言的关系的挑战，通过开发自动比较技术促进语言和形成它们之间的关系家谱分组。技术是基于某些关键词和概念的语音表示。例如字组包括编号1-10（策划），大数据库编号1-10和羊计数编号1-10（其它来源），颜色（策划）的，基本字（策划）。为了使基于Levenshtein距离度量计算编辑距离的测量集合中的比较。两个字符串之间的度量是单字符编辑，操作，包括的最小数目：插入，缺失或取代。探讨其中的话表现出或多或少的变化，这词更保存和研究如何可以语言基于集内的语言距离进行分组，几个数据分析技术的参与。这些问题包括浓度评价，层次聚类，侧影，平均值，标准偏差和查亚系数的计算。这些技术导致后来被合并的Unix shell脚本，一个开发[R包，SWI Prolog的实现工作流的发展。事实证明，这是计算效率和许可的大型语言组和他们的分析快速探索。
3. Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification [PDF] 返回目录
Maria Mihaela Trusca, Gerasimos Spanakis
Abstract: The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the tiled CNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled CNN that applies a filter only on the words that appear in the similar contexts and on their neighbor words (a necessary step for preventing the loss of some n-grams). The experiments on the datasets of IMDB movie reviews and SemEval 2017 demonstrate the efficiency of the hybrid tiled CNN that performs better than both CNN and tiled CNN.
摘要：平铺卷积神经网络（CNN平铺）已经只适用于计算机视觉学习不变性。我们调整公司架构，以NLP提高最显着的特征为情感分析提取。明知平铺CNN在NLP领域的主要缺点是其不灵活的过滤器结构，我们提出了一种新的架构称为混合平铺CNN说，仅在出现在相似的背景和他们的邻居的话的话应用过滤器（必要步骤，用于防止一些的n-gram的损失）。对IMDB电影评论和SemEval 2017年的数据集上的实验证明了混合动力的效率平铺CNN说，比CNN都和瓷砖CNN性能更好。
Maria Mihaela Trusca, Gerasimos Spanakis
Abstract: The tiled convolutional neural network (tiled CNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the tiled CNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled CNN that applies a filter only on the words that appear in the similar contexts and on their neighbor words (a necessary step for preventing the loss of some n-grams). The experiments on the datasets of IMDB movie reviews and SemEval 2017 demonstrate the efficiency of the hybrid tiled CNN that performs better than both CNN and tiled CNN.
摘要：平铺卷积神经网络（CNN平铺）已经只适用于计算机视觉学习不变性。我们调整公司架构，以NLP提高最显着的特征为情感分析提取。明知平铺CNN在NLP领域的主要缺点是其不灵活的过滤器结构，我们提出了一种新的架构称为混合平铺CNN说，仅在出现在相似的背景和他们的邻居的话的话应用过滤器（必要步骤，用于防止一些的n-gram的损失）。对IMDB电影评论和SemEval 2017年的数据集上的实验证明了混合动力的效率平铺CNN说，比CNN都和瓷砖CNN性能更好。
4. Break It Down: A Question Understanding Benchmark [PDF] 返回目录
Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch, Jonathan Berant
Abstract: Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through natural language, that are necessary for answering a question. We develop a crowdsourcing pipeline, showing that quality QDMRs can be annotated at scale, and release the Break dataset, containing over 83K pairs of questions and their QDMRs. We demonstrate the utility of QDMR by showing that (a) it can be used to improve open-domain question answering on the HotpotQA dataset, (b) it can be deterministically converted to a pseudo-SQL formal language, which can alleviate annotation in semantic parsing applications. Last, we use Break to train a sequence-to-sequence model with copying that parses questions into QDMR structures, and show that it substantially outperforms several natural baselines.
摘要：理解自然语言问题需要一个问题分解成用于计算其答案的必要步骤的能力。在这项工作中，我们介绍的问题一个问题分解含义表示（QDMR）。 QDMR构成的步骤，通过自然语言来表达，所必需的回答问题的有序列表。我们开发了一个众包管道，显示出质量QDMRs可以大规模进行标注，并释放中断的数据集，包含超过83K对遇到的问题进行QDMRs。我们通过展示（一），它可以被用来改善对HotpotQA数据集开放域问答，（B），可以确定性地转换成伪SQL形式语言，它可以在语义缓解标注证明QDMR的效用解析应用。最后，我们使用中断训练序列到序列模型复制，它分析问题到QDMR结构，并表明它大幅优于几种天然基线。
Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch, Jonathan Berant
Abstract: Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through natural language, that are necessary for answering a question. We develop a crowdsourcing pipeline, showing that quality QDMRs can be annotated at scale, and release the Break dataset, containing over 83K pairs of questions and their QDMRs. We demonstrate the utility of QDMR by showing that (a) it can be used to improve open-domain question answering on the HotpotQA dataset, (b) it can be deterministically converted to a pseudo-SQL formal language, which can alleviate annotation in semantic parsing applications. Last, we use Break to train a sequence-to-sequence model with copying that parses questions into QDMR structures, and show that it substantially outperforms several natural baselines.
摘要：理解自然语言问题需要一个问题分解成用于计算其答案的必要步骤的能力。在这项工作中，我们介绍的问题一个问题分解含义表示（QDMR）。 QDMR构成的步骤，通过自然语言来表达，所必需的回答问题的有序列表。我们开发了一个众包管道，显示出质量QDMRs可以大规模进行标注，并释放中断的数据集，包含超过83K对遇到的问题进行QDMRs。我们通过展示（一），它可以被用来改善对HotpotQA数据集开放域问答，（B），可以确定性地转换成伪SQL形式语言，它可以在语义缓解标注证明QDMR的效用解析应用。最后，我们使用中断训练序列到序列模型复制，它分析问题到QDMR结构，并表明它大幅优于几种天然基线。
5. Teaching Machines to Converse [PDF] 返回目录
Jiwei Li
Abstract: The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing's epoch-making work in the early 1950s, which proposes that a machine's intelligence can be tested by how well it, the machine, can fool a human into believing that the machine is a human through dialogue conversations. Many systems learn generation rules from a minimal set of authored rules or labels on top of hand-coded rules or templates, and thus are both expensive and difficult to extend to open-domain scenarios. Recently, the emergence of neural network models the potential to solve many of the problems in dialogue learning that earlier systems cannot tackle: the end-to-end neural frameworks offer the promise of scalability and language-independence, together with the ability to track the dialogue state and then mapping between states and dialogue actions in a way not possible with conventional systems. On the other hand, neural systems bring about new challenges: they tend to output dull and generic responses; they lack a consistent or a coherent persona; they are usually optimized through single-turn conversations and are incapable of handling the long-term success of a conversation; and they are not able to take the advantage of the interactions with humans. This dissertation attempts to tackle these challenges: Contributions are two-fold: (1) we address new challenges presented by neural network models in open-domain dialogue generation systems; (2) we develop interactive question-answering dialogue systems by (a) giving the agent the ability to ask questions and (b) training a conversation agent through interactions with humans in an online fashion, where a bot improves through communicating with humans and learning from the mistakes that it makes.
摘要：一台机器与人沟通的能力一直与AI的普遍成功有关。这可以追溯到50年代初阿兰·图灵的划时代的工作，这提出了一个机器的智能可以通过如何，将本机，可以欺骗一个人相信该机器是通过对话谈话人进行测试。许多系统学习生成规则从一组上的手工编码的规则或模板顶部撰写规则或标签最小，从而既昂贵又难以扩展到开放域场景。最近，神经网络模型的出现的可能性，解决了许多在对话学习的问题，早期的系统无法应对：终端到终端的神经框架提供的可扩展性和语言独立性的承诺，与跟踪的能力一起对话状态，并与传统的系统不可能的方式国和对话的行动之间的映射，然后。在另一方面，神经系统带来了新的挑战：他们往往输出沉闷和通用的应对措施;他们缺乏一致或连贯的角色;他们通常是通过单圈的谈话进行了优化，不能处理的对话的长期成功;他们不能够采取互动的优势与人类。本文试图解决这些挑战：捐款有两方面：（1）我们解决在开放领域对话发电系统的神经网络模型提出了新的挑战; （2）我们开发给代理提问以在线的方式，其中一个机器人通过与人类和学习交流提高训练的对话代理通过互动与人类的能力，和（b）通过互动答疑对话系统（一）从它使错误。
Jiwei Li
Abstract: The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing's epoch-making work in the early 1950s, which proposes that a machine's intelligence can be tested by how well it, the machine, can fool a human into believing that the machine is a human through dialogue conversations. Many systems learn generation rules from a minimal set of authored rules or labels on top of hand-coded rules or templates, and thus are both expensive and difficult to extend to open-domain scenarios. Recently, the emergence of neural network models the potential to solve many of the problems in dialogue learning that earlier systems cannot tackle: the end-to-end neural frameworks offer the promise of scalability and language-independence, together with the ability to track the dialogue state and then mapping between states and dialogue actions in a way not possible with conventional systems. On the other hand, neural systems bring about new challenges: they tend to output dull and generic responses; they lack a consistent or a coherent persona; they are usually optimized through single-turn conversations and are incapable of handling the long-term success of a conversation; and they are not able to take the advantage of the interactions with humans. This dissertation attempts to tackle these challenges: Contributions are two-fold: (1) we address new challenges presented by neural network models in open-domain dialogue generation systems; (2) we develop interactive question-answering dialogue systems by (a) giving the agent the ability to ask questions and (b) training a conversation agent through interactions with humans in an online fashion, where a bot improves through communicating with humans and learning from the mistakes that it makes.
摘要：一台机器与人沟通的能力一直与AI的普遍成功有关。这可以追溯到50年代初阿兰·图灵的划时代的工作，这提出了一个机器的智能可以通过如何，将本机，可以欺骗一个人相信该机器是通过对话谈话人进行测试。许多系统学习生成规则从一组上的手工编码的规则或模板顶部撰写规则或标签最小，从而既昂贵又难以扩展到开放域场景。最近，神经网络模型的出现的可能性，解决了许多在对话学习的问题，早期的系统无法应对：终端到终端的神经框架提供的可扩展性和语言独立性的承诺，与跟踪的能力一起对话状态，并与传统的系统不可能的方式国和对话的行动之间的映射，然后。在另一方面，神经系统带来了新的挑战：他们往往输出沉闷和通用的应对措施;他们缺乏一致或连贯的角色;他们通常是通过单圈的谈话进行了优化，不能处理的对话的长期成功;他们不能够采取互动的优势与人类。本文试图解决这些挑战：捐款有两方面：（1）我们解决在开放领域对话发电系统的神经网络模型提出了新的挑战; （2）我们开发给代理提问以在线的方式，其中一个机器人通过与人类和学习交流提高训练的对话代理通过互动与人类的能力，和（b）通过互动答疑对话系统（一）从它使错误。
6. Pseudo-Bidirectional Decoding for Local Sequence Transduction [PDF] 返回目录
Wangchunshu Zhou, Tao Ge, Ke Xu
Abstract: Local sequence transduction (LST) tasks are sequence transduction tasks where there exists massive overlapping between the source and target sequences, such as Grammatical Error Correction (GEC) and spell or OCR correction. Previous work generally tackles LST tasks with standard sequence-to-sequence (seq2seq) models that generate output tokens from left to right and suffer from the issue of unbalanced outputs. Motivated by the characteristic of LST tasks, in this paper, we propose a simple but versatile approach named Pseudo-Bidirectional Decoding (PBD) for LST tasks. PBD copies the corresponding representation of source tokens to the decoder as pseudo future context to enable the decoder to attends to its bi-directional context. In addition, the bidirectional decoding scheme and the characteristic of LST tasks motivate us to share the encoder and the decoder of seq2seq models. The proposed PBD approach provides right side context information for the decoder and models the inductive bias of LST tasks, reducing the number of parameters by half and providing good regularization effects. Experimental results on several benchmark datasets show that our approach consistently improves the performance of standard seq2seq models on LST tasks.
摘要：本地序列转导（LST）任务是在存在源和目标序列，例如语法纠错（GEC）和拼写或OCR校正之间大量重叠序列转导的任务。以前的工作通常铲球与生成输出令牌由左到右，并从非平衡输出的问题遭受标准序列对序列（seq2seq）模型LST任务。通过LST任务特性的启发，在本文中，我们提出了一个简单而通用的命名伪双向解码（PBD）为LST任务的方法。 PBD拷贝源的相应表示令牌给解码器作为伪未来上下文，以使解码器能够照顾到其双向上下文。此外，双向解码方案和LST任务的特点促使我们分享编码器和seq2seq车型的解码器。所提出的PBD方法提供了解码器和模型的LST任务归纳偏置，减少一半的参数的数量和提供良好的正规化效果右侧的上下文信息。在几个基准数据集的实验结果表明，该方法可以始终如一提高标准seq2seq车型上LST任务的性能。
Wangchunshu Zhou, Tao Ge, Ke Xu
Abstract: Local sequence transduction (LST) tasks are sequence transduction tasks where there exists massive overlapping between the source and target sequences, such as Grammatical Error Correction (GEC) and spell or OCR correction. Previous work generally tackles LST tasks with standard sequence-to-sequence (seq2seq) models that generate output tokens from left to right and suffer from the issue of unbalanced outputs. Motivated by the characteristic of LST tasks, in this paper, we propose a simple but versatile approach named Pseudo-Bidirectional Decoding (PBD) for LST tasks. PBD copies the corresponding representation of source tokens to the decoder as pseudo future context to enable the decoder to attends to its bi-directional context. In addition, the bidirectional decoding scheme and the characteristic of LST tasks motivate us to share the encoder and the decoder of seq2seq models. The proposed PBD approach provides right side context information for the decoder and models the inductive bias of LST tasks, reducing the number of parameters by half and providing good regularization effects. Experimental results on several benchmark datasets show that our approach consistently improves the performance of standard seq2seq models on LST tasks.
摘要：本地序列转导（LST）任务是在存在源和目标序列，例如语法纠错（GEC）和拼写或OCR校正之间大量重叠序列转导的任务。以前的工作通常铲球与生成输出令牌由左到右，并从非平衡输出的问题遭受标准序列对序列（seq2seq）模型LST任务。通过LST任务特性的启发，在本文中，我们提出了一个简单而通用的命名伪双向解码（PBD）为LST任务的方法。 PBD拷贝源的相应表示令牌给解码器作为伪未来上下文，以使解码器能够照顾到其双向上下文。此外，双向解码方案和LST任务的特点促使我们分享编码器和seq2seq车型的解码器。所提出的PBD方法提供了解码器和模型的LST任务归纳偏置，减少一半的参数的数量和提供良好的正规化效果右侧的上下文信息。在几个基准数据集的实验结果表明，该方法可以始终如一提高标准seq2seq车型上LST任务的性能。
7. Self-Adversarial Learning with Comparative Discrimination for Text Generation [PDF] 返回目录
Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou
Abstract: Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. In contrast to standard GANs that use a binary classifier as its discriminator to predict whether a sample is real or generated, SAL employs a comparative discriminator which is a pairwise classifier for comparing the text quality between a pair of samples. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. This self-improvement reward mechanism allows the model to receive credits more easily and avoid collapsing towards the limited number of real samples, which not only helps alleviate the reward sparsity issue but also reduces the risk of mode collapse. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity, and yields more stable performance compared to the previous GANs for text generation.
摘要：传统的生成性对抗性网络（甘斯）的文本生成往往具有影响的质量和产生的样本的多样性奖励稀疏和模式崩溃的问题。为了解决这个问题，我们提出了一个新的自我对抗学习（SAL）为提高文本生成甘斯的表现模式。与此相反使用二元分类器作为它的鉴别器以预测样品是否是真实的还是生成的标准甘斯，SAL采用比较鉴别器，其是用于在一对样品之间比较所述文本质量成对分类器。在训练期间，如果其目前产生的句子被认为比其以前生成的样本更好SAL奖励发电机。这种自强不息的奖励机制，使模型更容易获得信贷，并避免对数量有限的实际样品，这不仅有助于缓解奖励稀疏问题倒塌，但也降低了模式崩溃的风险。在文本生成基准数据集的实验表明，该方法显着提高的质量和多样性，并产生更稳定的性能相比之前的甘斯的文本生成。
Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou
Abstract: Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. In contrast to standard GANs that use a binary classifier as its discriminator to predict whether a sample is real or generated, SAL employs a comparative discriminator which is a pairwise classifier for comparing the text quality between a pair of samples. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. This self-improvement reward mechanism allows the model to receive credits more easily and avoid collapsing towards the limited number of real samples, which not only helps alleviate the reward sparsity issue but also reduces the risk of mode collapse. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity, and yields more stable performance compared to the previous GANs for text generation.
摘要：传统的生成性对抗性网络（甘斯）的文本生成往往具有影响的质量和产生的样本的多样性奖励稀疏和模式崩溃的问题。为了解决这个问题，我们提出了一个新的自我对抗学习（SAL）为提高文本生成甘斯的表现模式。与此相反使用二元分类器作为它的鉴别器以预测样品是否是真实的还是生成的标准甘斯，SAL采用比较鉴别器，其是用于在一对样品之间比较所述文本质量成对分类器。在训练期间，如果其目前产生的句子被认为比其以前生成的样本更好SAL奖励发电机。这种自强不息的奖励机制，使模型更容易获得信贷，并避免对数量有限的实际样品，这不仅有助于缓解奖励稀疏问题倒塌，但也降低了模式崩溃的风险。在文本生成基准数据集的实验表明，该方法显着提高的质量和多样性，并产生更稳定的性能相比之前的甘斯的文本生成。
8. Augmenting Visual Question Answering with Semantic Frame Information in a Multitask Learning Approach [PDF] 返回目录
Mehrdad Alizadeh, Barbara Di Eugenio
Abstract: Visual Question Answering (VQA) concerns providing answers to Natural Language questions about images. Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. Whereas the task is grounded in visual processing, if the question focuses on events described by verbs, the language understanding component becomes crucial. Our hypothesis is that models should be aware of verb semantics, as expressed via semantic role labels, argument types, and/or frame elements. Unfortunately, no VQA dataset exists that includes verb semantic information. Our first contribution is a new VQA dataset (imSituVQA) that we built by taking advantage of the imSitu annotations. The imSitu dataset consists of images manually labeled with semantic frame elements, mostly taken from FrameNet. Second, we propose a multitask CNN-LSTM VQA model that learns to classify the answers as well as the semantic frame elements. Our experiments show that semantic frame element classification helps the VQA system avoid inconsistent responses and improves performance.
摘要：视觉答疑（VQA）的担忧提供了回答有关图像自然语言问题。一些深层神经网络方法被提出来的任务结束到终端的时装模特。尽管任务是在视觉处理接地，如果问题集中在事件描述由动词，理解组件的语言变得至关重要。我们的假设是模型应该知道动词语义的，如通过语义角色标签，参数类型，和/或框架元素表示。不幸的是，没有VQA数据集存在，包括动词语义信息。我们的第一个贡献是一个新的VQA的数据集（imSituVQA），我们通过采取imSitu注释的优势构建。数据集由具有语义框架元件手动标记的图像的imSitu，大多是从框架网络服用。其次，我们提出了一个多任务CNN-LSTM VQA模型学会的答案，以及语义框架内容进行分类。我们的实验表明，语义框架元素的分类有助于VQA系统避免不一致的响应和提高性能。
Mehrdad Alizadeh, Barbara Di Eugenio
Abstract: Visual Question Answering (VQA) concerns providing answers to Natural Language questions about images. Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. Whereas the task is grounded in visual processing, if the question focuses on events described by verbs, the language understanding component becomes crucial. Our hypothesis is that models should be aware of verb semantics, as expressed via semantic role labels, argument types, and/or frame elements. Unfortunately, no VQA dataset exists that includes verb semantic information. Our first contribution is a new VQA dataset (imSituVQA) that we built by taking advantage of the imSitu annotations. The imSitu dataset consists of images manually labeled with semantic frame elements, mostly taken from FrameNet. Second, we propose a multitask CNN-LSTM VQA model that learns to classify the answers as well as the semantic frame elements. Our experiments show that semantic frame element classification helps the VQA system avoid inconsistent responses and improves performance.
摘要：视觉答疑（VQA）的担忧提供了回答有关图像自然语言问题。一些深层神经网络方法被提出来的任务结束到终端的时装模特。尽管任务是在视觉处理接地，如果问题集中在事件描述由动词，理解组件的语言变得至关重要。我们的假设是模型应该知道动词语义的，如通过语义角色标签，参数类型，和/或框架元素表示。不幸的是，没有VQA数据集存在，包括动词语义信息。我们的第一个贡献是一个新的VQA的数据集（imSituVQA），我们通过采取imSitu注释的优势构建。数据集由具有语义框架元件手动标记的图像的imSitu，大多是从框架网络服用。其次，我们提出了一个多任务CNN-LSTM VQA模型学会的答案，以及语义框架内容进行分类。我们的实验表明，语义框架元素的分类有助于VQA系统避免不一致的响应和提高性能。
9. Enhancement of Short Text Clustering by Iterative Classification [PDF] 返回目录
Md Rashadul Hasan Rakib, Norbert Zeh, Magdalena Jankowska, Evangelos Milios
Abstract: Short text clustering is a challenging task due to the lack of signal contained in such short texts. In this work, we propose iterative classification as a method to b o ost the clustering quality (e.g., accuracy) of short texts. Given a clustering of short texts obtained using an arbitrary clustering algorithm, iterative classification applies outlier removal to obtain outlier-free clusters. Then it trains a classification algorithm using the non-outliers based on their cluster distributions. Using the trained classification model, iterative classification reclassifies the outliers to obtain a new set of clusters. By repeating this several times, we obtain a much improved clustering of texts. Our experimental results show that the proposed clustering enhancement method not only improves the clustering quality of different clustering methods (e.g., k-means, k-means--, and hierarchical clustering) but also outperforms the state-of-the-art short text clustering methods on several short text datasets by a statistically significant margin.
摘要：短文本聚类是一个具有挑战性的任务，由于包含在如此短的文字缺乏的信号。在这项工作中，我们提出的迭代分类为B○OST短文本的聚类质量（例如，准确度）的方法。鉴于使用任意的聚类算法获得的短文本的聚类，分类迭代适用异常值去除以获得离群-空闲簇。然后训练使用基于其集群分布的非离群的分类算法。利用训练的分类模型，迭代分类重新分类离群获得一组新的集群。通过重复几次，我们得到的文本大大改善群集。我们的实验结果表明，所提出的聚类增强方法不仅提高了的不同的聚类方法（例如，k均值，K-指：，和层次聚类）聚类质量也优于状态的最先进的短文本有统计显著保证金聚类在几个简短的文本数据集的方法。
Md Rashadul Hasan Rakib, Norbert Zeh, Magdalena Jankowska, Evangelos Milios
Abstract: Short text clustering is a challenging task due to the lack of signal contained in such short texts. In this work, we propose iterative classification as a method to b o ost the clustering quality (e.g., accuracy) of short texts. Given a clustering of short texts obtained using an arbitrary clustering algorithm, iterative classification applies outlier removal to obtain outlier-free clusters. Then it trains a classification algorithm using the non-outliers based on their cluster distributions. Using the trained classification model, iterative classification reclassifies the outliers to obtain a new set of clusters. By repeating this several times, we obtain a much improved clustering of texts. Our experimental results show that the proposed clustering enhancement method not only improves the clustering quality of different clustering methods (e.g., k-means, k-means--, and hierarchical clustering) but also outperforms the state-of-the-art short text clustering methods on several short text datasets by a statistically significant margin.
摘要：短文本聚类是一个具有挑战性的任务，由于包含在如此短的文字缺乏的信号。在这项工作中，我们提出的迭代分类为B○OST短文本的聚类质量（例如，准确度）的方法。鉴于使用任意的聚类算法获得的短文本的聚类，分类迭代适用异常值去除以获得离群-空闲簇。然后训练使用基于其集群分布的非离群的分类算法。利用训练的分类模型，迭代分类重新分类离群获得一组新的集群。通过重复几次，我们得到的文本大大改善群集。我们的实验结果表明，所提出的聚类增强方法不仅提高了的不同的聚类方法（例如，k均值，K-指：，和层次聚类）聚类质量也优于状态的最先进的短文本有统计显著保证金聚类在几个简短的文本数据集的方法。
10. Unwanted Advances in Higher Education: Uncovering Sexual Harassment Experiences in Academia with Text Mining [PDF] 返回目录
Amir Karami, Cynthia Nicole White, Kayla Ford, Suzanne Swan, Melek Yildiz Spinel
Abstract: Sexual harassment in academia is often a hidden problem because victims are usually reluctant to report their experiences. Recently, a web survey was developed to provide an opportunity to share thousands of sexual harassment experiences in academia. Using an efficient approach, this study collected and investigated more than 2,000 sexual harassment experiences to better understand these unwanted advances in higher education. This paper utilized text mining to disclose hidden topics and explore their weight across three variables: harasser gender, institution type, and victim's field of study. We mapped the topics on five themes drawn from the sexual harassment literature and found that more than 50% of the topics were assigned to the unwanted sexual attention theme. Fourteen percent of the topics were in the gender harassment theme, in which insulting, sexist, or degrading comments or behavior was directed towards women. Five percent of the topics involved sexual coercion (a benefit is offered in exchange for sexual favors), 5% involved sex discrimination, and 7% of the topics discussed retaliation against the victim for reporting the harassment, or for simply not complying with the harasser. Findings highlight the power differential between faculty and students, and the toll on students when professors abuse their power. While some topics did differ based on type of institution, there were no differences between the topics based on gender of harasser or field of study. This research can be beneficial to researchers in further investigation of this paper's dataset, and to policymakers in improving existing policies to create a safe and supportive environment in academia.
摘要：在学术界性骚扰往往是一个隐藏的问题，因为受害者往往不愿意报告自己的经历。最近，网络调查的开发提供共享成千上万的性骚扰经历学术界的机会。使用一种有效的方法，这项研究收集和调查2000余和性骚扰的经验，以更好地了解高等教育这些不必要的进步。本文利用文本挖掘透露隐藏的主题和跨越三个变量探索自己的体重：骚扰者性别，机构类型和研究的受害人的领域。我们映射从性骚扰文献中提取，发现的主题超过50％被分配到不必要的性关注主题五个主题的主题。的主题十四％的人在性别骚扰主题，在这种侮辱，性别歧视，或侮辱性的评论或行为针对妇女。的主题百分之五参与性胁迫（一个好处是提供以换取性方面的好处），5％涉及性别歧视，以及主题7％讨论对受害者报复举报骚扰，或者干脆不与骚扰符合。发现突出的教师和学生，以及学生的收费之间的功率差时，教授滥用职权。虽然有些题目确实有所不同根据类型的机构，有基于研究的骚扰或领域的性别主题之间没有差异。这项研究可以在本文的数据集的进一步调查研究有利，对政策制定者改善现有的政策，创造学术界安全和支持的环境。
Amir Karami, Cynthia Nicole White, Kayla Ford, Suzanne Swan, Melek Yildiz Spinel
Abstract: Sexual harassment in academia is often a hidden problem because victims are usually reluctant to report their experiences. Recently, a web survey was developed to provide an opportunity to share thousands of sexual harassment experiences in academia. Using an efficient approach, this study collected and investigated more than 2,000 sexual harassment experiences to better understand these unwanted advances in higher education. This paper utilized text mining to disclose hidden topics and explore their weight across three variables: harasser gender, institution type, and victim's field of study. We mapped the topics on five themes drawn from the sexual harassment literature and found that more than 50% of the topics were assigned to the unwanted sexual attention theme. Fourteen percent of the topics were in the gender harassment theme, in which insulting, sexist, or degrading comments or behavior was directed towards women. Five percent of the topics involved sexual coercion (a benefit is offered in exchange for sexual favors), 5% involved sex discrimination, and 7% of the topics discussed retaliation against the victim for reporting the harassment, or for simply not complying with the harasser. Findings highlight the power differential between faculty and students, and the toll on students when professors abuse their power. While some topics did differ based on type of institution, there were no differences between the topics based on gender of harasser or field of study. This research can be beneficial to researchers in further investigation of this paper's dataset, and to policymakers in improving existing policies to create a safe and supportive environment in academia.
摘要：在学术界性骚扰往往是一个隐藏的问题，因为受害者往往不愿意报告自己的经历。最近，网络调查的开发提供共享成千上万的性骚扰经历学术界的机会。使用一种有效的方法，这项研究收集和调查2000余和性骚扰的经验，以更好地了解高等教育这些不必要的进步。本文利用文本挖掘透露隐藏的主题和跨越三个变量探索自己的体重：骚扰者性别，机构类型和研究的受害人的领域。我们映射从性骚扰文献中提取，发现的主题超过50％被分配到不必要的性关注主题五个主题的主题。的主题十四％的人在性别骚扰主题，在这种侮辱，性别歧视，或侮辱性的评论或行为针对妇女。的主题百分之五参与性胁迫（一个好处是提供以换取性方面的好处），5％涉及性别歧视，以及主题7％讨论对受害者报复举报骚扰，或者干脆不与骚扰符合。发现突出的教师和学生，以及学生的收费之间的功率差时，教授滥用职权。虽然有些题目确实有所不同根据类型的机构，有基于研究的骚扰或领域的性别主题之间没有差异。这项研究可以在本文的数据集的进一步调查研究有利，对政策制定者改善现有的政策，创造学术界安全和支持的环境。
注：中文为机器翻译结果！