检索结果-内蒙古大学图书馆

13th workshop on graph-based methods for natural language processing, Textgraphs 2019, in conjunction with the 2019 Conference on Empirical methods in natural language processing and 9th International Joint Conference on natural language processing, EMNLP-IJCNLP 2019

作者： Banerjee, Pratyay School of Computing Informatics and Decision Systems Engineering Arizona State University United States

ISBN: (纸本)9781950737864

In this work we describe the system from natural language processing group at Arizona State University for the Textgraphs 2019 Shared Task. The task focuses on Explanation Regeneration, an intermediate step towards general multi-hop inference on large graphs. Our approach consists of modeling the explanation regeneration task as a learning to rank problem, for which we use state-of-theart language models and explore dataset preparation techniques. We utilize an iterative reranking based approach to further improve the rankings. Our system secured 2nd rank in the task with a mean average precision (MAP) of 41.3% on the test set. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Media Bias, the Social Sciences, and NLP: Automating Frame Analyses to Identify Bias by Word Choice and Labeling 58

Media Bias, the Social Sciences, and NLP: Automating Frame A...

引用

58th Annual Meeting of the Association-for-Computational-Linguistics (ACL)

作者： Hamborg, Felix Univ Konstanz Dept Comp & Informat Sci Constance Germany

ISBN: (纸本)9781952148033

Media bias can strongly impact the public perception of topics reported in the news. A difficult to detect, yet powerful form of slanted news coverage is called bias by word choice and labeling (WCL). WCL bias can occur, for example, when journalists refer to the same semantic concept by using different terms that frame the concept differently and consequently may lead to different assessments by readers, such as the terms "freedom fighters" and "terrorists," or "gun rights" and "gun control." In this research project, I aim to devise methods that identify instances of WCL bias and estimate the frames they induce, e.g., not only is "terrorists" of negative polarity but also ascribes to aggression and fear. To achieve this, I plan to research methods using natural language processing and deep learning while employing models and using analysis concepts from the social sciences, where researchers have studied media bias for decades. The first results indicate the effectiveness of this interdisciplinary research approach. My vision is to devise a system that helps news readers to become aware of the differences in media coverage caused by bias.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Neural speech translation using lattice transformations and graph networks 13

Neural speech translation using lattice transformations and ...

引用

作者： Beck, Daniel Cohn, Trevor Haffari, Gholamreza School of Computing and Information Systems University of Melbourne Australia Faculty of Information Technology Monash University Australia

ISBN: (纸本)9781950737864

Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation. However, previous work assume access to the original transcriptions used to train the ASR system, which can limit applicability in real scenarios. In this work we propose an approach for speech translation through lattice transformations and neural models based on graph networks. Experimental results show that our approach reaches competitive performance without relying on transcriptions, while also being orders of magnitude faster than previous work. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Chains-of-reasoning at textgraphs 2019 shared task: Reasoning over chains of facts for explainable multi-hop inference 13

Chains-of-reasoning at textgraphs 2019 shared task: Reasonin...

引用

作者： Godbole, Ameya Das, Rajarshi Zaheer, Manzil Dhuliawala, Shehzaad McCallum, Andrew University of Massachusetts Amherst United States Google Research United States Microsoft Research Montreal Canada

ISBN: (纸本)9781950737864

This paper describes our submission to the shared task1 on "Multi-hop Inference Explanation Regeneration" in Textgraphs workshop at EMNLP 2019 (Jansen and Ustalov, 2019). Our system identifies chains of facts relevant to explain an answer to an elementary science examination question. To counter the problem of 'spurious chains' leading to 'semantic drifts', we train a ranker that uses contextualized representation of facts to score its relevance for explaining an answer to a question. Our system2 was ranked first w.r.t the mean average precision (MAP) metric outperforming the second best system by 14.95 points. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

Essentia: Mining domain-specific paraphrases with word-alignment graphs 13

Essentia: Mining domain-specific paraphrases with word-align...

引用

作者： Ma, Danni Chen, Chen Golshan, Behzad Tan, Wang-Chiew Department of Computer and Information Science University of Pennsylvania United States Megagon Labs

ISBN: (纸本)9781950737864

Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at discovering generic paraphrases, they often fail to identify domain-specific paraphrases (e.g. {"staff ", "concierge"} in the hospitality domain). This is because current techniques are often based on statistical methods, while domain-specific corpora are too small to fit statistical methods. In this paper, we present an unsupervised graph-based technique to mine paraphrases from a small set of sentences that roughly share the same topic or intent. Our system, ESSENTIA, relies on word-alignment techniques to create a word-alignment graph that merges and organizes tokens from input sentences. The resulting graph is then used to generate candidate paraphrases. We demonstrate that our system obtains high quality paraphrases, as evaluated by crowd workers. We further show that the majority of the identified paraphrases are domain-specific and thus complement existing paraphrase databases. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： Statistical methods

来源：评论

学校读者我要写书评

暂无评论

graph enhanced cross-domain text-to-SQL generation 13

Graph enhanced cross-domain text-to-SQL generation

引用

作者： Huo, Siyu Ma, Tengfei Chen, Jie Chang, Maria Wu, Lingfei Witbrock, Michael IBM Research United States IBM Research AI United States MIT-IBM Watson AI Lab United States University of Auckland New Zealand

ISBN: (纸本)9781950737864

Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches for semantic parsing have shown promise on a variety of benchmark data sets, particularly on textto- SQL parsing. However, most text-to-SQL parsers do not generalize to unseen data sets in different domains. In this paper, we propose a new cross-domain learning scheme to perform text-to-SQL translation and demonstrate its use on Spider, a large-scale cross-domain text-to-SQL data set. We improve upon a state-of-the-art Spider model, SyntaxSQLNet, by constructing a graph of column names for all databases and using graph neural networks to compute their embeddings. The resulting embeddings offer better cross-domain representations and SQL queries, as evidenced by substantial improvement on the Spider data set compared to SyntaxSQLNet. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Layerwise relevance visualization in convolutional text graph classifiers 13

Layerwise relevance visualization in convolutional text grap...

引用

作者： Schwarzenberg, Robert Hübner, Marc Harbecke, David Alt, Christoph Hennig, Leonhard Berlin Germany

ISBN: (纸本)9781950737864

Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. graph Convolutional Networks (GCN) allow this projection, but existing explainability methods do not exploit this fact, i.e. do not focus their explanations on intermediate states. In this work, we present a novel method that traces and visualizes features that contribute to a classification decision in the visible and hidden layers of a GCN. Our method exposes hidden cross-layer dynamics in the input graph structure. We experimentally demonstrate that it yields meaningful layerwise explanations for a GCN sentence classifier. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Reasoning over paths via knowledge base completion 13

Reasoning over paths via knowledge base completion

引用

作者： Sudhahar, Saatviga Roberts, Ian Pierleoni, Andrea Healx Cambridge United Kingdom

ISBN: (纸本)9781950737864

Reasoning over paths in large scale knowledge graphs is an important problem for many applications. In this paper we discuss a simple approach to automatically build and rank paths between a source and target entity pair with learned embeddings using a knowledge base completion model (KBC). We assembled a knowledge graph by mining the available biomedical scientific literature and extracted a set of high frequency paths to use for validation. We demonstrate that our method is able to effectively rank a list of known paths between a pair of entities and also come up with plausible paths that are not present in the knowledge graph. For a given entity pair we are able to reconstruct the highest ranking path 60% of the time within the top 10 ranked paths and achieve 49% mean average precision. Our approach is compositional since any KBC model that can produce vector representations of entities can be used. © 2019 EMNLP-IJCNLP 2019 - graph-based methods for natural language processing - proceedings of the 13th workshop. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

FAITHFUL EXPLANATIONS OF BLACK-BOX NLP MODELS USING LLM-GENERATED COUNTERFACTUALS

arXiv

引用

arXiv 2023年

作者： Gat, Yair Ori Calderon, Nitay Feder, Amir Chapanin, Alexander Sharma, Amit Reichart, Roi Faculty of Data and Decision Sciences Technion IIT Columbia University Data Science Institute United States Microsoft Research India India

Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In this paper, we address model-agnostic explanations, proposing two approaches for counterfactual (CF) approximation. The first approach is CF generation, where a large language model (LLM) is prompted to change a specific text concept while keeping confounding concepts unchanged. While this approach is demonstrated to be very effective, applying LLM at inference-time is costly. We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space. This space is faithful to a given causal graph and effectively serves to identify matches that approximate CFs. After showing theoretically that approximating CFs is required in order to construct faithful explanations, we benchmark our approaches and explain several models, including LLMs with billions of parameters. Our empirical results demonstrate the excellent performance of CF generation models as model-agnostic explainers. Moreover, our matching approach, which requires far less test-time resources, also provides effective explanations, surpassing many baselines. We also find that Top-K techniques universally improve every tested method. Finally, we showcase the potential of LLMs in constructing new benchmarks for model explanation and subsequently validate our conclusions. Our work illuminates new pathways for efficient and accurate approaches to interpreting NLP systems. © 2023, CC0.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Relation Extraction in Biomedical Texts based on Multi-Head Attention Model With Syntactic Dependency Feature: Modeling Study

引用

JMIR MEDICAL INFORMATICS 2022年第10期10卷 e41136页

作者： Li, Yongbin Hui, Linhu Zou, Liping Li, Huyang Xu, Luo Wang, Xiaohua Chua, Stephanie Zunyi Med Univ Sch Med Informat Engn 6 Xuefu Rd West Zunyi 563000 Guizhou Peoples R China Univ Malaysia Sarawak Fac Comp Sci & Informat Technol Sarawak Malaysia

Background: With the rapid expansion of biomedical literature, biomedical information extraction has attracted increasing attention from researchers. In particular, relation extraction between 2 entities is a long-term research topic. Objective: This study aimed to perform 2 multiclass relation extraction tasks of Biomedical natural language processing workshop 2019 Open Shared Tasks: relation extraction of Bacteria-Biotope (BB-rel) task and binary relation extraction of plant seed development (SeeDev-binary) task. In essence, these 2 tasks are aimed at extracting the relation between annotated entity pairs from biomedical texts, which is a challenging problem. methods: Traditional research methods adopted feature- or kernel-based methods and achieved good performance. For these tasks, we propose a deep learning model based on a combination of several distributed features, such as domain-specific word embedding, part-of-speech embedding, entity-type embedding, distance embedding, and position embedding. The multi-head attention mechanism is used to extract the global semantic features of an entire sentence. Meanwhile, we introduced a dependency-type feature and the shortest dependency path connecting 2 candidate entities in the syntactic dependency graph to enrich the feature representation. Results: Experiments show that our proposed model has excellent performance in biomedical relation extraction, achieving F1 scores of 65.56% and 38.04% on the test sets of the BB-rel and SeeDev-binary tasks. Especially in the SeeDev-binary task, the F1 score of our model is superior to that of other existing models and achieves state-of-the-art performance. Conclusions: We demonstrated that the multi-head attention mechanism can learn relevant syntactic and semantic features in different representation subspaces and different positions to extract comprehensive feature representation. Moreover, syntactic dependency features can improve the performance of the model by learning dep

关键词： biomedical relation extraction deep learning feature combination multi-head attention additive attention syntactic dependency feature syntactic dependency graph shortest dependency path

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：