检索结果-内蒙古大学图书馆

14th workshop on graph-based methods for natural language processing, Textgraphs 2020, in conjunction with the 28th International Conference on Computational Linguistics, COLING 2020

作者： Shah, Haseeb Villmow, Johannes Ulges, Adrian Department of Computer Science University of Alberta Canada DCSM Department RheinMain University of Applied Sciences Germany

ISBN: (纸本)9781952148422

We propose an open-world knowledge graph completion model that can be combined with common closed-world approaches (such as ComplEx) and enhance them to exploit text-based representations for entities unseen in training. Our model learns relation-specific transformation functions from text-based embedding space to graph-based embedding space, where the closed-world link prediction model can be applied. We demonstrate state-of-the-art results on common open-world benchmarks and show that our approach benefits from relation-specific transformation functions (RST), giving substantial improvements over a relation-agnostic approach. © COLING *** rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level Attention Model for Evidence-based Fact Checking

A Multi-Level Attention Model for Evidence-Based Fact Checki...

引用

Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint Conference on natural language processing (IJCNLP) / 6th workshop on Representation Learning for NLP (RepL4NLP)

作者： Kruengkrai, Canasai Yamagishi, Junichi Wang, Xin Natl Inst Informat Tokyo Japan

ISBN: (纸本)9781954085541

Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent state-of-the-art approaches have developed increasingly sophisticated models based on graph structures. We present a simple model that can be trained on sequence structures. Our model enables inter-sentence attentions at different levels and can benefit from joint training. Results on a large-scale dataset for Fact Extraction and VERification (FEVER) show that our model outperforms the graph-based approaches and yields 1.09% and 1.42% improvements in label accuracy and FEVER score, respectively, over the best published model.

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

TIME-AWARE MULTIWAY ADAPTIVE FUSION NETWORK FOR TEMPORAL KNOWLEDGE graph QUESTION ANSWERING

arXiv

引用

arXiv 2023年

作者： Liu, Yonghao Liang, Di Fang, Fang Wang, Sirui Wu, Wei Jiang, Rui Department of Automation Tsinghua University Beijing China Centre for Natural Language Processing Meituan Inc. Beijing China

Knowledge graphs (KGs) have received increasing attention due to its wide applications on natural language processing. However, its use case on temporal question answering (QA) has not been well-explored. Most of existing methods are developed based on pre-trained language models, which might not be capable to learn temporal-specific presentations of entities in terms of temporal KGQA task. To alleviate this problem, we propose a novel Time-aware Multiway Adaptive (TMA) fusion network. Inspired by the step-by-step reasoning behavior of humans. For each given question, TMA first extracts the relevant concepts from the KG, and then feeds them into a multiway adaptive module to produce a temporal-specific representation of the question. This representation can be incorporated with the pre-trained KG embedding to generate the final prediction. Empirical results verify that the proposed model achieves better performance than the state-of-the-art models in the benchmark dataset. Notably, the Hits@1 and Hits@10 results of TMA on the CronQuestions dataset’s complex questions are absolutely improved by 24% and 10% compared to the best-performing baseline. Furthermore, we also show that TMA employing an adaptive fusion mechanism can provide interpretability by analyzing the proportion of information in question representations. Copyright © 2023, The Authors. 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

Seeing stars when there aren't many stars: graph-based semi-supervised learning for sentiment categorization 1

Seeing stars when there aren't many stars: Graph-based semi-...

引用

1st workshop on graph-based Algorithms for natural language processing, Textgraphs 2006 at Human language Technologies

作者： Goldberg, Andrew B. Zhu, Xiaojin Computer Sciences Department University of Wisconsin-Madison Madison WI53706 United States

We present a graph-based semi-supervised learning algorithm to address the sentiment analysis task of rating inference. Given a set of documents (e.g., movie reviews) and accompanying ratings (e.g., "4 stars"), the task calls for inferring numerical ratings for unlabeled documents based on the perceived sentiment expressed by their text. In particular, we are interested in the situation where labeled data is scarce. We place this task in the semi-supervised setting and demonstrate that considering unlabeled reviews in the learning process can improve rating-inference performance. We do so by creating a graph on both labeled and unlabeled data to encode certain assumptions for this task. We then solve an optimization problem to obtain a smooth rating function over the whole graph. When only limited labeled data is available, this method achieves significantly better predictive accuracy over other methods that ignore the unlabeled examples during training. © 2006 Association for Computational Linguistics

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Global information-aware argument mining based on a top-down multi-turn QA model

引用

INFORMATION processing & MANAGEMENT 2023年第5期60卷

作者： Liu, Boyang Schlegel, Viktor Thompson, Paul Batista-Navarro, Riza Theresa Ananiadou, Sophia Univ Manchester Natl Ctr Text Min Dept Comp Sci Manchester M1 7DN England Alan Turing Inst London NW1 2DB England ASUS Intelligent Cloud Serv AICS 37 Craig Rd02-01 Singapore 089675 Singapore

Argument mining (AM) aims to automatically generate a graph that represents the argument structure of a document. Most previous AM models only pay attention to a single argument component (AC) to classify the type of the AC or a pair of ACs to identify and classify the argumentative relation (AR) between the two ACs. These models ignore the impact of global argument structure of the documents, which is important, especially in some highly structured genres such as scientific papers, where the process of argumentation is relatively fixed. Inspired by this, we propose a novel two-stage model which leverages global structure information to support AM. The first stage uses a multi-turn question-answering model to incrementally generate an initial argumentative graph that identifies relations among ACs. At each turn, all ACs related to the query AC are generated simultaneously, such that the sibling global information between the answer ACs is considered. In addition, the partially constructed graph is used as global structure information to support the extension of the graph with additional ACs. After the whole initial graph structure has been determined, the second stage assigns semantic types to both the ACs and ARs among them, leveraging information from this initial graph as global structure information. We test the proposed methods on two scientific datasets (one is the AbstRCT dataset including 659 abstracts about cancer research and the other is the SciARG dataset that consists of 225 computer linguistic abstracts and 285 biomedical abstracts) and a student essay dataset PE with 402 essays. Our experiments show that our model improves the state-of-the-art performance on two scientific datasets for different AM subtasks, with average improvements of 1%, 2.41%, 1.1% for the ACC, ARI and ARC task respectively on the AbstRCT dataset, and 2.36%, 1.84%, 8.87% for the ACC, ARI and ARC task on the SciARG dataset. Our model also achieves comparative results on the PE data

关键词： Argument mining Question answering Machine reading comprehension natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Study of Two graph Algorithms in Topic-driven Summarization 1

A Study of Two Graph Algorithms in Topic-driven Summarizatio...

引用

1st workshop on graph-based Algorithms for natural language processing, Textgraphs 2006 at Human language Technologies

作者： Nastase, Vivi Szpakowicz, Stan School of Information Technology and Engineering University of Ottawa Ottawa Canada Institute of Computer Science Polish Academy of Sciences Warsaw Poland

We study how two graph algorithms apply to topic-driven summarization in the scope of Document Understanding Conferences. The DUC 2005 and 2006 tasks were to summarize into 250 words a collection of documents on a topic consisting of a few statements or questions. Our algorithms select sentences for extraction. We measure their performance on the DUC 2005 test data, using the Summary Content Units made available after the challenge. One algorithm matches a graph representing the entire topic against each sentence in the collection. The other algorithm checks, for pairs of open-class words in the topic, whether they can be connected in the syntactic graph of each sentence. Matching performs better than connecting words, but a combination of both methods works best. They also both favour longer sentences, which makes summaries more fluent. © 2006 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

A graph based semi-supervised approach for analysis of derivational nouns in Sanskrit 11

A graph based semi-supervised approach for analysis of deriv...

引用

11th workshop on graph-based methods for natural language processing, Textgraphs 2017, in conjunction with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

作者： Krishna, Amrith Satuluri, Pavankumar Ponnada, Harshavardhan Ahmed, Muneeb Arora, Gulab Hiware, Kaustubh Goyal, Pawan School of Linguistics and Literary Studies Chinmaya Vishwavidyapeeth CEG Campus India Dept. of Electrical Engineering Indian Institute of Technology BHU India Dept. of Computer Science and Engineering Indian Institute of Technology Kharagpur India

ISBN: (纸本)9781945626609

Derivational nouns are widely used in Sanskrit corpora and is a prevalent means of productivity in the language. Currently there exists no analyser that identifies the derivational nouns. We propose a semi supervised approach for identification of derivational nouns in Sanskrit. We not only identify the derivational words, but also link them to their corresponding source words. The novelty of our work is primarily in its design of the network structure for the task. The edge weights are featurised based on the phonetic, morphological, syntactic and the semantic similarity shared between the words to be identified. We find that our model is effective for the task, even when we employ a labelled dataset which is only 5 % to that of the entire dataset. © 2017 Association for Computational Linguistics

关键词： graphic methods

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Adapter-based Tuning for Pretrained language Model Adaptation 59

On the Effectiveness of Adapter-based Tuning for Pretrained ...

引用

作者： He, Ruidan Liu, Linlin Ye, Hai Tan, Qingyu Ding, Bosheng Cheng, Liying Low, Jia-Wei Bing, Lidong Si, Luo Alibaba Grp DAMO Acad Hangzhou Peoples R China Nanyang Technol Univ Singapore Singapore Natl Univ Singapore Singapore Singapore Singapore Univ Technol & Design Singapore Singapore

ISBN: (纸本)9781954085527

Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to finetuning. However, existing work only focuses on the parameter-efficient aspect of adapterbased tuning while lacking further investigation on its effectiveness. In this paper, we study the latter. We first show that adapterbased tuning better mitigates forgetting issues than fine-tuning since it yields representations with less deviation from those generated by the initial PrLM. We then empirically compare the two tuning methods on several downstream NLP tasks and settings. We demonstrate that 1) adapter-based tuning outperforms fine-tuning on low-resource and cross-lingual tasks;2) it is more robust to overfitting and less sensitive to changes in learning rates.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Data Driven Content Creation using Statistical and natural language processing Techniques for Financial Domain 3

Data Driven Content Creation using Statistical and Natural L...

引用

3rd Financial Narrative processing workshop, FNP 2021

作者： Chopra, Ankush Nagwanshi, Prateek Ghosh, Sohom Fidelity Investments AI CoE Bengaluru India

Over the years customers’ expectation of getting information instantaneously has given rise to the increased usage of channels like virtual assistants. Typically, customers try to get their questions answered by low-touch channels like search and virtual assistant first, before getting in touch with a live chat agent or the phone representative. Higher usage of these low-touch systems is a win-win for both customers and the organization since it enables organizations to attain a low cost of service while customers get served without delay. In this paper, we propose a two-part framework where the first part describes methods to combine the information from different interaction channels like call, search, and chat. We do this by summarizing (using a stacked Bi-LSTM network) the high-touch interaction channel data such as call and chat into short search-query like customer intents and then creating an organically grown intent taxonomy from interaction data (using Hierarchical Agglomerative Clustering). The second part of the framework focuses on extracting customer questions by analyzing interaction data sources. It calculates similarity scores using TF-IDF and BERT (Devlin et al., 2019). It also maps these identified questions to the output of the first part of the framework using syntactic and semantic similarity. © proceedings of the 3rd Financial Narrative processing workshop, FNP 2021. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MDC: An Interpretable GNNs Method based on Node Motif Degree and graph Diffusion Convolution 8th

MDC: An Interpretable GNNs Method Based on Node Motif Degre...

引用

8th China National Conference on Big Data and Social Computing, BDSC 2023

作者： Wang, Tingting Ding, Feng Luo, Naiwen Lei, Qihang Huang, Huafei Zhang, Tong Yu, Shuo School of Software Dalian University of Technology Dalian116620 China Faculty of Humanities and Social Sciences Dalian University of Technology Dalian116024 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China

ISBN: (纸本)9789819939244

graph Neural Networks (GNNs) have achieved significant success in various real-world applications, including social networks, recommendation systems, and natural language processing. One of the challenges in GNNs is their black-box nature, which limits their interpretability and hinders their applications in critical areas such as healthcare and finance. However, existing interpretability of GNNs methods mainly focus on first-hop neighbors of a node and ignores multivariate relationship, resulting in low interpretability and inaccurate predictions. To tackle this challenge, we propose a Motif Diffusion Convolution (MDC) framework with a high-order structure feature augmentation mechanism based on graph diffusion convolution. The mechanism is utilizing multivariate relationship by calculating various node motif degree to enhance the feature channel, which obtains the relationship from a higher-order structure than two directly connecting entities. For better interpretability, MDC automatically learns a set of diffusion coefficients for each feature channel via graph diffusion convolution. We conduct experiments on six real-world datasets with three baselines. The experimental results show that MDC framework can build interpretability of GNNs, and improve accuracy by 2 % on node classification benchmarks. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diffusion

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：