发布求助
文献互助 智能选刊 最新文献

Workshop on Continuous Vector Space Models and their Compositionality最新文献

筛选
英文 中文
Observed versus latent features for knowledge base and text inference 知识库与文本推理的观察特征与潜在特征
Workshop on Continuous Vector Space Models and their Compositionality Pub Date : 2015-07-30 DOI: 10.18653/v1/W15-4007
Kristina Toutanova, Danqi Chen
{"title":"Observed versus latent features for knowledge base and text inference","authors":"Kristina Toutanova, Danqi Chen","doi":"10.18653/v1/W15-4007","DOIUrl":"https://doi.org/10.18653/v1/W15-4007","url":null,"abstract":"In this paper we show the surprising effectiveness of a simple observed features model in comparison to latent feature models on two benchmark knowledge base completion datasets, FB15K and WN18. We also compare latent and observed feature models on a more challenging dataset derived from FB15K, and additionally coupled with textual mentions from a web-scale corpus. We show that the observed features model is most effective at capturing the information present for entity pairs with textual relations, and a combination of the two combines the strengths of both model types.","PeriodicalId":430104,"journal":{"name":"Workshop on Continuous Vector Space Models and their Compositionality","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125272945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 721
Concept Extensions as the Basis for Vector-Space Semantics: Combining Distributional and Ontological Information about Entities 概念扩展作为向量空间语义的基础:结合实体的分布信息和本体信息
Workshop on Continuous Vector Space Models and their Compositionality Pub Date : 2015-07-01 DOI: 10.18653/v1/W15-4003
J. Cheung
{"title":"Concept Extensions as the Basis for Vector-Space Semantics: Combining Distributional and Ontological Information about Entities","authors":"J. Cheung","doi":"10.18653/v1/W15-4003","DOIUrl":"https://doi.org/10.18653/v1/W15-4003","url":null,"abstract":"We propose to base the development of vector-space models of semantics on concept extensions, which defines concepts to be sets of entities. We investigate two sources of knowledge about entities that could be relevant: distributional information provided by word or phrase embeddings, and ontological information derived from a knowledge base. We develop a feedforward neural network architecture to learn entity representations that are used to predict their concept memberships, and show that the two sources of information are actually complementary. In an entity ranking experiment, the combination approach that uses both types of information outperforms models that only rely on one of the two. We also perform an analysis of the output using fuzzy logic techniques to demonstrate the potential of learning concept extensions for supporting inference involving classical semantic operations.","PeriodicalId":430104,"journal":{"name":"Workshop on Continuous Vector Space Models and their Compositionality","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115209846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Exploring the effect of semantic similarity for Phrase-based Machine Translation 探讨语义相似度在基于短语的机器翻译中的作用
Workshop on Continuous Vector Space Models and their Compositionality Pub Date : 2015-07-01 DOI: 10.18653/v1/w15-4005
Kunal Sachdeva, D. Sharma
{"title":"Exploring the effect of semantic similarity for Phrase-based Machine Translation","authors":"Kunal Sachdeva, D. Sharma","doi":"10.18653/v1/w15-4005","DOIUrl":"https://doi.org/10.18653/v1/w15-4005","url":null,"abstract":"The paper investigates the use of semantic similarity scores as feature in the phrase based machine translation system. We propose the use of partial least square regression to learn the bilingual word embedding using compositional distributional semantics. The model outperforms the baseline system which is shown by an increase in BLEU score. We also show the effect of varying the vector dimension and context window for two different approaches of learning word vectors.","PeriodicalId":430104,"journal":{"name":"Workshop on Continuous Vector Space Models and their Compositionality","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116571698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Joint Semantic Relevance Learning with Text Data and Graph Knowledge 基于文本数据和图形知识的联合语义关联学习
Workshop on Continuous Vector Space Models and their Compositionality Pub Date : 2015-07-01 DOI: 10.18653/v1/W15-4004
Dongxu Zhang, Bin Yuan, Dong Wang, Rong Liu
{"title":"Joint Semantic Relevance Learning with Text Data and Graph Knowledge","authors":"Dongxu Zhang, Bin Yuan, Dong Wang, Rong Liu","doi":"10.18653/v1/W15-4004","DOIUrl":"https://doi.org/10.18653/v1/W15-4004","url":null,"abstract":"Inferring semantic relevance among entities (e.g., entries of Wikipedia) is important and challenging. According to the information resources, the inference can be categorized into learning with either raw text data, or labeled text data (e.g., wiki page), or graph knowledge (e.g, WordNet). Although graph knowledge tends to be more reliable, text data is much less costly and offers a better coverage. We show in this paper that different resources are complementary and can be combined to improve semantic learning. Particularly, we present a joint learning approach that learns vectors of entities by leveraging resources of both text data and graph knowledge. The experiments conducted on the semantic relatedness task show that text-based learning works well on general domain tasks, however for tasks in specific domains, joint learning that involves both text data and graph knowledge offers significant improvement.","PeriodicalId":430104,"journal":{"name":"Workshop on Continuous Vector Space Models and their Compositionality","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129468843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 34
Incremental Adaptation Strategies for Neural Network Language Models 神经网络语言模型的增量适应策略
Workshop on Continuous Vector Space Models and their Compositionality Pub Date : 2014-12-20 DOI: 10.18653/v1/W15-4006
Aram Ter-Sarkisov, Holger Schwenk, Fethi Bougares, Loïc Barrault
{"title":"Incremental Adaptation Strategies for Neural Network Language Models","authors":"Aram Ter-Sarkisov, Holger Schwenk, Fethi Bougares, Loïc Barrault","doi":"10.18653/v1/W15-4006","DOIUrl":"https://doi.org/10.18653/v1/W15-4006","url":null,"abstract":"It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take several days. We present efficient techniques to adapt a neural network language model to new data. Instead of training a completely new model or relying on mixture approaches, we propose two new methods: continued training on resampled data or insertion of adaptation layers. We present experimental results in an CAT environment where the post-edits of professional translators are used to improve an SMT system. Both methods are very fast and achieve significant improvements without overfitting the small adaptation data.","PeriodicalId":430104,"journal":{"name":"Workshop on Continuous Vector Space Models and their Compositionality","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130202142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 15
Recursive Neural Networks Can Learn Logical Semantics 递归神经网络可以学习逻辑语义
Workshop on Continuous Vector Space Models and their Compositionality Pub Date : 2014-06-06 DOI: 10.18653/v1/W15-4002
Samuel R. Bowman, Christopher Potts, Christopher D. Manning
{"title":"Recursive Neural Networks Can Learn Logical Semantics","authors":"Samuel R. Bowman, Christopher Potts, Christopher D. Manning","doi":"10.18653/v1/W15-4002","DOIUrl":"https://doi.org/10.18653/v1/W15-4002","url":null,"abstract":"Tree-structured recursive neural networks (TreeRNNs) for sentence meaning have been successful for many applications, but it remains an open question whether the fixed-length representations that they learn can support tasks as demanding as logical deduction. We pursue this question by evaluating whether two such models---plain TreeRNNs and tree-structured neural tensor networks (TreeRNTNs)---can correctly learn to identify logical relationships such as entailment and contradiction using these representations. In our first set of experiments, we generate artificial data from a logical grammar and use it to evaluate the models' ability to learn to handle basic relational reasoning, recursive structures, and quantification. We then evaluate the models on the more natural SICK challenge data. Both models perform competitively on the SICK data and generalize well in all three experiments on simulated data, suggesting that they can learn suitable representations for logical inference in natural language.","PeriodicalId":430104,"journal":{"name":"Workshop on Continuous Vector Space Models and their Compositionality","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116574787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 133
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书