The term Natural Language Processing encompasses a broad set of techniques for automated generation, manipulation and analysis of natural or human languages. Although most NLP techniques inherit largely from Linguistics and Artificial Intelligence, they are also influenced by relatively newer areas such as Machine Learning, Computational Statistics and Cognitive Science. Before we see some examples of NLP techniques, it will be useful to introduce some very basic terminology. Please note that as a side effect of keeping things simple, these definitions may not stand up to strict linguistic scrutiny.
{"title":"Getting started on natural language processing with Python","authors":"Nitin Madnani","doi":"10.1145/1315325.1315330","DOIUrl":"https://doi.org/10.1145/1315325.1315330","url":null,"abstract":"The term Natural Language Processing encompasses a broad set of techniques for automated generation, manipulation and analysis of natural or human languages. Although most NLP techniques inherit largely from Linguistics and Artificial Intelligence, they are also influenced by relatively newer areas such as Machine Learning, Computational Statistics and Cognitive Science. Before we see some examples of NLP techniques, it will be useful to introduce some very basic terminology. Please note that as a side effect of keeping things simple, these definitions may not stand up to strict linguistic scrutiny.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130117537","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}
At IBM Research, Jennifer Lai (jlai@us.ibm.com) has been a key player in speech technology research, holding thirteen patents, publishing chapters for several books, and having over thirty papers appear in peer-reviewed journals and conferences. Jennifer took time out of her busy schedule to answer some questions about speech technologies for Crossroads. In the interview, Jennifer shares her expertise on designing speech interfaces, her history at IBM, and advice for undergraduate and graduate students who are interested in working with speech technologies.
在IBM研究院，Jennifer Lai (jlai@us.ibm.com)一直是语音技术研究的关键人物，拥有13项专利，为几本书出版了章节，并在同行评审的期刊和会议上发表了30多篇论文。詹妮弗从百忙之中抽出时间回答了《十字路口》的一些关于语音技术的问题。在采访中，Jennifer分享了她在设计语音界面方面的专业知识，她在IBM的经历，以及对语音技术感兴趣的本科生和研究生的建议。
{"title":"Superhuman speech by 2010: an interview with Jennifer Lai","authors":"P. Bach","doi":"10.1145/1315325.1315329","DOIUrl":"https://doi.org/10.1145/1315325.1315329","url":null,"abstract":"At IBM Research, Jennifer Lai (jlai@us.ibm.com) has been a key player in speech technology research, holding thirteen patents, publishing chapters for several books, and having over thirty papers appear in peer-reviewed journals and conferences. Jennifer took time out of her busy schedule to answer some questions about speech technologies for Crossroads. In the interview, Jennifer shares her expertise on designing speech interfaces, her history at IBM, and advice for undergraduate and graduate students who are interested in working with speech technologies.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117169246","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}
Almost any popular computer game that has been released recently draws complex three-dimensional figures as part of ordinary game play. From Warcraft's moving figures to the complex but less mobile realism of Riven or Uru, computer games display and produce shapes on the fly depending on user input. Often, the more realistic (and more complicated) the shapes, the more believable the game. For that reason, significant research has focused on the science of shape, from its generation, to its visualization and analysis.
{"title":"The science of shape: revolutionizing graphics and vision with the third dimension","authors":"J. Solomon","doi":"10.1145/1315325.1315335","DOIUrl":"https://doi.org/10.1145/1315325.1315335","url":null,"abstract":"Almost any popular computer game that has been released recently draws complex three-dimensional figures as part of ordinary game play. From Warcraft's moving figures to the complex but less mobile realism of Riven or Uru, computer games display and produce shapes on the fly depending on user input. Often, the more realistic (and more complicated) the shapes, the more believable the game. For that reason, significant research has focused on the science of shape, from its generation, to its visualization and analysis.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134150216","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}
A method for detecting voice activity comprises receiving audio signals on a plurality of channels and processing the audio signals on the channels e.g. by beamformers 200 to improve the signal-to-noise ratio thereof. The processed audio signals on each channel are then fed to associated voice activity detection algorithms 202 and further processed. A voice or silence determination is then rendered by decision logic 204 based on at least the output of the voice activity detection algorithms. The method is useful in talker localization systems e.g. for teleconferencing.
{"title":"Voice activity detection","authors":"Deepti Singh, F. Boland","doi":"10.1145/1315325.1315332","DOIUrl":"https://doi.org/10.1145/1315325.1315332","url":null,"abstract":"A method for detecting voice activity comprises receiving audio signals on a plurality of channels and processing the audio signals on the channels e.g. by beamformers 200 to improve the signal-to-noise ratio thereof. The processed audio signals on each channel are then fed to associated voice activity detection algorithms 202 and further processed. A voice or silence determination is then rendered by decision logic 204 based on at least the output of the voice activity detection algorithms. The method is useful in talker localization systems e.g. for teleconferencing.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131825502","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}
If you are interested in computers with human capabilities, vision and speech open an entirely new world of computers that can see and talk like we do. Computer vision is the moody input cousin of computer graphics-in graphics, you have all the time you can afford to program the rendering, but visual input is an unpredictable and messy reality. Computer speech is both input and output, like in systems capable of spoken dialogue.
{"title":"Introduction: computer vision and speech","authors":"N. Bernsen","doi":"10.1145/1315325.1315326","DOIUrl":"https://doi.org/10.1145/1315325.1315326","url":null,"abstract":"If you are interested in computers with human capabilities, vision and speech open an entirely new world of computers that can see and talk like we do. Computer vision is the moody input cousin of computer graphics-in graphics, you have all the time you can afford to program the rendering, but visual input is an unpredictable and messy reality. Computer speech is both input and output, like in systems capable of spoken dialogue.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124597028","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}
Most of you who are graduate students, and a few of you who are senior undergraduates, will have the pleasure of being a teaching assistant, otherwise known as a TA. A TA-ship usually consists of marking assignments and running labs. A lot of the time, students see the TA-ship as a way to make some quick extra cash, and oftentimes it is. This attitude, however, is not acceptable when you are the TA for firstyear computer science.
{"title":"At a crossroads: TA-ing first-year computer science","authors":"C. Jordan","doi":"10.1145/1315325.1315327","DOIUrl":"https://doi.org/10.1145/1315325.1315327","url":null,"abstract":"Most of you who are graduate students, and a few of you who are senior undergraduates, will have the pleasure of being a teaching assistant, otherwise known as a TA. A TA-ship usually consists of marking assignments and running labs. A lot of the time, students see the TA-ship as a way to make some quick extra cash, and oftentimes it is. This attitude, however, is not acceptable when you are the TA for firstyear computer science.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122585685","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}
This design pattern is an extension of the well-known state pattern [2], which allows an object to change its behavior depending on the internal state of the object. The behavior is defined by events, whose transformation to actions depends on the object state. This pattern introduces a way to manage state actions.
{"title":"Modeling object states and behaviors using a state action manager","authors":"G. Palfinger","doi":"10.1145/1315325.1315333","DOIUrl":"https://doi.org/10.1145/1315325.1315333","url":null,"abstract":"This design pattern is an extension of the well-known state pattern [2], which allows an object to change its behavior depending on the internal state of the object. The behavior is defined by events, whose transformation to actions depends on the object state. This pattern introduces a way to manage state actions.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114714787","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}
In what will likely become a regular feature, this issue of Crossroads introduces the Computational Recreations column. These columns will include puzzles, games, and brainteasers intended to challenge and tickle the mind. In the well-known song The Twelve Days of Christmas, each verse builds upon the previous one to describe an ever-increasing influx of gifts. But why stop after a mere twelve days when we can extend the song? Instead of a fixed number, we can continue for some arbitrary number of days! This new song, The n Days of Christmas, continues the pattern established in the original version: 1. On the first day, you receive a present of type T 1. 2. On the second day, you receive two presents of type T 2 , plus one of type T 1. 3. On the third day, you receive three presents of type T 3 , two of type T 2 , and one of type T 1. ... 4. On the n th day, you receive n presents of type T n , plus n-1 of type T n-1 , n-2 of type T n-2 , and so forth, down to one present of type T 1. Questions 1. How many presents do you receive on day n?
{"title":"Computational recreations: the n days of Christmas","authors":"Jonathan Doyle","doi":"10.1145/1315325.1315334","DOIUrl":"https://doi.org/10.1145/1315325.1315334","url":null,"abstract":"In what will likely become a regular feature, this issue of Crossroads introduces the Computational Recreations column. These columns will include puzzles, games, and brainteasers intended to challenge and tickle the mind. In the well-known song The Twelve Days of Christmas, each verse builds upon the previous one to describe an ever-increasing influx of gifts. But why stop after a mere twelve days when we can extend the song? Instead of a fixed number, we can continue for some arbitrary number of days! This new song, The n Days of Christmas, continues the pattern established in the original version: 1. On the first day, you receive a present of type T 1. 2. On the second day, you receive two presents of type T 2 , plus one of type T 1. 3. On the third day, you receive three presents of type T 3 , two of type T 2 , and one of type T 1. ... 4. On the n th day, you receive n presents of type T n , plus n-1 of type T n-1 , n-2 of type T n-2 , and so forth, down to one present of type T 1. Questions 1. How many presents do you receive on day n?","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131707888","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}
In this study, we developed an algorithmic method to analyze late contrast-enhanced (CE) magnetic resonance (MR) images, revealing the so-called hibernating myocardium. The algorithm is based on an efficient and robust image registration algorithm. Using our method, we are able to integrate the static late CE MR image with its corresponding cardiac cine MR images, constructing cardiac motion CE MR images, which are referred to as cardiac cine CE MR images. This method appears promising as an improved cardiac viability assessment tool
{"title":"Use of motion field warping to generate cardiac images","authors":"G. Gao, W. Cockshott","doi":"10.1145/1315325.1315331","DOIUrl":"https://doi.org/10.1145/1315325.1315331","url":null,"abstract":"In this study, we developed an algorithmic method to analyze late contrast-enhanced (CE) magnetic resonance (MR) images, revealing the so-called hibernating myocardium. The algorithm is based on an efficient and robust image registration algorithm. Using our method, we are able to integrate the static late CE MR image with its corresponding cardiac cine MR images, constructing cardiac motion CE MR images, which are referred to as cardiac cine CE MR images. This method appears promising as an improved cardiac viability assessment tool","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131183517","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}
Recently, it seems that there is a growing number of complaints coming out of academia regarding getting work published at good venues and the importance of having a high publication count. I am sure many of us have heard the phrase "publish or perish" before. In fact, there has been a case of a professor leaving his field of research (http://www.cs.utah.edu/~michael/leaving.html) over these issues. He criticizes the peer review process as being both fallible and corrupt in his explanation of why he left. He also discusses what he believes to be misplaced importance that many people have put on publishing at top conferences.
{"title":"At a Crossroads: peer review","authors":"C. Jordan","doi":"10.1145/1247238.1247242","DOIUrl":"https://doi.org/10.1145/1247238.1247242","url":null,"abstract":"Recently, it seems that there is a growing number of complaints coming out of academia regarding getting work published at good venues and the importance of having a high publication count. I am sure many of us have heard the phrase \"publish or perish\" before. In fact, there has been a case of a professor leaving his field of research (http://www.cs.utah.edu/~michael/leaving.html) over these issues. He criticizes the peer review process as being both fallible and corrupt in his explanation of why he left. He also discusses what he believes to be misplaced importance that many people have put on publishing at top conferences.","PeriodicalId":429016,"journal":{"name":"ACM Crossroads","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131881007","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：