The Berkeley UNIX Consultant Project

UC (UNIX Consultant) is an intelligent, natural-language interface thatallows naive users to learn about the UNIX operating system. UC wasundertaken because the task was thought to be both a fertile domain forArtificial Intelligence research and a useful application of AI work inplanning, reasoning, natural language processing, and knowledgerepresentation. The current implementation of UC comprises the followingcomponents: A language analyzer, called ALANA, that produces arepresentation of the content contained in an utterance; aninference component called a concretion mechanism that furtherrefines this content; a goal analyzer, PAGAN, that hypothesizes theplans and goals under which the user is operating; an agent, calledUCEgo, that decides on UC's goals and proposes plans for them; adomain planner, called KIP, that computes a plan to address the user'srequest; an expression mechanism, UCExpress, that determines thecontent to be communicated to the user, and a language productionmechanism, UCGen, that expresses UC's response in English. UC alsocontains a component called KNOME that builds a model of the user'sknowledge state with respect to UNIX. Another mechanism, UCTeacher,allows a user to add knowledge of both English vocabulary and factsabout UNIX to UC's knowledge base. This is done by interacting with theuser in natural language. All these aspects of UC make use of knowledgerepresented in a knowledge representation system called KODIAK. KODIAKis a relation-oriented system that is intended to have widerepresentational range and a clear semantics, while maintaining acognitive appeal. All of UC's knowledge, ranging from its most generalconcepts to the content of a particular utterance, is represented inKODIAK.     

Planning Intelligent Responses in a Natural Language System

Intelligent help systems cannot merely respond passively to the user'scommands and queries. They need to be able to volunteer information,correct user misconceptions, and reject unethical requests when appropriate.In order to do these things, a system must be designed as an intelligentagent. That is, a system needs to have its own goals and then plan forthese goals. A system which did not have its own goals would never refuseto help users perform unethical actions.Such an intelligent agent has been implemented in the UCEgo component of UC(Wilensky et al. 1984; Wilensky et al. 1988) (UNIX Consultant), a natural languagesystem that helps the user solve problems in using the UNIX operatingsystem. UCEgo provides UC with its own goals and plans. By adoptingdifferent goals in different situations, UCEgo creates and executesdifferent plans, enabling it to interact appropriately with the user.UCEgo adopts goals when it notices that the user either lacks necessaryknowledge, or has incorrect beliefs. In these cases, UCEgo plans tovolunteer information or correct the user's misconception as appropriate.These plans are pre-stored skeletal plans that are indexed under the types ofsituations in which they are typically useful. Plan suggestion situationsinclude the goal which the plan is used to achieve, the preconditions of theplan, and appropriateness conditions for the plan. Indexing plans bysituations improves efficiency and allows UC to respond appropriately to theuser in real time.Detecting situations in which a plan should be suggested or a goal adoptedis implemented using if-detected daemons. These daemons provide asingle mechanism which can be used both for detecting goals and suggestingplans. Different methodologies for the efficient implementation ofif-detected daemons are discussed.     

Generating queries and replies during information-seeking interactions

Analysis of naturally occurring information-seeking dialogues indicates that they usually consist of a number of distinct discourse segments, such as a greeting segment, a request issued by a user, an optional clarification segment, a transfer of information segment and a final closing segment. The clarification interaction is often initiated by the information provider and it may be due to one of the following reasons: (1) there is confusion regarding the user's intentions, (2) there is insufficient information to formulate a plan to satisfy a recognized intention, or (3) there is difficulty in formulating a plan that satisfies a recognized intention. Once the information provider determines the user's intention and formulates a plan to achieve this intention, the information transfer phase is initiated to inform the user about the proposed plan.In this paper, we present a mechanism for generating queries during the clarification stage and answers during the information transfer stage. Given a hierarchical representation of the alternatives possibly intended by a user and the probabilities of these alternatives, our mechanism determines the hierarchy level at which a query must be directed and the query to be posed in order to determine the alternative intended by the user. Once the user's intentions are ascertained, the mechanism determines whether additional information is required and the manner in which queries may be posed to acquire this information. When a user's intentions cannot be satisfied by means of a single plan, our mechanism enters into a negotiation process to alter the user's specifications until a valid plan is formulated. In the final stages of the interaction, the mechanism determines the information to be transferred and generates an answer to effect the transfer. The mechanisms for negotiation and for the generation of queries and answers described in this paper have been implemented in a system called , a computerized information providing system that functions as a travel agent.     

Panorama: A database system that annotates its answers to queries with their properties

When responding to queries, humans often volunteer additional information about their answers. Among other things, they may qualify the answer as to its reliability, and they may characterize it abstractly. This paper describes a relational database system that similarly annotates its answers with their properties. The process assumes that various assertions about properties of the data have been stored in the database (meta-information). These assertions are then used to infer properties of each answer provided by the system (meta-answers). Meta-answers are offered to users along with each answer issued, and help them to assess the value and meaning of the information that they receive. The advantages of the method described include: (1) It is extensible in that it allows users to determine the kinds of properties that the system will maintain and manipulate. (2) It has a built-in mechanism for determining the relevance of computed meta-information. (3) It is efficient: the number of operations required for meta-processing a given query can be expressed as a polynomial in the size of the meta-database. (4) It can be implemented externally with any commercial relational database system.     

A knowledge-based system for generating informative responses to indirect database queries

The objective of this study is to develop a knowledge-base framework for generatingcooperative answers to indirect queries. Anindirect query can be considered as a nonstandard database query in which a user did not specify explicitly the information request. In a cooperative query answering system, a user's indirect query should be answered with an informative response, either anaffirmative response or anegative response, which is generated on the basis of the inference of the user's information request and the reformulation of the users' indirect query.This paper presents methods for inferring users' intended actions, determining users' information requirements, and for automatically reformulating indirect queries into direct queries. The inference process is carried out on the basis of a user model, calluser action model, as well as the query context. Two kinds ofinformative responses, i.e.affirmative responses andnegative responses can be generated by arule-based approach.     

面向自然交互的多通道人机对话系统中答句自动生成方法

多通道自然人机对话系统要求计算机能够对用户的语句产生智能应答,传统的人机对话系统由于知识库的限制以及用户话语的随意性,当对话内容超出知识库范围时,系统将无法应答或产生与用户期望不符的回答,这在一定程度上影响了人机对话系统用户的体验感.为了解决该问题,提出了一种融合多模态历史交互信息和面向数据的句法分析(data-oriented parsing,简称DOP)模型的最优答句生成方法:首先从大规模句法树库中提取上下文无关文法的语法规则,然后结合对话过程中用户呈现的表情、姿态等多模态历史交互信息,融合DOP模型对上下文无关文法生成的汉语句子进行过滤,最终生成一个符合语法规则且符合语义的答句返回给用户,让计算机在无法获得知识库支撑时,根据交互历史信息生成应对当前对话的语句,有效地提升了多通道自然人机交互系统用户的体验感.该方法应用于交通信息查询以及咖啡厅的多主题多模态人机自由对话系统.用户的体验表明,该方法能够有效提高用户交互的自然度和体验感.     

Dynamically generated follow-up questions

Automatic text generators are at the heart of systems that provide users with information. The trick is getting the system to answer follow-up questions as naturally as possible. We have devised a direct manipulation interface that treats system-generated texts as structured objects that users can manipulate. With our interface, users select the portions of system-generated text that they don't understand or want more information about, and the system provides a menu of questions to ask. Question menus, generated on the fly, take into account the user model, underlying knowledge base(s), and the prior discourse context     

A Web-Based Platform for User-Interactive Question-Answering

A user-interactive question-answering (QA) platform named BuyAns (at ) is presented. The platform is a special kind of online community and mainly features a rewarding scheme for answering questions among all users, a pattern-based user interface (UI) for questioning and answering, and a pattern-based representation and storage scheme for accumulated question-answer pairs. The system actually proposes and promotes a C2C business model for exchanging and commercializing knowledge from ordinary people. It can also be used as an incentive and collaborative approach to knowledge acquisition. Driven by the business model, prompt and quality answers are quickly accumulated. Due to the patterns used, accurate answers can be provided automatically for repeated questions. Facilitating features and technologies, including user modeling, reputation management, and answer clustering and fusion, are also developed and briefly described. Preliminary user studies show the potential attraction of the system to its users as well as reasonable usability and user-satisfaction. We anticipate hot applications of such a system in the Web 2.0 era.     

基于Guillou—Quisquater数字签名的几种应用方案

随着计算机和网络通信技术的发展,数字签名技术得到了广泛的应用,本文以Guillou-Quisquater为基础设计了群体数字签名和零知识用户鉴别2种应用方案。群体数字签名允许多人分别签署同一份文件,然后所有的个体签名组成同一份群体签名,零知识用户鉴别可以让用户在不暴露自己的秘密信息的情况下进行身份验证。     

The role of the user's domain knowledge in generation

A question-answering program that provides access to a large amount of data will be most useful if it can tailor its answers to each individual user. In particular, a user's level of knowledge about the domain of discourse is an important factor in this tailoring if the answer provided is to be both informative and understandable to the user. In this research, we address the issue of how the user's domain knowledge, or the level of expertise, might affect an answer. We present TAILOR, a flexible computer system that takes into account this knowledge to provide an answer that is appropriate for users with varying levels of expertise (including novices and experts), without requiring an a priori set of user types.
Un programme qui donne accès à un système de connaissances à de nombreux et divers utilisateurs serait plus utile s'il pouvait adapter ses réponses pour chaque utilisateur. En particulier, le savoir de l'utilisateur est un facteur important pour que la réponse soit compréhensible et informative. Dans cet article, nous étudions le rle de la connaissance de l'utilisateur pour former un texte qui soit approprié pour la personne qui le lira. Nous présentons TAILOR, un système de génération flexible qui est sensitif au niveau de connaissance de l'utilisateur. TAILOR peut générer des textes appropries pour des utilisateurs aux niveaux de connaissances très variés, sans avoir besoin ďun groupe de stéréotypes définis a priori.     

Experimenting with a Question Answering System for the Arabic Language

The World Wide Web (WWW) today is so vast that it has become more and more difficult to find answers to questions using standard search engines. Current search engines can return ranked lists of documents, but they do not deliver direct answers to the user. The goal of Open Domain Question Answering (QA) systems is to take a natural language question, understand the meaning of the question, and present a short answer as a response based on a repository of information. In this paper we present QARAB, a QA system that combines techniques from Information Retrieval and Natural Language Processing. This combination enables domain independence. The system takes natural language questions expressed in the Arabic language and attempts to provide short answers in Arabic. To do so, it attempts to discover what the user wants by analyzing the question and a variety of candidate answers from a linguistic point of view.     

基于用户兴趣的搜索引擎

随着WWW的出现和发展,Internet上出现的信息迅速增长.如何从大量的信息中获取有用的信息,正成为信息领域的关键技术.传统的搜索引擎没有考虑不同用户的兴趣,因此搜索出来的结果往往无法满足不同用户的特定需求.提出一种用户兴趣模型,能够有效表示用户兴趣,并对传统搜索引擎的搜索结果进行匹配度计算,从而将符合用户兴趣的结果返回给用户.基于这种模型开发了一个基于用户兴趣的法律领域的搜索引擎MyLaw.     

The virtual library secretary: A user model-based software agent

A user model comprises knowledge of the user's past and present tasks, and is the essential element in adaptive user interfaces. Through the propagation of user models, we can take the user models into the world of software agents, and thus construct user model-based software agents. The user model approach reduces the threats of software agents penetrating a local host and the amount of data transferred. This paper presents the Virtual Library Secretary, which is a user model-based software agent system. The Virtual Library Secretary offers information retrieval and information filtering to the user. The system is part of the Virtual Secretary project. The user model is established by a simple neural network. In this way, the agent is able to learn and adapt to the user's behaviour. This paper discusses the user model concept, presents the Virtual Secretary system architecture and describes how this architecture works through the Virtual Library Secretary.The Virtual Secretary project is an on-going project at the University of Tromsø. It includes two phases: the first phase (ViSe) focuses on user model-based software agents for information filtering and agent control propagation; the second phase (ViSe2) concentrates on information integration via cooperative agents in a distributed environment. The project is partly supported by the Research Council of Norway (Grant no. 112577/431).     

Generating help for users of application software

Help for users of Information Processing Systems (IPSs) is typically based upon the presentation of pre-stored texts written by the system designers for predictable situations. Though advances in user interface technology have eased the process of requesting advice, current on-line help facilities remain tied to a back-end of canned answers, spooled onto users, screens to describe queried facilities.This paper argues that the combination of a user's knowledge of an application and the particular states which a system can assume require different answers for the large number of possible situations. Thus, a marriage of techniques from the fields of text generation and Intelligent Help Systems research is needed to construct responses dynamically. Furthermore, it is claimed that the help texts should attempt to address not only the immediate needs of the user, but to facilitate learning of the system by incorporating a variety of educational techniques to specialise answers in given contexts.A computational scheme for help text generation based on schema of rhetorical predicates is presented. Using knowledge of applications programs and their users, it is possible to provide a variety of answers in response to a number of questions. The approach uses object-oriented techniques to combine different information from a variety of sources in a flexible manner, yielding responses which are appropriate to the state of the IPS and to the user's level of knowledge.Modifications to the scheme which resulted from its evaluation in the EUROHELP project are described, together with ongoing collaborative work and further research developments.Colin Tattersall is a Research Fellow at the Computer Based Learning Unit. He completed his B. Sc. in Computational Studies at Leeds University in 1986, then joined the CBL Unit on an ESRC studentship linked to ESPRIT project P280 EUROHELP. Within the project, his work related to knowledge representation and text generation for intelligent help systems, leading to a Ph.D. in mid-1990 entitled Question-answering and explanation in online help systems: a knowledge-based approach. The work was followed by a year-long fellowship, funded by ICL, to investigate the commercial viability of advanced help system architectures. This paper reflects results and experience gained from both research and development of intelligent help systems.     

Incorporating statistical information into expert classification systems to reduce classification costs

Interactive expert systems seek relevant information from a user in order to answer a query or to solve a problem that the user has posed. A fundamental design issue for such a system is therefore itsinformation-seeking strategy, which determines the order in which it asks questions or performs experiments to gain the information that it needs to respond to the user. This paper examines the problem of optimal knowledge acquisition through questioning in contexts where it is expensive or time-consuming to obtain the answers to questions. An abstract model of an expert classification system — considered as a set of logical classification rules supplemented by some statistical knowledge about attribute frequencies — is developed and applied to analyze the complexity and to present constructive algorithms for doing probabilistic question-based classification. New heuristics are presented that generalize previous results for optimal identification keys and questionnaires. For an important class of discrete discriminant analysis problems, these heuristics find optimal or near-optimal questioning strategies in a small fraction of the time required by an exact solution algorithm.     

PVA: A Self-Adaptive Personal View Agent

In this paper, we present PVA, an adaptive personal view information agent system for tracking, learning and managing user interests in Internet documents. PVA consists of three parts: a proxy, personal view constructor, and personal view maintainer. The proxy logs the user's activities and extracts the user's interests without user intervention. The personal view constructor mines user interests and maps them to a class hierarchy (i.e., personal view). The personal view maintainer synchronizes user interests and the personal view periodically. When user interests change, in PVA, not only the contents, but also the structure of the user profile are modified to adapt to the changes. In addition, PVA considers the aging problem of user interests. The experimental results show that modulating the structure of the user profile increases the accuracy of a personalization system.     

The OODB path-method generator (PMG) using access weights and precomputed access relevance

A path-method is used as a mechanism in object-oriented databases (OODBs) to retrieve or to update information relevant to one class that is not stored with that class but with some other class. A path-method is a method which traverses from one class through a chain of connections between classes and accesses information at another class. However, it is a difficult task for a casual user or even an application programmer to write path-methods to facilitate queries. This is because it might require comprehensive knowledge of many classes of the conceptual schema that are not directly involved in the query, and therefore may not even be included in a user's (incomplete) view about the contents of the database. We have developed a system, called path-method generator (PMG), which generates path-methods automatically according to a user's database-manipulating requests. The PMG offers the user one of the possible path-methods and the user verifies from his knowledge of the intended purpose of the request whether that path-method is the desired one. If the path method is rejected, then the user can utilize his now increased knowledge about the database to request (with additional parameters given) another offer from the PMG. The PMG is based on access weights attached to the connections between classes and precomputed access relevance between every pair of classes of the OODB. Specific rules for access weight assignment and algorithms for computing access relevance appeared in our previous papers [MGPF92, MGPF93, MGPF96]. In this paper, we present a variety of traversal algorithms based on access weights and precomputed access relevance. Experiments identify some of these algorithms as very successful in generating most desired path-methods. The PMG system utilizes these successful algorithms and is thus an efficient tool for aiding the user with the difficult task of querying and updating a large OODB. Received July 19, 1993 / Accepted May 16, 1997     

基于加权潜在语义分析的答案抽取

问答系统应该能够用准确、简洁的语言回答用户用自然语言提出的问题,其关键和核心实现技术是答案抽取。结合关键词在用户问句和返回文档中的权重,通过潜在语义分析技术实现了中文问答系统中的答案抽取。实验结果表明,加权LSA的MRR值要明显优于未加权LSA和空间向量模型的MRR值,实际用于回答用户提出的问题具有较好的效果。     

基于HowNet语义相似度的FAQ研究

FAQ是网站提供在线帮助的主要手段。利用检索机制根据用户提出的问题建立一个候选问句集,利用知网研究了用户问句和候选问句之间的相似度,从中找出最相似的问句,并将相应答案返回给用户。实验表明,该方法提高了问句匹配的准确率。     

Triggering information by context

With the increased availability of personal computers with attached sensors to capture their environment, there is a big opportunity forcontext-aware applications; these automatically provide information and/or take actions according to the user's present context, as detected by sensors. When well designed, these applications provide an opportunity to tailor the provision of information closely to the user's current needs. A sub-set of context-aware applications arediscrete applications, where discrete pieces of information are attached to individual contexts, to be triggered when the user enters those contexts. The advantage of discrete applications is that authoring them can be solely a creative process rather than a programming process: it can be a task akin to creating simple web pages. This paper looks at a general system that can be used in any discrete context-aware application. It propounds a general triggering rule, and investigates how this rule applies in practical applications.