Trans Type: Development-Evaluation Cycles to Boost Translator's Productivity

We present TransType: a new approach to Machine-Aided Translation in which the human translator maintains control of the translation process while being helped by real-time completions proposed by a statistical translation engine. The TransType approach is first presented through a series of prototypes that illustrate their underlying translation model and graphical interface. The results of two rounds of in situ evaluation of TransType prototypes are discussed followed by a set of lessons learned in these experiments. It will be shown that this approach is valued by translators but given the short time allotted for the evaluation, translators were not able to quantitatively increase their productivity. TransType is compared with other approaches and new perspectives are elaborated for a new version being developed in the context of a Fifth Framework European Community Project. This revised version was published online in November 2006 with corrections to the Cover Date.     

Head-Transducer Models for Speech Translation and Their Automatic Acquisition from Bilingual Data

This article presents statistical language translation models,called dependency transduction models, based on collectionsof head transducers. Head transducers are middle-out finite-state transducers which translate a head word in a source stringinto its corresponding head in the target language, and furthertranslate sequences of dependents of the source head into sequencesof dependents of the target head. The models are intended to capturethe lexical sensitivity of direct statistical translation models,while at the same time taking account of the hierarchical phrasalstructure of language. Head transducers are suitable for directrecursive lexical translation, and are simple enough to be trainedfully automatically. We present a method for fully automatictraining of dependency transduction models for which the only inputis transcribed and translated speech utterances. The method has beenapplied to create English–Spanish and English–Japanese translationmodels for speech translation applications. The dependencytransduction model gives around 75% accuracy for an English–Spanishtranslation task (using a simple string edit-distance measure) and70% for an English–Japanese translation task. Enhanced with targetn-grams and a case-based component, English–Spanish accuracy is over76%; for English–Japanese it is 73% for transcribed speech, and60% for translation from recognition word lattices.     

用户体验质量(QoE)的模型与评价方法综述

随着信息时代的到来,新的多样性的信息服务大量涌现,人们对信息服务的要求也越来越高.为了获得用户对服务的认可,服务提供商必须确保良好的用户体验质量.因此,用户体验质量不仅成为学术界重要的研究课题之一,而且也成为工业界关键的服务评价指标之一.文中综述了用户体验质量的模型与评价方法等方面的工作.介绍了该领域的研究现状与进展,总结归纳了用户体验质量的影响因素、量化方法及三类评价方法学,重点讨论了几种具体的基于不同学科的用户体验质量的模型和评价方法.基于这些讨论,该文以视频流媒体服务为背景,提出了基于隐马尔可夫的用户体验质量模型,建立了基于随机模型的评价方法,对未来的研究方向进行了展望.     

A syntactically informed reordering model for statistical machine translation

Word reordering is one of the challengeable problems of machine translation. It is an important factor of quality and efficiency of machine translation systems. In this paper, we introduce a novel reordering model based on an innovative structure, named, phrasal dependency tree. The phrasal dependency tree is a modern syntactic structure which is based on dependency relationships between contiguous non-syntactic phrases. The proposed model integrates syntactical and statistical information in the context of log-linear model aimed at dealing with the reordering problems. It benefits from phrase dependencies, translation directions (orientations) and translation discontinuity between translated phrases. In comparison with well-known and popular reordering models such as distortion, lexicalised and hierarchical models, the experimental study demonstrates the superiority of our model in terms of translation quality. Performance is evaluated for Persian → English and English → German translation tasks using Tehran parallel corpus and WMT07 benchmarks, respectively. The results report 1.54/1.7 and 1.98/3.01 point improvements over the baseline in terms of BLEU/TER metrics on Persian → English and German → English translation tasks, respectively. On average our model retrieved a significant impact on precision with comparable recall value with respect to the lexicalised and distortion models.     

Maximum Entropy Modeling: A Suitable Framework to Learn Context-Dependent Lexicon Models for Statistical Machine Translation

Current statistical machine translation systems are mainly based on statistical word lexicons. However, these models are usually context-independent, therefore, the disambiguation of the translation of a source word must be carried out using other probabilistic distributions (distortion distributions and statistical language models). One efficient way to add contextual information to the statistical lexicons is based on maximum entropy modeling. In that framework, the context is introduced through feature functions that allow us to automatically learn context-dependent lexicon models.In a first approach, maximum entropy modeling is carried out after a process of learning standard statistical models (alignment and lexicon). In a second approach, the maximum entropy modeling is integrated in the expectation-maximization process of learning standard statistical models.Experimental results were obtained for two well-known tasks, the French–English Canadian Parliament Hansards task and the German–English Verbmobil task. These results proved that the use of maximum entropy models in both approaches, can help to improve the performance of the statistical translation systems.This work has been partially supported by the European Union under grant IST-2001-32091 and by the Spanish CICYT under project TIC-2003-08681-C02-02. The experiments on the Verbmobil task were done when the first author was a visiting scientist at RWTH Aachen-Germany.Editors: Dan Roth and Pascale Fung     

Heterogeneous learning in the Doppelgänger user modeling system

Doppelgänger is a generalized user modeling system that gathers data about users, performs inferences upon the data, and makes the resulting information available to applications.Doppelgänger's learning is calledheterogeneous for two reasons: first, multiple learning techniques are used to interpret the data, and second, the learning techniques must often grapple with disparate data types. These computations take place at geographically distributed sites, and make use of portable user models carried by individuals. This paper concentrates onDoppelgänger's learning techniques and their implementation in an application-independent, sensor-independent environment.     

Pivot language approach for phrase-based statistical machine translation

This paper proposes a novel method for phrase-based statistical machine translation based on the use of a pivot language. To translate between languages L _s and L _t with limited bilingual resources, we bring in a third language, L _p , called the pivot language. For the language pairs L _s  − L _p and L _p  − L _t , there exist large bilingual corpora. Using only L _s  − L _p and L _p  − L _t bilingual corpora, we can build a translation model for L _s  − L _t . The advantage of this method lies in the fact that we can perform translation between L _s and L _t even if there is no bilingual corpus available for this language pair. Using BLEU as a metric, our pivot language approach significantly outperforms the standard model trained on a small bilingual corpus. Moreover, with a small L _s  − L _t bilingual corpus available, our method can further improve translation quality by using the additional L _s  − L _p and L _p  − L _t bilingual corpora.     

Target-Text Mediated Interactive Machine Translation

The use of Machine Translation as a tool for professional or other highly skilled translators is for the most part currently limited to postediting arrangements in which the translator invokes MT when desired and then manually cleans up the results. A theoretically promising but hitherto largely unsuccessful alternative to postediting for this application is interactive machine translation (IMT), in which the translator and MT system work in tandem. We argue that past failures to make IMT viable as a tool for skilled translators have been the result of an infelicitous mode of interaction rather than any inherent flaw in the idea. As a solution, we propose a new style of IMT in which the target text under construction serves as the medium of communication between an MT system and its user. We describe the design, implementation, and performance of an automatic word completion system for translators which is intended to demonstrate the feasibility of the proposed approach, albeit in a very rudimentary form.     

A Neural Syntactic Language Model

This paper presents a study of using neural probabilistic models in a syntactic based language model. The neural probabilistic model makes use of a distributed representation of the items in the conditioning history, and is powerful in capturing long dependencies. Employing neural network based models in the syntactic based language model enables it to use efficiently the large amount of information available in a syntactic parse in estimating the next word in a string. Several scenarios of integrating neural networks in the syntactic based language model are presented, accompanied by the derivation of the training procedures involved. Experiments on the UPenn Treebank and the Wall Street Journal corpus show significant improvements in perplexity and word error rate over the baseline SLM. Furthermore, comparisons with the standard and neural net based N-gram models with arbitrarily long contexts show that the syntactic information is in fact very helpful in estimating the word string probability. Overall, our neural syntactic based model achieves the best published results in perplexity and WER for the given data sets.This work was supported by the National Science Foundation under grant No. IIS-0085940.Editors: Dan Roth and Pascale Fung     

CONTEXTUAL LANGUAGE MODELS FOR RANKING ANSWERS TO NATURAL LANGUAGE DEFINITION QUESTIONS

Question–answering systems make good use of knowledge bases (KBs, e.g., Wikipedia) for responding to definition queries. Typically, systems extract relevant facts from articles regarding the question across KBs, and then they are projected into the candidate answers. However, studies have shown that the performance of this kind of method suddenly drops, whenever KBs supply narrow coverage. This work describes a new approach to deal with this problem by constructing context models for scoring candidate answers, which are, more precisely, statistical n‐gram language models inferred from lexicalized dependency paths extracted from Wikipedia abstracts. Unlike state‐of‐the‐art approaches, context models are created by capturing the semantics of candidate answers (e.g., “novel,”“singer,”“coach,” and “city”). This work is extended by investigating the impact on context models of extra linguistic knowledge such as part‐of‐speech tagging and named‐entity recognition. Results showed the effectiveness of context models as n‐gram lexicalized dependency paths and promising context indicators for the presence of definitions in natural language texts.     

基于用户行为模型的计算机辅助翻译方法

与全自动机器翻译相比,计算机辅助翻译技术更具实用性,已成为机器翻译领域的一个研究热点.传统的辅助翻译过程中,用户只能被动接受系统提供的辅助译文,并进行翻译后编辑操作.该文提出一种基于用户行为模型的辅助翻译方法,通过实时记录用户的后编辑过程,分析出用户的翻译决策,建立用户行为模型,使得翻译系统能够动态获取和共享用户的翻译...     

The Role of Instructional Design in Persuasion: A Comics Approach for Improving Cybersecurity

Abstract

Although computer security technologies are the first line of defense to secure users, their success is dependent on individuals’ behavior. It is therefore necessary to persuade users to practice good computer security. This interview analysis of users’ conceptualization of security password guessing attacks, antivirus protection, and mobile online privacy shows that poor understanding of security threats influences users’ motivation and ability to practice safe behaviors. An online interactive comic series called Secure Comics was designed and developed based on instructional design principles to address this problem. An eye-tracking experiment suggests that the graphical and interactive components of the comics direct users’ attention and facilitate comprehension of the information. In the evaluations of Secure Comics, results from several user studies show that the comics improve understanding and motivate positive changes in security management behavior. The implication of the findings to better understand the role of instructional design and persuasion in education technology are discussed.     

基于句法的统计机器翻译模型与方法

该文总结了我们近几年来在基于句法的统计机器翻译方面所做的研究工作,特别是基于源语言句法的一系列统计机器翻译模型与方法,具体包括 基于最大熵括号转录语法的翻译模型,基于源语言短语结构树的树到串翻译模型及其相应的基于树的翻译方法,基于森林的翻译方法和句法分析与解码一体化翻译方法,基于源语言依存树的翻译模型。     

面向统计机器翻译的重对齐方法研究

词对齐是统计机器翻译中的重要技术之一。该文提出了一种重对齐方法,它在IBM models获得的正反双向词对齐的基础上,确定出正反双向对齐不一致的部分。之后,对双向词对齐不一致的部分进行重新对齐以得到更好的对称化的词对齐结果。此外,该文提出的方法还可以利用大规模单语语料来强化对齐结果。实验结果表明,相比在统计机器翻译中广泛使用的基于启发信息的词对齐对称化方法,该文提出的方法可以使统计机器翻译系统得到更高的翻译准确率。     

Exploring Privacy Management on Facebook: Motivations and Perceived Consequences of Voluntary Disclosure

This study examined the perceived motivations and consequences of voluntary disclosure of Facebook active users using a survey administered to college students in a public‐speaking course. College‐age students who took the survey were motivated to use Facebook because they perceived their relationships improved with friends and family, although using Facebook could become negatively habit forming. The research suggests that users of Facebook use it more for disclosing to distant friends rather than to close friends, which is divergent from most early disclosure research that equates disclosure with intimacy. This research utilizes Communication Privacy Management Theory for the theoretical framework.     

Statistical Translation of Text and Speech: First Results with the RWTH System

In this paper, we describe a first version of a system for statisticaltranslation and present experimental results. The statistical translationapproach uses two types of information: a translation model and a languagemodel. The language model used is a standard bigram model. The translationmodel is decomposed into lexical and alignment models. After presenting the details of the alignment model, we describe the search problem and present a dynamic programming-based solution for the special case of monotone alignments.So far, the system has been tested on two limited-domain tasks for which abilingual corpus is available: the EuTrans traveller task (Spanish–English,500-word vocabulary) and the Verbmobil task (German–English, 3000-wordvocabulary). We present experimental results on these tasks. In addition to the translation of text input, we also address the problem of speech translation and suitable integration of the acoustic recognition process and the translation process.     

Automated Query Formulation Using an Entity–Relationship Conceptual Schema

Significant effort is expended in developing a high-level conceptual schema for a relational database. However, criticalknowledge is often discarded when the conceptual schema is mapped to aset of relation schemas. As a result, designers and users must employsparser logical-level knowledge to access data. Unfortunately, naiveusers do not possess the detailed logical-level knowledge required toformulate queries corresponding to ad hoc requests. Auniversal relation interface can shield users from underlyingdesign details. However, most universal relation systems have beenbased on abstractions not typically used by database designers.Consequently, the usefulness of these interfaces has been limited.This article demonstrates how an Entity-Relationship (ER) conceptualschema can be used by a high-level interface to formulate queriesautomatically. The notion of contextsis introduced to describethe segmentation of an ER conceptual schema into overlapping subgraphsthat correspond to sets of relations that can be joined in a losslessmanner. Given a set of contexts, natural join query formulation isstraightforward. As demonstrated with a case study using theprototype QUICK system, the techniques presented facilitate theconstruction of high-level, intelligent interfaces.     

Statistical morphology and Bayesian reconstruction

The aim of this paper is to show that basic morphological operations can be incorporated within a statistical physics formulation as a limit when the temperature of the system tends to zero. These operations can then be expressed in terms of finding minimum-variance estimators of probability distributions. It enables us to relate these operations to alternative Bayesian or Markovian approaches to image analysis.We first show how to derive elementary dilations (winner-take-all) and erosions (loser-take-all). These operations, referred to as statistical dilations and erosion, depend on a temperature parameter =1/T. They become purely morphological as goes to infinity and become purely linear averages as goes to zero. Experimental results are given for a range of intermediate values of . Concatenations of elementary operations can be naturally expressed by stringing together conditional probability distributions, each corresponding to the original operations, thus yielding statistical openings and closings. Techniques are given for computing the minimum-variance estimators. Finally, we describe simulations comparing statistical morphology and Bayesian methods for image smoothing, edge detection, and noise reduction.     

Linking card sorting to browsing performance – are congruent municipal websites more efficient to use?

Card sorting is a method for eliciting mental models and is frequently used for creating efficient website navigation structures. The present studies set out to validate card sorting by linking browsing performance to the degree of match between the mental model and the navigation structure. First, a card sorting study was conducted (n?=?27) to elicit users’ mental model of municipal websites. Second, performance was measured for a number of search tasks with varying degrees of congruence with users’ mental model (n?=?50). Analysis by linear mixed-effect models suggests that the match between mental model and website structure has no effect on browsing performance. We discuss possible reasons and consequences of the failure to validate card sorting for designing navigation structures of informational websites.