Among other factors, student behavior during learning activities is affected by the pedagogical content they are interacting with. In this paper, we analyze this effect in the context of a problem-solving based online Physics course. We use a representation of the content in terms of its position, composition and visual layout to identify eight content types that correspond to problem solving sub-tasks. Canonical examples as well as a sequence model of these tasks are presented. Student behaviors, measured in terms of activity, help-requests, mistakes and time on task, are compared across each content type. Students request more help while working through complex computational tasks and make more mistakes on tasks that apply conceptual knowledge. We discuss how these findings can inform the design of pedagogical content and authoring tools.

Lexical ambiguity can cause critical failure in conversational spoken language translation (CSLT) systems that rely on statistical machine translation (SMT) if the wrong sense is presented in the target language. Interactive CSLT systems offer the capability to detect and pre-empt such word-sense translation errors (WSTEs) by engaging the human operators in a precise clarification dialogue aimed at resolving the problem. This paper presents an end-to-end framework for accurate detection and interactive resolution of WSTEs to minimize communication errors due to ambiguous source words. We propose (a) a novel, extensible, two-level classification architecture for identifying potential WSTEs in SMT hypotheses; (b) a constrained phrase-pair clustering mechanism for identifying the translated sense of ambiguous source words in SMT hypotheses; and (c) an interactive strategy that integrates this information to request specific clarifying information from the operator. By leveraging unsupervised and lightly supervised learning techniques, our approach minimizes the need for expensive human annotation in developing each component of this framework. Each component, as well as the overall framework, was evaluated in the context of an interactive English-to-Iraqi Arabic CSLT system.

Recent efforts to improve two-way speech-to-speech translation (S2S) systems have focused on developing error detection and interactive error recovery capabilities. This article describes our current work on developing an eyes-free English-Iraqi Arabic S2S system that detects ASR errors and attempts to resolve them by eliciting user feedback. Here, we report improvements in performance across multiple system components (ASR, MT and error detection). We also present a controlled evaluation of the S2S system that quantifies the effect of error recovery on user effort and conversational goal achievement.

Component models of speech-to-speech translation (S2S) systems need to be customized to emerging needs. In this demonstration, we will showcase the technical functionality of BBN’s domain customization tools for S2S systems that allow subject matter experts to augment an existing S2S system with new vocabulary items and translation rules using a web-based user interface. To reduce the user effort and time, our tools leverage Wikipedia as a linguistic resource for enrichment of domain profiles by finding lexical items and translations related to the domain. In a recent evaluation of BBN S2S system customized for using these tools, we found 15% (relative) reduction in word error rate as well as 30% (relative) reduction in untranslatable words when used within customized conversational domains.

In our recent work, we have proposed that multiple behavior demonstrations can be automatically combined to generate an Example-Tracing Tutor model. In this paper, we compare four algorithms for this problem using a number of different metrics for two different datasets, one of which is publicly available. Our experiments show that these four algorithms are complementary to each other in terms of their performance along the different metrics. These findings make a case for incorporating multiple algorithms for building behavior graphs into authoring tools for Intelligent Tutoring Systems (ITS) that use behavior graphs.

Automation of tutor modeling can contribute to scalable development and maintenance of Intelligent Tutoring Systems (ITS). In this paper, we are proposing a modification to the process used to build Example Tracing tutors which are a widely used tutor model. Our approach automatically uses behavior demonstrations by multiple non-experts (such as learners) to create a partially annotated generalized tutor model.

In this demonstration, we will showcase BBN’s Speech-to-Speech (S2S) translation system that employs novel interaction strategies to resolve errors through user-friendly dialog with the speaker. The system performs a series of analysis on input utterances to detect out-ofvocabulary (OOV) named-entities and terms, sense ambiguities, homophones, idioms and ill-formed inputs. This analysis is used to identify potential errors and select an appropriate resolution strategy. Our evaluation shows a 34% (absolute) improvement in cross-lingual transfer of erroneous concepts in our English to Iraqi-Arabic S2S system.

1 We describe a novel two-way speech-to-speech (S2S) translation system that actively detects a wide variety of common error types and resolves them through user-friendly dialog with the user(s). We present algorithms for detecting out-of-vocabulary (OOV) named entities and terms, sense ambiguities, homophones, idioms, ill-formed input, etc. and discuss novel, interactive strategies for recovering from such errors. We also describe our approach for prioritizing different error types and an extensible architecture for implementing these decisions. We demonstrate the efficacy of our system by presenting analysis on live interactions in the English-to-Iraqi Arabic direction that are designed to invoke different error types for spoken language translation. Our analysis shows that the system can successfully resolve 47% of the errors, resulting in a dramatic improvement in the transfer of problematic concepts.