Citation Context

...s correlated with learning gain (Litman & Forbes-Riley 2006). Thus, some tutorial dialogue systems encourage students to produce language by asking “why” questions (Aleven, Popescu, & Koedinger 2001; =-=Jordan et al. 2006-=-; Graesser et al. 1999). They use natural language understanding techniques to analyze student answers and choose feedback based on the faults (errors and missing parts) discovered. However, for remed...

Citation Context

...ck to the learner's level, affective factors [4], and the interactive nature of human-human dialogue. Some tutorial dialogue systems use NLP techniques to analyze student responses to “why” questions =-=[5,6,7]-=-. However, for remediation they revert to scripted dialogue, with short-answer questions and canned feedback. The resulting dialogue may be redundant in ways detrimental to student understanding [8] a...

Citation Context

...tali and Burstein, 2006; Shermis and Burstein, 2013), error detection and correction (Leacock et al., 2010), and classification of texts by grade level (Petersen and Ostendorf, 2009; Sheehan et al., 2010; Nelson et al., 2012). In these applications, NLP methods based on shallow features and supervised learning are often highly effective. However, for the assessment of responses to short-answer questions (Leacock and Chodorow, 2003; Pulman and Sukkarieh, 2005; Nielsen et al., 2008a; Mohler et al., 2011) and in tutorial dialog systems (Graesser et al., 1999; Glass, 2000; Pon-Barry et al., 2004; Jordan et al., 2006; VanLehn et al., 2007; Dzikovska et al., 2010) deeper semantic processing is likely to be appropriate. Since the task of making and testing a full educational dialog system is daunting, Dzikovska et al. (2012) identified a key subtask and proposed it as a new shared task for the NLP community. Student response analysis (henceforth SRA) is the task of labeling student answers with categories that could Example 1 QUESTION You used several methods to separate and identify the substances in mock rocks. How did you separate the salt from the water? REF. ANS. The water was evaporated, leaving the s...

Citation Context

...e range of possible questions and answers grows, achieving complete coverage becomes more difficult. For essays in large domains, statistical methods can be used to identify problems with the answer (=-=Jordan et al., 2006-=-; Graesser et al., 1999), but these approaches do not perform well on relatively short single-sentence explanations, and such systems often revert to short-answer questions during remediation to ensur...

Citation Context

...94), adapting tutorial feedback to the learner’s level, and engagement/affect. Some tutorial dialogue systems use NLP techniques to analyze student responses to “why” questions. (Aleven et al., 2001; =-=Jordan et al., 2006-=-). However, for remediation they revert to scripted dialogue, relying on shortanswer questions and canned feedback. The resulting dialogue may be redundant in ways detrimental to student understanding...

Citation Context

...ment scheduling [30]. Dialogue systems that use more complex domain reasoners tend to rely on either on domain-specific grammars, or on wider-coverage syntactic grammars with domain-specific lexicons =-=[42, 33, 17, 28]-=-. However, the language components in such dialogue systems are difficult to port to new domains because of their domain-specific representations. They are also not easily extended to handle complex p...

Citation Context

...ve been shown to help learning as part of a technology-enhanced learning curriculum [1], and there has been a lot of interest in developing tutoring systems that understand student explanations (e.g. =-=[2]-=-). However, existing ITS with natural language support typically support only short answer questions; at most, they can analyze student essays but then revert to pre-authored short answer dialogues if...

Citation Context

...have historically been based on handcrafted rules derived from observing human tutors (e.g., Aleven, McLaren, Roll, & Koedinger, 2004; Evens & Michael, 2006; Graesser, Chipman, Haynes, & Olney, 2005; =-=Jordan, Makatchev, Pappuswamy, VanLehn, & Albacete, 2006-=-). While these systems can achieve results on par with unskilled human tutors, tutorial dialogue systems have not yet matched the effectiveness of expert human tutors (VanLehn et al., 2007). A more fl...

Citation Context

...roduction In recent years, there has been considerable research on tutorial dialogue systems that accept natural language input and engage in dialogue with students to help them improve their answers =-=[1, 4, 12, 13, 15, 17, 20, 23]-=-. Such systems are designed to allow students to express their answers in their own words, thus encouraging knowledge construction and harnessing the power of self-explanation [3]. One of the challeng...