Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease
Open accessThe DOI matches its Crossref record; 65 of the 66 references it cites were found in a registry or an index.
Abstract
Alzheimer's disease (AD) is an increasingly prevalent cognitive disorder in which memory, language, and executive function deteriorate, usually in that order. There is a growing need to support individuals with AD and other forms of dementia in their daily lives, and our goal is to do so through speech-based interaction. Given that 33% of conversations with people with middle-stage AD involve a breakdown in communication, it is vital that automated dialogue systems be able to identify those breakdowns and, if possible, avoid them. In this article, we discuss several linguistic features that are verbal indicators of confusion in AD (including vocabulary richness, parse tree structures, and acoustic cues) and apply several machine learning algorithms to identify dialogue-relevant confusion from speech with up to 82% accuracy. We also learn dialogue strategies to avoid confusion in the first place, which is accomplished using a partially observable Markov decision process and which obtains accuracies (up to 96.1%) that are significantly higher than several baselines. This work represents a major step towards automated dialogue systems for individuals with dementia.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures













Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In [108], ML algorithms have been applied to identify dialog-related confusion from speech with individuals with Alzheimer's disease; accuracies above 80% were obtained and learn policies implemented to avoid conversation breakdowns.”
From Conversational Affective Social Robots for Ageing and Dementia Support (2022) · cites this paper as [108]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Some recent work has used reinforcement learning to learn policies that can at least limit those instances [5].”
From A Conversational Robot for Older Adults with Alzheimer's Disease (2020) · cites this paper as [5]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Several linguistic features were extracted as verbal indicators of confusion (e.g., vocabulary richness, parse tree structures, and acoustic cues).”
From Conversational Affective Social Robots for Ageing and Dementia Support (2022) · cites this paper as [108]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Folstein, M. F., Folstein, S. E., & McHugh, P. R. (1975) · Journal of Psychiatric Research · doi:10.1016/0022-3956(75)90026-6 · Cited by 88,282 · cited 1×
“…provides a unified and validated scale for measuring the severity of dementia on a scale of 0 (greatest cognitive decline) to 30 (no cognitive decline), based on a series of questions in five areas: orientation, registration, attention, memory, and language (Folstein, Folstein, and McHugh 1975).”
BackgroundSMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · cited 1×
“In this experiment, we generate synthetic data points using the synthetic minority oversampling technique (SMOTE), which under-samples the majority class and over-samples the minority class by creating synthetic minority class examples (Chawla et al. 2002).”
MethodWordNet: a lexical database for English
Miller, G. A. (1995) · Communications of the ACM · doi:10.1145/219717.219748 · Cited by 14,015
The Preference for Self-Correction in the Organization of Repair in Conversation
Schegloff, E. A., Jefferson, G., & Sacks, H. (1977) · Language · doi:10.2307/413107 · Cited by 5,150 · cited 1×
“The trouble source-repair (TSR) model describes difficulties in communication in any dyads, including how repairs are initiated and carried out (Schegloff, Jefferson, and Sacks 1977).”
MethodRecognizing contextual polarity in phrase-level sentiment analysis
Wilson, T., Wiebe, J., & Hoffmann, P. (2005) · Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05 · doi:10.3115/1220575.1220619 · Cited by 3,345 · cited 1×
“We also compute objectivity measures using the MPQA Subjectivity Lexicon (Wilson, Wiebe, and Hoffmann 2005), which categorizes words by their subjectivity (strong or weak) and their prior, out-of-context, polarity (positive, negative, both, or neutral).”
MethodThe assessment of aphasia and related disorders
Goodglass, H., & Kaplan, E. (1972) · Medical Entomology and Zoology · Cited by 3,258
Accurate unlexicalized parsing
Klein, D., & Manning, C. D. (2003) · Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03 · doi:10.3115/1075096.1075150 · Cited by 3,008 · cited 1×
“Lu’s Syntactic Complexity Analyzer was initially designed to measure the syntactic complexity of second-language writing and, in turn, uses the Stanford parser (Klein and Manning 2003).”
MethodFeature-rich part-of-speech tagging with a cyclic dependency network
Toutanova, K., Klein, D., Manning, C. D., & Singer, Y. (2003) · Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03 · doi:10.3115/1073445.1073478 · Cited by 2,844 · cited 2×
“We include various part-of-speech (POS) features, such as the proportion of nouns, verbs, light verbs, adjectives, adverbs, prepositional words, demonstratives, functional words generally, and the noun-to-verb ratio, obtained using the Stanford POS tagger (Toutanova et al. 2003).”
MethodBrysbaert, M., & New, B. (2009) · Behavior Research Methods · doi:10.3758/brm.41.4.977 · Cited by 2,821
SWITCHBOARD: telephone speech corpus for research and development
Godfrey, J. J., Holliman, E. C., & McDaniel, J. (1992) · [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1992.225858 · Cited by 2,134 · cited 1×
“To estimate statistical deviations from typical language, we also compute the average log probability of each word in each utterance given two trigram models with Good-Turing smoothing, from the Brown and Switchboard (Godfrey, Holliman, and McDaniel 1992) corpora, respectively.”
Method(2000) · doi:10.2460/ajvr.67.2.323 · Cited by 1,621 · cited 1×
“In the future, we intend to learn this function based on inverse reinforcement learning (Ng and Russell 2000; Choi and Kim 2011; Chinaei and Chaib-Draa 2014).”
Background(1994) · Aston Publications Explorer (Aston University) · Cited by 1,245
Point-based value iteration: an anytime algorithm for POMDPs
Pineau, J., Gordon, G., & Thrun, S. (2003) · International Joint Conference on Artificial Intelligence · Cited by 1,209
Cummings, J. L. (2004) · New England Journal of Medicine · doi:10.1056/nejmra040223 · Cited by 1,152
Automatic analysis of syntactic complexity in second language writing
Lu, X. (2010) · International Journal of Corpus Linguistics · doi:10.1075/ijcl.15.4.02lu · Cited by 1,041 · cited 2×
“Lu’s Syntactic Complexity Analyzer was initially designed to measure the syntactic complexity of second-language writing and, in turn, uses the Stanford parser (Klein and Manning 2003).”
MethodPOMDP-Based Statistical Spoken Dialog Systems: A Review
Young, S., Gasic, M., Thomson, B., & Williams, J. D. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2225812 · Cited by 882 · cited 3×
“POMDP reward functions are often defined to encourage task completion (Young et al. 2013).”
BackgroundInfluentialLinguistic Features Identify Alzheimer’s Disease in Narrative Speech
Fraser, K. C., Meltzer, J. A., & Rudzicz, F. (2015) · Journal of Alzheimer's Disease · doi:10.3233/jad-150520 · Cited by 797 · cited 3×
“Much of this work is based on prior work in which we used similar linguistic features to train machine learning classifiers to distinguish between participants with and without AD (Fraser, Meltzer, and Rudzicz 2016).”
BackgroundMethodResultInfluentialSelf-citationDisfluency Rates in Conversation: Effects of Age, Relationship, Topic, Role, and Gender
Bortfeld, H., Leon, S. D., Bloom, J. E., Schober, M. F., & Brennan, S. E. (2001) · Language and Speech · doi:10.1177/00238309010440020101 · Cited by 632 · cited 1×
“In the middle, they often indicate the need for a trouble source repair (Bortfeld et al. 2001).”
BackgroundPredictors of nursing home admission for persons with dementia
Gaugler, J. E., Yu, F., Krichbaum, K., & Wyman, J. F. (2009) · Medical Care · doi:10.1097/mlr.0b013e31818457ce · Cited by 617 · cited 1×
“Caregivers who assist individuals with AD at home are common, but their involvement is often the precursor to placement in a long-term care facility (Gaugler et al. 2009).”
BackgroundSmith, E. A., & Senter, R. J. (1967) · PubMed · Cited by 587
The Natural History of Alzheimer's Disease: Description of Study Cohort and Accuracy of Diagnosis
Becker, J. T. (1994) · Archives of Neurology · doi:10.1001/archneur.1994.00540180063015 · Cited by 576
Perseus: Randomized point-based value iteration for POMDPs
Spaan, M. T. J., & Vlassis, N. A. (2005) · UvA-DARE (University of Amsterdam) · Cited by 526
Nonlinear analysis of bivariate data with cross recurrence plots
Marwan, N., & Kurths, J. (2002) · Physics Letters A · doi:10.1016/s0375-9601(02)01170-2 · Cited by 482 · cited 1×
“Nevertheless, we perform recurrence quantification analysis of the cross recurrence (Marwan and Kurths 2002) of each utterance.”
MethodBird, H., Franklin, S., & Howard, D. (2001) · Behavior Research Methods, Instruments, & Computers · doi:10.3758/bf03195349 · Cited by 385 · cited 1×
“…mental images... used to evaluate the effects of meaning on memory and word recognition” and as closely related to “concreteness,” with some exceptions (Bird, Franklin, and Howard 2001); raters of imageability were asked to indicate how easily each word elicited mental images, on a 7-point scale.”
MethodConnected speech as a marker of disease progression in autopsy-proven Alzheimer’s disease
Ahmed, S., Haigh, A.-M. F., de Jager, C. A., & Garrard, P. (2013) · Brain · doi:10.1093/brain/awt269 · Cited by 362 · cited 1×
“Ahmed et al. (2013) found that two-thirds of their participants showed subtle, but significant, changes in connected speech production up to a year before their diagnosis of probable AD.”
BackgroundSpoken Language Derived Measures for Detecting Mild Cognitive Impairment
Roark, B., Mitchell, M., Hosom, J.-P., Hollingshead, K., & Kaye, J. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2112351 · Cited by 355 · cited 2×
“2010), mean pause duration, and phonation rate (the amount of the recording spent in voiced speech) (Roark et al. 2011).”
BackgroundInfluentialBharucha, A. J., Anand, V., Forlizzi, J., Dew, M. A., Reynolds, C. F., Stevens, S., & Wactlar, H. (2009) · The American Journal of Geriatric Psychiatry · doi:10.1097/jgp.0b013e318187dde5 · Cited by 350 · cited 1×
“As the population ages, the incidence of AD will double or triple, with Medicare costs alone reaching $189 billion in the United States presently (Bharucha et al. 2009).”
BackgroundPerseus: Randomized Point-based Value Iteration for POMDPs
Spaan, M. T. J., & Vlassis, N. (2005) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1659 · Cited by 331 · cited 1×
“We evaluate the learned POMDP policies in 1,000 simulation runs using the default simulation in Perseus (Spaan and Vlassis 2005) in which the true state of the user is estimated from the provided transition function, and the observations are sampled from the provided observation function.”
MethodA Study of K-Nearest Neighbour as an Imputation Method.
Batista, G. E. A. P. A., & Monard, M. C. (2002) · Cited by 329
The Bristol norms for age of acquisition, imageability, and familiarity
Stadthagen-Gonzalez, H., & Davis, C. J. (2006) · Behavior Research Methods · doi:10.3758/bf03193891 · Cited by 315
Empty Speech in Alzheimer's Disease and Fluent Aphasia
Nicholas, M., Obler, L. K., Albert, M. L., & Helm-Estabrooks, N. (1985) · Journal of Speech, Language, and Hearing Research · doi:10.1044/jshr.2803.405 · Cited by 303 · cited 1×
“This appears to be consistent with previous analysis of AD language use (Nicholas et al. 1985; Almor et al. 1999).”
ResultExploiting structure to efficiently solve large scale partially observable markov decision processes
Poupart, P. (2005) · Cited by 247
Bucks, R. S., Singh, S., Cuerden, J. M., & Wilcock, G. K. (2000) · Aphasiology · doi:10.1080/026870300401603 · Cited by 233
Hoey, J., Poupart, P., Bertoldi, A. V., Craig, T., Boutilier, C., & Mihailidis, A. (2010) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.06.008 · Cited by 229 · cited 1×
“This is intractable in many real-world scenarios, so Hoey et al. (2010) simplified the problem by explicitly designing a reward function R ( s t , a t ), s ∈ S , a ∈ A , learning a prior model of user behavior (via maximum likelihood estimation given appropriately annotated data) and a prior model…”
MethodAlmor, A., Kempler, D., MacDonald, M. C., Andersen, E. S., & Tyler, L. K. (1999) · Brain and Language · doi:10.1006/brln.1999.2055 · Cited by 219
Sentence Extraction as a Classification Task
Teufel, S. (1997) · Cited by 215
Aphasia in senile dementia of the alzheimer type
Faber‐Langendoen, K., Morris, J. C., Knesevich, J. W., LaBarge, E., Miller, J. P., & Berg, L. (1988) · Annals of Neurology · doi:10.1002/ana.410230409 · Cited by 214 · cited 2×
“Faber-Langendoen et al. (1988) found that 36% of mild AD patients and 100% of severe AD patients had aphasia, according to standard aphasia testing protocols.”
Small, J. A., GUTMAN, G. M., Makela, S., & Hillhouse, B. (2003) · Journal of Speech Language and Hearing Research · doi:10.1044/1092-4388(2003/028 · Cited by 190
Cognitive Function and the Costs of Alzheimer Disease: An Exploratory Study
Ernst, R. L. (1997) · Archives of Neurology · doi:10.1001/archneur.1997.00550180013006 · Cited by 171 · cited 1×
“Approximately $100 billion are spent annually in North America on the direct and indirect care for patients with AD and other dementias, the majority of which is attributed to long-term institutional care (Ernst et al. 1997).”
BackgroundFinding a balance: The Carolinas Conversation Collection
Pope, C., & Davis, B. H. (2011) · Corpus Linguistics and Linguistic Theory · doi:10.1515/cllt.2011.007 · Cited by 110 · cited 1×
“Some analysis (Section 4.1.4) uses the Carolina Conversations Collection (CCC), in which transcriptions and audio of undirected conversations between interviewees (older adults) and interviewers (younger adults) are recorded longitudinally (Pope and Davis 2011).”
MethodInfluentialConversational Repair by Individuals With Dementia of the Alzheimer's Type
Orange, J. B., Lubinski, R. B., & Higginbotham, D. J. (1996) · Journal of Speech, Language, and Hearing Research · doi:10.1044/jshr.3904.881 · Cited by 100 · cited 2×
“…can be phonological (e.g., mispronunciation), morphological/syntactic (e.g., incorrect agreement among constituents), semantic (e.g., disturbances related to lexical access), and discourse-based (i.e., misunderstanding of shared knowledge, or cohesion) (Orange, Lubinsky, and Higginbotham 1996).”
BackgroundInfluentialWATSON, C. M. (1999) · Aphasiology · doi:10.1080/026870399402181 · Cited by 95 · cited 3×
“Watson (1999) showed that almost half of TIBs exhibited by speakers without AD are either TIB 5 (request for specific information) or TIB 9 (hypothesis formation).”
BackgroundNonlinear, Biophysically-Informed Speech Pathology Detection
Little, M., McSharry, P., Moroz, I., & Roberts, S. (2006) · 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings · doi:10.1109/icassp.2006.1660534 · Cited by 95 · cited 1×
“…power, the mean and maximum of the first autocorrelation function, sample-level skewness and kurtosis, zero-crossing rate, and mean recurrence period density entropy (which measures the periodicity of a signal, and has been applied to pathological speech generally [Little et al. 2006]).”
BackgroundJitter Estimation Algorithms for Detection of Pathological Voices
Silva, D. G., Oliveira, L. C., & Andrea, M. (2009) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/2009/567875 · Cited by 91 · cited 1×
“…shimmer (measures of the cycle-to-cycle variations of F 0 and amplitude, respectively, also largely applied to pathological speech) are computed (Silva, Oliveira, and Andrea 2009) as: where P 0 ( k ) is the pitch period length (1 / F 0) at time k in a sequence x with N observations, and x [ k ]…”
MethodLanguage in Alzheimer's Disease
Weiner, M. F., Neubecker, K. E., Bret, M. E., & Hynan, L. S. (2008) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.v69n0804 · Cited by 86 · cited 1×
“Weiner et al. (2008), in a study of 486 AD patients, reported a significant correlation between dementia severity and a number of different linguistic measures, including confrontation naming, articulation, word-finding ability, and semantic fluency.”
BackgroundRudzicz, F., Wang, R., Begum, M., & Mihailidis, A. (2015) · ACM Transactions on Accessible Computing · doi:10.1145/2744206 · Cited by 83 · cited 4×
“Also, Control subjects do not exhibit any lack of uptake (TIB 8) at all in this view, which is in sharp contrast to its relatively frequent occurrence among people with dementia, especially in our related work (Rudzicz et al. 2015).”
BackgroundResultInfluentialSelf-citationAffirmative Cue Words in Task-Oriented Dialogue
Gravano, A., Hirschberg, J., & Beňuš, Š. (2012) · Computational Linguistics · doi:10.1162/coli_a_00083 · Cited by 77
Rochon, E., Waters, G. S., & Caplan, D. (2000) · Journal of Speech, Language, and Hearing Research · doi:10.1044/jslhr.4302.395 · Cited by 74 · cited 1×
“Furthermore, Rochon, Waters, and Caplan (2000) showed that the syntactic complexity of received utterances is not necessarily the only predictor of comprehension in individuals with AD; rather, comprehension of the semantics of sentences is inversely related to the increasing number of propositions…”
BackgroundLanguage Analysis of Speakers with Dementia of the Alzheimer’s Type
Guinn, C. I., & Habash, A. (2012) · National Conference on Artificial Intelligence · Cited by 71
Reducing working memory load in spoken dialogue systems
Wolters, M., Georgila, K., Moore, J. D., Logie, R. H., MacPherson, S. E., & Watson, M. (2009) · Interacting with Computers · doi:10.1016/j.intcom.2009.05.009 · Cited by 66 · cited 2×
“However, there is some evidence that, at least in automated dialogue systems, neither simple confirmations nor reducing the number of options have a measurable effect on user performance, at least within specific appointment-scheduling applications (Wolters et al. 2009).”
BackgroundPakhomov, S. V. S., Smith, G. E., Chacon, D., Feliciano, Y., Graff-Radford, N., Caselli, R., & Knopman, D. S. (2010) · Cognitive and Behavioral Neurology · doi:10.1097/wnn.0b013e3181c5dde3 · Cited by 64
Speech Recognition in Alzheimer’s Disease and in its Assessment
Zhou, L., Fraser, K. C., & Rudzicz, F. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-1228 · Cited by 62 · cited 1×
“31) (Zhou, Fraser, and Rudzicz 2016).”
Self-citationUsing text and acoustic features to diagnose progressive aphasia and its subtypes
Fraser, K. C., Rudzicz, F., & Rochon, E. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-514 · Cited by 61 · cited 2×
“Other indicative measures include noun rate, pronoun rate, verb rate, and adjective rate, per 100 words, which have been used in studies of aphasia and speech in affective disorders (Bucks et al. 2000; Fraser, Rudzicz, and Rochon 2013).”
BackgroundInfluentialSelf-citationNeuroscience for the Study of Communicative Disorders
Bhatnagar, S. (1995) · Medical Entomology and Zoology · Cited by 60
Speech rate and syntactic complexity effects on the auditory comprehension of alzheimer patients
Tomoeda, C. K., Bayles, K. A., Boone, D. R., Kaszniak, A. W., & Slauson, T. J. (1990) · Journal of Communication Disorders · doi:10.1016/0021-9924(90)90019-u · Cited by 53 · cited 1×
“Tomoeda et al. (1990) showed that rates of speech that are too slow may interfere with comprehension if they introduce problems of short-term retention of working memory.”
BackgroundCortese, M. J., Balota, D. A., Sergent-Marshall, S. D., Buckner, R. L., & Gold, B. T. (2006) · Cognitive Neuropsychology · doi:10.1080/02643290500483124 · Cited by 49
Automatic detection of expressed emotion in Parkinson's Disease
Zhao, S., Rudzicz, F., Carvalho, L. G., Márquez-Chin, C., & Livingstone, S. R. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854516 · Cited by 45 · cited 1×
“With the exception of power, which may generally be a heuristic for energy in the voice, these measures are all related to repetitiveness in the vocal signal, which have been associated with pathological speech in older voices, following our recent work (Zhao et al. 2014).”
BackgroundSelf-citationChanges in Style in Authors with Alzheimer's Disease
Hirst, G., & Feng, V. W. (2012) · English Studies · doi:10.1080/0013838x.2012.668789 · Cited by 42 · cited 1×
“Because degraded cognitive function is correlated with a smaller active vocabulary, individuals with AD may be more likely to resort to more common, general words and therefore a lower degree of word specificity (Hirst and Feng 2012).”
BackgroundEffects of working memory capacity on understanding rate-altered speech
Small, J. A., Andersen, E. S., & Kempler, D. (1997) · Aging Neuropsychology and Cognition · doi:10.1080/13825589708256641 · Cited by 42 · cited 1×
“Small, Andersen, and Kempler (1997) showed that paraphrased repetition is just as effective as verbatim repetition (indeed, syntactic variation of common semantics may assist comprehension).”
BackgroundIndirect Interventions to Facilitate Communication in Alzheimer's Disease
Hopper, T. L. (2001) · Seminars in Speech and Language · doi:10.1055/s-2001-17428 · Cited by 35 · cited 1×
“Formal caregivers are often trained in responsive verbal communication strategies that are meant to adapt to an individual’s state-of-mind (Hopper 2001; Goldfarb and Pietro 2004).”
BackgroundGoldfarb, R., & Pietro, M. J. S. (2004) · Journal of Ambulatory Care Management · doi:10.1097/00004479-200410000-00008 · Cited by 13 · cited 1×
“Formal caregivers are often trained in responsive verbal communication strategies that are meant to adapt to an individual’s state-of-mind (Hopper 2001; Goldfarb and Pietro 2004).”
BackgroundA Method for Speeding Up Value Iteration in Partially Observable Markov Decision ProcessesPreprint
Zhang, N. L., Lee, S. S., & Zhang, W. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.6751 · Cited by 11 · cited 1×
“This algorithm first picks a finite set of belief states B = { b 0 , b 1 , ... , b q } then finds the optimal value function for each of these states (Zhang, Lee, and W 1999).”
BackgroundDialogue POMDP components (Part II): learning the reward function
Chinaei, H., & Chaib-draa, B. (2014) · International Journal of Speech Technology · doi:10.1007/s10772-014-9224-x · Cited by 8
Self-citationLongitudinal Detection of Dementia Through Lexical and Syntactic Changes in Writing
Hirst, G. (2010) · Cited by 6
News Summarization Based on Semantic Similarity Measure
Yu, H. L. (2009) · International Conference on Hybrid Intelligent Systems (HIS) · doi:10.1109/his.2009.43 · Cited by 2 · cited 2×
“To estimate semantic similarity between two utterances, we first use singular value decomposition (Yu 2009) given co-occurrence counts among terms and utterances in latent semantic space.”
Method
Research works printed but not linked: 2
- Choi, J. and K.E. Kim. 2011. Inverse reinforcement learning in partially observable environments. Journal of Machine Learning Research, 12:691–730.
- 10.1353/lan.1977.0041 · doi:10.1353/lan.1977.0041 · Paper page
Cited by
Artificial intelligence and the implementation challenge
Shaw, J., Rudzicz, F., Jamieson, T., & Goldfarb, A. (2019) · Journal of Medical Internet Research · doi:10.2196/13659 · Cited by 389
“…ML can dynamically adapt survey questions to more quickly identify possible diseases [17], dynamically avoid potential communication breakdowns during speech conversation in the assessment of dementia [18], and even recommend treatments directly when using structured institutional data [19].”
BackgroundSelf-citationLinguistic features and automatic classifiers for identifying mild cognitive impairment and dementia
Calzà, L., Gagliardi, G., Rossini Favretti, R., & Tamburini, F. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2020.101113 · Cited by 89
Conversational Affective Social Robots for Ageing and Dementia Support
Lima, M. R., Wairagkar, M., Gupta, M., Rodriguez y Baena, F., Barnaghi, P., Sharp, D. J., & Vaidyanathan, R. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2021.3115228 · Cited by 75
“In [108], ML algorithms have been applied to identify dialog-related confusion from speech with individuals with Alzheimer’s disease; accuracies above 80% were obtained and learn policies implemented to avoid conversation breakdowns.”
BackgroundA Conversational Robot for Older Adults with Alzheimer's Disease
Pou-Prom, C., Raimondo, S., & Rudzicz, F. (2020) · ACM Transactions on Human-Robot Interaction · doi:10.1145/3380785 · Cited by 59
“Some recent work has used reinforcement learning to learn policies that can at least limit those instances [5].”
BackgroundSelf-citationKobayashi, M., Kosugi, A., Takagi, H., Nemoto, M., Nemoto, K., Arai, T., & Yamada, Y. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-29390-1_4 · Cited by 45
“Rudzicz et al. [39] and Chinaei et al. [40] built a computational model that aimed to exploit linguistic and acoustic features to detect a breakdown in conversations.”
Metadata
- Authors
- Chinaei, H., Currie, L. C., Danks, A., Lin, H., Mehta, T., & Rudzicz, F.
- Affiliations
- University of Toronto (CA)
- Venue
- Computational Linguistics
- Publisher
- MIT Press
- Published
- 2017-06
- Volume
- 43
- Issue
- 2
- Pages
- 377-406
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W2602799059
- Semantic Scholar
- 247fff8f5d3281a20f11d28df3c592bc4fa1e553
- Cited by
- 30
- References
- 66
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 2 · 2023: 1 · 2022: 2 · 2021: 4 · 2020: 8 · 2019: 7 · 2018: 1
- FWCI
- 2.61
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by-nc-nd
- Locations
- Computational Linguistics (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- University of Pittsburgh
- Carnegie Mellon University
- AGE-WELL
- Alzheimer Society
- National Institutes of Health (AG005133, AG005133 and AG003705)
- Natural Sciences and Engineering Research Council of Canada (RGPIN 435874)
- National Institute on Deafness and Other Communication Disorders (DC008524, R01DC008524)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Social Sciences › Arts and Humanities › Language and Linguistics › Language, Discourse, Communication Strategies
- Keywords
- Alzheimer's disease, dementia, communication breakdown, confusion detection, speech-based interaction, dialogue strategies, lexical diversity, acoustic cues, partially observable Markov decision processes, conversational support
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.