## Co-occurrence & Dialog Systems 2017

Notes:

{Automatically generated text:}

In corpus linguistics, collocation refers to the mere co-occurrence of words. Filtering harmful sentences can be done based on three-word co-occurrence. Similarity can be measured based on co-occurrence probabilities for inducing semantic classes. Content may be created from summarized text and keywords extracted from documents using an algorithm based on term co-occurrence. Using a combination of ontology content, structure and co-occurrence information is more beneficial for the extension of large multi-domain ontologies, than using only content, only co-occurrence or only concept denotation information.

Automatically-generated summaries and representation of relationships between documents can be accomplished based on the co-occurrence of named entities and on clustering results. Choice of action verbs can be based only on the co-occurrence statistics encoded in a template-based generator for multimodal dialog systems. Statistical models can be based on co-occurrence measurements. Speech recognition errors may be detected based on semantic knowledge, constraint rules and statistical modeling, ie pointwise mutual information and co-occurrence analysis. Semantically different forms of multi-functionality may be represented by the co-occurrence of dialog acts in different types of dialog.

A popular method to estimate co-occurrence is to pose conjunctive queries including both terms to a web search engine, called “co-occurrence in snippets”. One system was designed using co-occurrence between the word in the news article and emotion words. For example, if people express their emotions in text, the single association language feature of a two terms combination, ie “myself” and “feeling”, has a high frequency of co-occurrence in sentences. Even emoticons can be automatically annotated according to their co-occurrence in a database. In robot navigation, a landmark component can ground novel noun phrases such as “the computers” in the perceptual frame of the robot by exploiting object co-occurrence statistics between unknown noun phrases and known perceptual features.

Wikipedia:

References:

Collocation Extraction & Dialog Systems

Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
L Yang, H Zamani, Y Zhang, J Guo, WB Croft – arXiv preprint arXiv …, 2017 – arxiv.org
… WordCountIDF: is method computes the word co-occurrence count weighted by IDF value between the two sequences … In many question answering and chatbot/dialogue systems, new questions issued by users have no explicit prede ned category …

Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
W Zhu, K Mo, Y Zhang, Z Zhu, X Peng… – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Flexible End-to-End Dialogue System for Knowledge Grounded Conversation … We propose a fully data-driven genera- tive dialogue system GenDS that is capable of generating re- sponses based on input message and related knowledge base (KB) …

A roadmap for natural language processing research in information systems
D Liu, Y Li, MA Thomas – … of the 50th …, 2017 – hl-128-171-57-22.library.manoa …
… In addition, we employ Association Rules (AR) mining for data analysis to investigate co-occurrence of prototypical tasks and discuss insights … refinement and application of NLP techniques to solve real-world problems [3], such as creating spoken dialogue systems [4], speech …

Affective Neural Response Generation
N Asghar, P Poupart, J Hoey, X Jiang, L Mou – arXiv preprint arXiv …, 2017 – arxiv.org
… Our work differs from Affect-LM in that we consider af- fective dialogue systems instead of merely language mod- els, and we have explored more affective aspects … Typically, word embeddings are learned from the co- occurrence statistics of words in large natural language cor …

Two-stage multi-intent detection for spoken language understanding
B Kim, S Ryu, GG Lee – Multimedia Tools and Applications, 2017 – Springer
… All the models that are needed to process the method are constructed from only the text corpus that is to train the dialog system. 3.1 ASR error detection … A word that is not present in the dictionary is regarded as an error candidate. Word Co-occurrence based detection …

Miscommunication handling in spoken dialog systems based on error-aware dialog state detection
CH Wu, MH Su, WB Liang – EURASIP Journal on Audio, Speech, and …, 2017 – Springer
… Based on these observations, historical information is crucial to improve the performance of a dialog system [40, 44 … The co-occurrence relation between the linguistic features and each of the DSs are estimated to construct a linguistic feature-by-DS (LFDS) matrix ? as shown in …

A simple generative model of incremental reference resolution for situated dialogue
C Kennington, D Schlangen – Computer Speech & Language, 2017 – Elsevier
… early as possible (in other words, time is shared). The overall goal of this paper is to model L’s comprehension process and implement it as a component in a spoken dialogue system. More formally, this can be modelled as a …

Unsupervised text classification for natural language interactive narratives
J Bellassai, AS Gordon… – Proceedings of the …, 2017 – pdfs.semanticscholar.org
… processing in interactive narratives has his- torically shared many of the methods and technologies of research in natural language dialogue systems … excerpts directly into the human-computer interaction, however, the corpus is used as a source for word co-occurrence statistics …

Unsupervised induction of contingent event pairs from film scenes
Z Hu, E Rahimtoroghi, L Munishkina… – arXiv preprint arXiv …, 2017 – arxiv.org
… Elahe Rahimtoroghi, Larissa Munishkina, Reid Swanson and Marilyn A. Walker Natural Language and Dialogue Systems Lab Department of … scalar estimates of poten- tial CONTINGENCY between events using four previously defined measures of distributional co- occurrence …

Turn-taking Estimation Model Based on Joint Embedding of Lexical and Prosodic Contents
C Liu, C Ishi, H Ishiguro – Proc. Interspeech 2017, 2017 – pdfs.semanticscholar.org
… Furthermore, recog- nizing whether a phrase is backchannel is critical for a dialog system since it means a user has no intention to … embedding All three word embedding methods we used in this work learn vector representations of words from their co-occurrence in- formation …

Building multi-domain conversational systems from single domain resources
D Griol, JM Molina – Neurocomputing, 2018 – Elsevier
… To solve the domain identification problem in a multi-domain dialog system, the initial approach was asking users to explicitly specify the domain [20 … The features used for the vectorization of the sentence are: bag of words, bag of bigrams, and co-occurrence of two words in the …

Ethical Challenges in Data-Driven Dialogue Systems
P Henderson, K Sinha, N Angelard-Gontier… – arXiv preprint arXiv …, 2017 – arxiv.org
… Although both types of systems do in fact have objectives, typically the task-oriented dialogue systems have a well-defined measure of performance that is explicitly … In these samples, we calculate the co-occurrence of gender-specific words, also defined in (Bolukbasi et al …

Automatic Speech Recognition Adaptation to the IoT Domain Dialogue System
M Zembrzuski, H Jeon, J Marhula, K Beksa… – … on Methodologies for …, 2017 – Springer
… by [6]. Additionally, within the area of recognition and understanding of various proficiency-level speakers by the dialogue system, our approach … 14] present the usage of n-grams, confusion network and Normalized Web Distance – a measure of words’ co-occurrence on web …

Interaction Style Recognition Based on Multi-Layer Multi-View Profile Representation
WL Wei, JC Lin, CH Wu – IEEE Transactions on Affective …, 2017 – ieeexplore.ieee.org
… Most importantly, Berens provided the criteria for how a dialogue system selects appropriate responses based on the recognized IS of a speaker … In this study, PðI ˜SkjO;?iÞ is estimated from the i-th MCM-based classifier by considering the co-occurrence dependencies among …

Ontology based Baysian network for clinical specialty supporting in interactive question answering systems
JF Yeh, YJ Huang, KP Huang – Engineering Computations, 2017 – emeraldinsight.com
… The ontology incorporates close temporal associations between words in input query to represent word co-occurrence relationships in concept space … Therefore, a query system or spoken dialogue system is able to provide better service for the clinical specialty supporting by …

“I think you just got mixed up”: confident peer tutors hedge to support partners’ face needs
M Madaio, J Cassell, A Ogan – International Journal of Computer …, 2017 – Springer
… was over 0.7. To understand how tutoring moves were delivered indirectly, we analyzed the co- occurrence of the annotated indirectness markers with the annotated tutoring strategies for each given clause. We identified clauses …

A Dialogue System with Emotion Estimation and Knowledge Acquisition Functions
T MATSUI, M HAGIWARA – Transactions of Japan Society of Kansei …, 2017 – jstage.jst.go.jp
… consider the co-occurrence frequency of the emotion words in emotion dictionary. In the knowledge acquisition part, the relationship patterns from the input sentences are extracted. In the evaluation experiments, we can confirm that the proposed dialogue system obtains higher …

Entrainment in Multi-Party Spoken Dialogues at Multiple Linguistic Levels
Z Rahimi, A Kumar, D Litman, S Paletz… – Proc. Interspeech …, 2017 – isca-speech.org
… Several studies have focused on measuring entrainment in various modalities and implementing entrainment in Spoken Dialogue Systems (SDS) [11 … Experiment 2: Multimodal Co-Occurrence Our second hypothesis is that entrainment not only separately occurs at both acoustic …

Using Temporal Association Rule Mining to Predict Dyadic Rapport in Peer Tutoring
M Madaio, A Ogan, J Cassell – Proceedings of the …, 2017 – educationaldatamining.org
… Prior researchers in discourse analysis, multi-modal inter- action, and dialogue systems have developed detectors for various aspects of interpersonal … In prior EDM work, some [15] have used the temporal co- occurrence of nonverbal behaviors (operationalized as Facial Action …

Learning and Reusing Dialog for Repeated Interactions with a Situated Social Agent
J Kennedy, I Leite, A Pereira, M Sun, B Li… – … on Intelligent Virtual …, 2017 – Springer
… The mobile version of Kevin was implemented using Unity3D to provide a cross-platform mobile front-end to the dialog system. The phone used speech-to- text from IBM Watson, available as a Unity3D plug-in … the co-occurrence statistics of words, it is by no means perfect …

A Knowledge Enhanced Generative Conversational Service Agent
Y Long, J Wang, Z Xu, Z Wang… – … the 6th Dialog System …, 2017 – workshop.colips.org
… Figure 2: The Architecture of Our Dialog System … except delim- iters and stop words; (2) The score of each word is estimated by the ratio of degree to frequency (deg(w)/freq(w)), where the freq(w) is the word frequency and the deg(w) is the word co- occurrence frequency with …

Discovering the Recent Research in Natural Language Processing Field Based on a Statistical Approach
X Chen, B Chen, C Zhang, T Hao – International Symposium on Emerging …, 2017 – Springer
… researchers also focus on the applications of relevant tools in solving real-world problems, eg, spoken dialogue systems, speech-to … Research hotspots analysis: The recent research hotspots of NLP was acquired based upon keywords co-occurrence matrix, the specific steps of …

EEG: Knowledge Base for Event Evolutionary Principles and Patterns
Z Li, S Zhao, X Ding, T Liu – Chinese National Conference on Social Media …, 2017 – Springer
… events are of great value and important for many tasks, such as event prediction, decision-making and scenario design of dialog system … In recent years, a growing body of research has investigated learning probabilistic co-occurrence-based models with simpler events …

Inference of Fine-Grained Event Causality from Blogs and Films
Z Hu, E Rahimtoroghi, MA Walker – arXiv preprint arXiv:1708.09453, 2017 – arxiv.org
… Zhichao Hu, Elahe Rahimtoroghi and Marilyn A Walker Natural Language and Dialogue Systems Lab Department of Computer Science, University of … publicly available through an on- line search interface1. Rel-gram tuples are ex- tracted using a co-occurrence statistical metric …

Learning to attend, copy, and generate for session-based query suggestion
M Dehghani, S Rothe, E Alfonseca, P Fleury – arXiv preprint arXiv …, 2017 – arxiv.org
… However, co-occurrence based models su er from data sparsity and lack of coverage for rare or unseen queries … Dealing with these highly diverse sessions makes using co-occurrence based model almost impossible [6, 19, 42] …

Word affect intensities
SM Mohammad – arXiv preprint arXiv:1704.08798, 2017 – arxiv.org
… for issues and policies, tracking pub- lic health and well-being, literary analysis, devel- oping more natural dialogue systems, and disas … co- occur with each other more often than chance, and are particularly problematic when one uses auto- matic co-occurrence-based statistical …

Co-mention network of R packages: Scientific impact and clustering structure
K Li, E Yan – Journal of Informetrics, 2018 – Elsevier
… This framework takes software entities as the unit of analysis, employs bibliometric relationships such as co-occurrence and citation context … these relationships in information science, White & McCain (1998) selected the top 120 authors from the DIALOG system, analyzed their …

Distinguishing between facts and opinions for sentiment analysis: Survey and challenges
I Chaturvedi, E Cambria, RE Welsch, F Herrera – Information Fusion, 2017 – Elsevier
… 29] and political [30] forecasting, e-health [31] and e-tourism [32], human communication comprehension [33] and dialogue systems [34], etc … However, distributional similarities of words such as co-occurrence matrix and context information is unable to capture differences in …

Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
T Zhao, T Kawahara – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… Therefore DA segmentation becomes essential for spoken dialog systems … Compared with long documents, di- alog utterances have much fewer words and it is difficult to extract enough information from sim- ple word co-occurrence features …

Collection of responsive utterances to show attentive hearing attitude to speakers
T Ohno, M Murata, S Matsubara – Proceedings of the 11th International …, 2017 – dl.acm.org
… 7. REFERENCES [1] M. Inoue and H. Ueno. Dialogue system characterisation by back-channelling patterns extracted from dialogue corpus … Development of dialog interface for elderly people : Active listening with word co-occurrence analysis between utterance pairs. In Proc …

Hyponym/hypernym detection in science and technology thesauri from bibliographic datasets
T Kawaumra, M Sekine… – … Computing (ICSC), 2017 …, 2017 – ieeexplore.ieee.org
… In its basic form, word embedding is represented as a matrix whose elements are the co- occurrence frequencies between a word with a certain … This result is expected, because the co-occurrence frequency dictates the number of word combinations encoded in the vector space …

Natural Language Processing: State of The Art, Current Trends and Challenges
D Khurana, A Koli, K Khatter, S Singh – arXiv preprint arXiv:1708.05148, 2017 – arxiv.org
… Dialogue systems. 6.7 Medicine NLP is applied in medicine field as well … Then the information is used to construct a network graph of concept co-occurrence that is further analysed to identify content for the new conceptual model. 142 abstracts are analysed …

Learning to A end, Copy, and Generate for Session-Based ery Suggestion
M Dehghani, S Rothe, E Alfonseca, P Fleury – 2017 – pdfs.semanticscholar.org
… However, co-occurrence based models su er from data sparsity and lack of coverage for rare or unseen queries … Dealing with these highly diverse sessions makes using co-occurrence based model almost impossible [6, 19, 42] …

Discovering Stylistic Variations in Distributional Vector Space Models via Lexical Paraphrases
X Niu, M Carpuat – Proceedings of the Workshop on Stylistic Variation, 2017 – aclweb.org
… Processing systems are deployed in a variety of settings, detecting and analyzing stylistic variations is becoming increas- ingly important, and is relevant to applications ranging from dialogue systems (Mairesse, 2008) to … co-occurrence patterns that underlie register vari- ations …

DeepTingle
A Khalifa, GAB Barros, J Togelius – arXiv preprint arXiv:1705.03557, 2017 – arxiv.org
… 2007] Globerson, A.; Chechik, G.; Pereira, F.; and Tishby, N. 2007. Euclidean embedding of co- occurrence data … Stochastic language generation for spoken dialogue systems. In Proceedings of the 2000 ANLP/NAACL Work- shop on Conversational systems-Volume 3, 27–32 …

Convolutional Neural Network using a threshold predictor for multi-label speech act classification
G Xu, H Lee, MW Koo, J Seo – Big Data and Smart Computing …, 2017 – ieeexplore.ieee.org
… I. INTRODUCTION The spoken language understanding (SLU) is one of the core components of an end-to-end dialogue system [1]. The SLU … meanings, since both two models learn words in terms of the semantic relationship based on their context (ie co-occurrence) information …

Detecting Hypernym/Hyponym in Science and Technology Thesaurus Using Entropy-Based Clustering of Word Vectors
T Kawamura, M Sekine, K Matsumura – International Journal of …, 2017 – World Scientific
… In its basic form, word vectors are represented as a matrix whose elements are the co-occurrence frequencies between a word w with a certain appearance frequency in the corpus, and words within a ¯xed window size c from w. A popular representation of word vectors is …

The E2E Dataset: New Challenges For End-to-End Generation
J Novikova, O Dušek, V Rieser – arXiv preprint arXiv:1706.09254, 2017 – arxiv.org
… dialogue systems. In Proceedings of the 11th Conference of the Euro- pean Chapter of the ACL (EACL). pages 65–72. http://aclweb.org/anthology/E06-1009. George Doddington. 2002. Automatic evalu- ation of machine translation quality using n-gram co-occurrence statistics …

An iterative approach for the global estimation of sentence similarity
T Kajiwara, D Bollegala, Y Yoshida, K Kawarabayashi – PloS one, 2017 – journals.plos.org
… Different word association measures can be used to compute similarity scores from co-occurrence counts … includes 3,000 sentence pairs from five different domains: news headlines (Head), image descriptions (Img), answer pairs from a tutorial dialogue system (Stud), answer …

Deep Survey on Sentiment Analysis and Opinion Mining on Social Networking Sites and E-Commerce Website
P Arya, A mit Bhagat, B MANIT – International Journal of Engineering …, 2017 – ijesc.org
… Authors also evaluated the proposed framework with the UAH (Universidad Al Habla) spoken dialog system, implementing the prediction module between the systems natural language understanding module and dialog manager. 3. TEXT MINING …

Morph-fitting: Fine-tuning word vector spaces with simple language-specific rules
I Vuli?, N Mrkši?, R Reichart, DÓ Séaghdha… – arXiv preprint arXiv …, 2017 – arxiv.org
… representation tech- niques are grounded in the distributional hypothe- sis (Harris, 1954), relying on word co-occurrence information in … and antonyms may have grave implications in down- stream language understanding applications such as spoken dialogue systems: a user …

Functional and temporal relations between spoken and gestured components of language
KI Kok – International Journal of Corpus Linguistics, 2017 – jbe-platform.com
… It was mostly oriented towards the design of virtual avatars and automated dialogue systems (Bergmann & Kopp 2009, Bergmann et al … types of linguistic elements, the second part of this paper explores whether varying the operational definition of co-occurrence influ- ences the …

Inferring Narrative Causality between Event Pairs in Films
Z Hu, MA Walker – arXiv preprint arXiv:1708.09496, 2017 – arxiv.org
… Zhichao Hu and Marilyn A. Walker Natural Language and Dialogue Systems Lab Department of Computer Science, University of California Santa … sizes of each genre, illustrating the potential tradeoff be- tween getting good probability estimates for event co-occurrence when the …

Learning to generate one-sentence biographies from Wikidata
A Chisholm, W Radford, B Hachey – arXiv preprint arXiv:1702.06235, 2017 – arxiv.org
Page 1. Learning to generate one-sentence biographies from Wikidata Andrew Chisholm University of Sydney Sydney, Australia andy.chisholm.89@gmail.com Will Radford Hugo Australia Sydney, Australia wradford@hugo.ai …

Evaluate the Chinese Version of Machine Translation Based on Perplexity Analysis
H Tianwen, W Hong, H Baofang – Computational Science and …, 2017 – ieeexplore.ieee.org
… Spoken dialogue system for service robots and research about language model[D]. University of Science and Technology of China, 2014 … OpenE:an automatic method of MT evaluation based on N-gram co- occurrence[J]. Journal of Chinese Information Processing | J Chin Inf …

A Self-Adaptive Sliding Window Based Topic Model for Non-uniform Texts
J He, L Li, X Wu – Data Mining (ICDM), 2017 IEEE International …, 2017 – ieeexplore.ieee.org
… This method, referred to as SSWTM, is based on a simple assumption that semantically coherent words have a high co-occurrence frequency within a certain semantical distance … But this assumption is too simple to capture the word co- occurrence information …

I Probe, Therefore I Am: Designing a Virtual Journalist with Human Emotions
KK Bowden, T Nilsson, CP Spencer, K Cengiz… – arXiv preprint arXiv …, 2017 – arxiv.org
… qualitative evaluations of the agent’s conversational performance were continuously carried out in parallel to the development of the dialogue system in order to … We also attempt to identify nodes which appear to be related to each other based on frequent co-occurrence in the …

A Hybrid Architecture for Multi-Party Conversational Systems
MG de Bayser, P Cavalin, R Souza, A Braz… – arXiv preprint arXiv …, 2017 – arxiv.org
… Page 2. Turing’s test. Some of them have won prizes, some not [5]. Although in this paper we do not focus on creating a solution that is able to build conversational systems that pass the Turing’s test, we focus on Natural Dialogue Systems (NDS) …

To Phrase or Not to Phrase-Impact of User versus System Term Dependence Upon Retrieval
C Lioma, B Larsen, P Ingwersen – arXiv preprint arXiv:1802.02603, 2018 – arxiv.org
… b) phrase oper- ations constituted only 1.45% of all queries ([6], p. 518, Table 2). Other log analyses of the DIALOG system [11, 25 … It seems that the most popular methods for automatically detecting heavily de- pendent terms in queries rely on the co-occurrence frequency of the …

An Empirical Study on Incorporating Prior Knowledge into BLSTM Framework in Answer Selection
Y Li, M Yang, T Zhao, D Zheng, S Li – National CCF Conference on …, 2017 – Springer
… the former obviously, we guess that it may because this strategy violated the original aim of through the BLSTM to model the word co-occurrence information to … A comprehensive view demands further examination of this issue in other NLP tasks such as MT, dialogue system etc …

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
M Palmer, R Hwa, S Riedel – Proceedings of the 2017 Conference on …, 2017 – aclweb.org
… Thang Vu . . . . . 233 Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics Zhe Zhao, Tao Liu, Shen Li, Bofang Li and Xiaoyong Du. . . . . 244 Dict2vec …

Constructing a Language From Scratch: Combining Bottom–Up and Top–Down Learning Processes in a Computational Model of Language Acquisition
J Gaspers, P Cimiano, K Rohlfing… – IEEE Transactions on …, 2017 – ieeexplore.ieee.org
… At first, an initial lexicon is generated by exploiting the statistical co-occurrence of acoustic morpheme candidates, ie, phoneme sequences of certain length, and atomic entities observed in the visual context. Bootstrapping on this initial lexicon, construc- tions are then induced …

A comprehensive framework of information system design to provide organizational creativity support
CM Olszak, T Bartu?, P Lorek – Information & Management, 2018 – Elsevier

Identifying and avoiding confusion in dialogue with people with alzheimer’s disease
H Chinaei, LC Currie, A Danks, H Lin, T Mehta… – Computational …, 2017 – MIT Press
… However, there is some evidence that, at least in automated dialogue systems, neither simple confirmations nor reducing the number of … estimate semantic similarity between two utterances, we first use singular value decomposition (Yu 2009) given co-occurrence counts among …

Deep keyphrase generation
R Meng, S Zhao, S Han, D He, P Brusilovsky… – arXiv preprint arXiv …, 2017 – arxiv.org
… However, these features only target to detect the importance of each word in the document based on the statis- tics of word occurrence and co-occurrence, and are unable to reveal the full semantics that underlie the document content …

Annotating and modeling empathy in spoken conversations
F Alam, M Danieli, G Riccardi – Computer Speech & Language, 2017 – Elsevier
Empathy, as defined in behavioral sciences, expresses the ability of human beings to recognize, understand and react to emotions, attitudes and beliefs of other.

Event-based knowledge reconciliation using frame embeddings and frame similarity
M Alam, DR Recupero, M Mongiovi, A Gangemi… – Knowledge-Based …, 2017 – Elsevier
… [33,34] apply Frame Semantics and Distributional Semantics for slot filling in Spoken Dialogue System. In [35], the authors use Word and Frame Embeddings for generating categories of annoying behaviors where each category contains a set of words specific to that category …

Automatic problem extraction and analysis from unstructured text in IT tickets
S Agarwal, V Aggarwal, AR Akula… – IBM Journal of …, 2017 – ieeexplore.ieee.org
… We process the phrases further in the next two phases to reduce the noise, add context through co-occurrence to find similar meaning actions, and summarize the phrases suitably for consumption either by human or machine. 4.2 …

Crossing disciplinary boundaries to improve technology-rich learning environments
SP Lajoie, EG Poitras – Teachers College Record, 2017 – digitool.library.mcgill.ca
… spartnership.ca). In particular, LEADS members expand our examination of the metaphor of using computers as tools to include the co-occurrence of affect and metacognition while learning to determine their influence Page 7. TCR …

Association for Computational Linguistics (ACL), 68 association measure (AM), 155, 159 associative learning, 46, 56
MZ Afzal, M Akakura, S Akutsu, R Alanen… – Language …, 2017 – Wiley Online Library
… 16 Contingency, 46–47, 49, 56 Contrastive Interlanguage Analysis (CIA), 132 conversation analysis, 49, 256 co-occurrence, 17, 20 … Delta P, 161, 165 Deploying Online Video for Education (DOVE), 266 Developmental Sentence Score, 257 DevLex, 21 dialogue system, 69 D?az …

Learning fine-grained knowledge about contingent relations between everyday events
E Rahimtoroghi, E Hernandez, MA Walker – arXiv preprint arXiv …, 2017 – arxiv.org
… Elahe Rahimtoroghi, Ernesto Hernandez and Marilyn A Walker Natural Language and Dialogue Systems Lab Department of Computer Science, University of … work to us: they generate pairs of rela- tional tuples of events, called Rel-grams using co- occurrence statistics based …

The impact of peer tutors’ use of indirect feedback and instructions
M Madaio, J Cassell, A Ogan – 2017 – repository.isls.org
… Then, after finding the co- occurrence of indirect language with tutors’ feedback and instructions, we normalized those frequency counts by … These findings can also inform the design of educational dialogue systems, or conversational agents which could support peer tutoring by …

Fully automatic analysis of engagement and its relationship to personality in human-robot interactions
H Salam, O Celiktutan, I Hupont, H Gunes… – IEEE …, 2017 – ieeexplore.ieee.org
… In addition to individual-level features, they pro- posed a method to detect temporal co-occurrence patterns in the target’s features and the group’s features (eg, the others change their postures as the target speaks) and used these co-occurrence features to predict the …

Steering output style and topic in neural response generation
D Wang, N Jojic, C Brockett, E Nyberg – arXiv preprint arXiv:1709.03010, 2017 – arxiv.org
… Topic models (Blei et al., 2003; Lafferty and Blei, 2006), on the other hand, are admixtures that capture word co-occurrence statistics by using a much smaller number of topics that can be more freely combined to explain a single document (and this makes it harder to visualize …

Predicting emotional word ratings using distributional representations and signed clustering
J Sedoc, D Preo?iuc-Pietro, L Ungar – … of the 15th Conference of the …, 2017 – aclweb.org
… Inferring the emotional content of words is important for text-based sentiment anal- ysis, dialogue systems and psycholinguis- tics, but word ratings are expensive … Repro- ducing Affective Norms with Lexical Co-occurrence Statistics: Predicting Valence, Arousal, and Domi- nance …

Towards a top-down policy engineering framework for attribute-based access control
M Narouei, H Khanpour, H Takabi, N Parde… – Proceedings of the …, 2017 – dl.acm.org
… 4.2 Recurrent Neural Network (RNN) Sentence Classi er Recently, DNNs have been used with increasing frequency in a variety of text processing applications, from sentiment analysis [41] to conversational text processing for dialogue systems [22, 48]. Collobert et al …

Recent trends in deep learning based natural language processing
T Young, D Hazarika, S Poria, E Cambria – arXiv preprint arXiv …, 2017 – arxiv.org
… a wide range of natural language related tasks at all levels, ranging from parsing and part-of-speech (POS) tagging, to machine translation and dialog systems … Here, the word co-occurrence count matrix is preprocessed by normal- izing the counts and log-smoothing them …

Semantic specialisation of distributional word vector spaces using monolingual and cross-lingual constraints
N Mrkši?, I Vuli?, DÓ Séaghdha, I Leviant… – arXiv preprint arXiv …, 2017 – arxiv.org
… The common techniques for inducing distributed word representations are grounded in the distributional hypothesis, relying on co-occurrence information in large … of our knowledge, this is the first work on multilingual training of any compo- nent of a statistical dialogue system …

Facial expressions and speech acts: experimental evidences on the role of the upper face as an illocutionary force indicating device in language comprehension
F Domaneschi, M Passarelli, C Chiorri – Cognitive processing, 2017 – Springer
… No temporal dynamics were analyzed, except for co-occurrence of action units (combinations) … For AU combinations, intensity scoring considered only the peak intensity of the lowest firing AU during the co-occurrence period …

Structured learning for spoken language understanding in human-robot interaction
E Bastianelli, G Castellucci, D Croce… – … Journal of Robotics …, 2017 – journals.sagepub.com
Robots are slowly becoming a part of everyday life, being marketed for commercial applications such as telepresence, cleaning or entertainment. Thus, the abilit…

Incomplete Follow-up Question Resolution using Retrieval based Sequence to Sequence Learning
V Kumar, S Joshi – Proceedings of the 40th International ACM SIGIR …, 2017 – dl.acm.org
… In Section 2, we dis- cuss related work in interactive QA systems, dialogue systems and sequence to sequence learning … was followed by a rule-based approach [13] to determine what information was missing in a follow-up question, and using word co-occurrence statistics and …

Deep Learning for Sentiment Analysis: A Survey
L Zhang, S Wang, B Liu – arXiv preprint arXiv:1801.07883, 2018 – arxiv.org
… However, the SG model treats each context-target pair as a new observation and is better for larger datasets. Another frequently used learning approach is Global Vectorii (GloVe)17, which is trained on the non- zero entries of a global word-word co-occurrence matrix …

Hindi language text search: a literature review
P Singh, A Tripathi – Annals of Library and Information Studies …, 2017 – op.niscair.res.in
… query term are disambiguated using an iterative page-rank style algorithm, which is based on term- term co-occurrence statistics, to … C-DAC Kolkata developed a project named speech-to-speech MAT (Machine Aided Translation) based dialogue system from Hindi to Indian …

Why We Need New Evaluation Metrics for NLG
J Novikova, O Dušek, AC Curry, V Rieser – arXiv preprint arXiv …, 2017 – arxiv.org
… This is rarely the case, as shown by various studies in NLG (Stent et al., 2005; Belz and Reiter, 2006; Reiter and Belz, 2009), as well as in related fields, such as dialogue systems (Liu et al., 2016), machine translation (MT) (Callison-Burch et al., 2006), and image captioning …

Exploring the Dynamics of Relationships Between Expressed and Experienced Emotions
R Srinivasan, A Chander, CL Dam – International Conference on Intelligent …, 2017 – Springer
… The words in a user’s text are then matched for co-occurrence with the emotion vocabulary and are weighted (normalized) based on their frequency of occurrence to obtain probability of an emotion … Ward, N., DeVault, D.: Challenges in building highly interactive dialog systems …

Modelling semantic context of oov words in large vocabulary continuous speech recognition
I Sheikh, D Fohr, I Illina… – IEEE/ACM Transactions on …, 2017 – ieeexplore.ieee.org
… Adopted Approach Earlier proposed document specific vocabulary selection methods [14]–[18] query web search engines to retrieve rel- evant documents and then choose the new vocabulary words using term frequency, document frequency and co-occurrence based features …

Node Importance Ranking of Complex Networks with Entropy Variation
X Ai – Entropy, 2017 – mdpi.com
The heterogeneous nature of a complex network determines the roles of each node in the network that are quite different. Mechanisms of complex networks such as spreading dynamics, cascading reactions, and network synchronization are highly affected by a tiny fraction of so …

Improving the understanding of spoken referring expressions through syntactic-semantic and contextual-phonetic error-correction
I Zukerman, A Partovi – Computer Speech & Language, 2017 – Elsevier
… system. Abstract. Despite recent advances in automatic speech recognition, one of the main stumbling blocks to the widespread adoption of Spoken Dialogue Systems is the lack of reliability of automatic speech recognizers …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2017 – dl.acm.org
… There may be a clip video that contains a reporter, and a video that depicts the snapshot of the scene where the event in the news occurred. The co-occurrence between an image and texts signals ACM Computing Surveys, Vol. 49, No …

Combining Domain Knowledge and Deep Learning Makes NMT More Adaptive
L Ding, Y He, L Zhou, Q Liu – China Workshop on Machine Translation, 2017 – Springer
… Topic models establish co-occurrence matrix for words and documents to get generative model to infer the topics … knowledge is well retained and helps benefit many NLP task, such as dictionary compilation, sentiment classification, machine translation and dialogue system etc …

Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning
Z Wen, K Li, Z Huang, CH Lee, J Tao – Journal of Signal Processing …, 2017 – Springer
… This is inefficient because the co-occurrence of phonemes is represented by a long vector with the neighboring phonemes. Vector space model (VSM) J Sign Process Syst Page 3 … It is trained from the matrix of co-occurrence statistics and further decomposed by singular values …

Linguistic Knowledge Transfer for Enriching Vector Representations
JK Kim – 2017 – rave.ohiolink.edu
Page 1. Linguistic Knowledge Transfer for Enriching Vector Representations DISSERTATION Presented in Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the Graduate School of The Ohio State University By Joo-Kyung Kim, BE, MS …

Foundations of Intelligent Systems: 23rd International Symposium, ISMIS 2017, Warsaw, Poland, June 26-29, 2017, Proceedings
M Kryszkiewicz, A Appice, D ?l?zak, H Rybinski… – 2017 – books.google.com
Page 1. Marzena Dominik Kryszkiewicz S´le?zak · Henryk · Annalisa Rybinski Appice Andrzej Skowron · Zbigniew W. Ras´ (Eds.) Foundations of Intelligent Systems 23rd International Symposium, ISMIS 2017 Warsaw, Poland, June 26–29, 2017 Proceedings 123 Page 2 …

Transforming unstructured natural language descriptions into measurable process performance indicators using Hidden Markov Models
H van der Aa, H Leopold, A Del-Río-Ortega… – Information Systems, 2017 – Elsevier
… variety of contexts. A major application area for these techniques is spoken language understanding, where information is extracted from unstructured natural language text in the context of a dialog system [32]. To achieve this …

Multilingual extension and evaluation of a poetry generator
HG Oliveira, R Hervás, A Díaz… – Natural Language …, 2017 – cambridge.org
… N-gram- based language models have shown great applicability in many contexts – such as machine translation, speech processing, text prediction or dialog systems – and they present the important advantage of being language independent to a great extent …

Natural Logic Inference for Emotion Detection
H Ren, Y Ren, X Li, W Feng, M Liu – Chinese Computational Linguistics …, 2017 – Springer
… As one of the most important research topics in natural language processing, emotion detection is widely used in opinion mining, product recommendation, dialog system, and so on [1] … ( \equiv \). MRPC. paraphrase. $$\equiv$$. Google Distance. co-occurrence. $$\equiv$$ …

K Pichotta – 2017 – repositories.lib.utexas.edu
… labeling, and even syntactic parsing systems could, in principle, benefit from event co-occurrence models. To this end, we present a number of contributions related to statistical event co-occurrence models. First, we investigate a method of incorporating multiple en …

Automatic quality estimation for ASR system combination
S Jalalvand, M Negri, D Falavigna, M Matassoni… – Computer Speech & …, 2018 – Elsevier
… Voice search engines, voice question answering, broadcast news transcriptions, video/TV programs subtitling, meeting transcriptions and spoken. dialog systems are just some of the many applications involving ASR technology …

Neural Models for Information Retrieval
B Mitra, N Craswell – arXiv preprint arXiv:1705.01509, 2017 – arxiv.org
Page 1. Neural Models for Information Retrieval Bhaskar Mitra Microsoft, UCL? Cambridge, UK bmitra@microsoft.com Nick Craswell Microsoft Bellevue, USA nickcr@microsoft.com Abstract Neural ranking models for information …

Fast Node Embeddings: Learning Ego-Centric Representations
T Pimentel, A Veloso, N Ziviani – 2018 – openreview.net
… In IJCAI, pp. 1293–1299, 2016. Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Pei-Hao Su, David Vandyke, and Steve Young. Semantically conditioned lstm-based natural language generation for spoken dialogue systems. EMNLP, pp. 1711–1721, 2015 …

Robot task planning and explanation in open and uncertain worlds
M Hanheide, M Göbelbecker, GS Horn, A Pronobis… – Artificial Intelligence, 2017 – Elsevier
… models of sensory information. Finally, the distributions Pr s ? ( ? | ? Pr a ? ( ? | ? and Pr o i ? ( ? | ? represent the default knowledge about shape, appearance and object co-occurrence, respectively. They allow for inference …

Computational modeling of turn-taking dynamics in spoken conversations
SA Chowdhury – 2017 – eprints-phd.biblio.unitn.it
Page 1. PhD Dissertation International Doctorate School in Information and Communication Technologies DISI – University of Trento COMPUTATIONAL MODELING OF TURN-TAKING DYNAMICS IN SPOKEN CONVERSATIONS Shammur Absar Chowdhury Advisor: Prof …

Neural Logic Framework for Digital Assistants
N Cingillioglu, A Russo, K Broda – 2017 – imperial.ac.uk
Page 1. MEng Individual Project Imperial College London Department of Computing Neural Logic Framework for Digital Assistants Author: Nuri Cingillioglu Supervisor: Prof. Alessandra Russo Second Marker: Dr. Krysia Broda June 16, 2017 Page 2. Abstract …

Machine Translation Using Semantic Web Technologies: A Survey
D Moussallem, M Wauer, ACN Ngomo – arXiv preprint arXiv:1711.09476, 2017 – arxiv.org
Page 1. Machine Translation Using Semantic Web Technologies: A Survey Diego Moussallema,b,, Matthias Wauera, Axel-Cyrille Ngonga Ngomob, aUniversity of Leipzig AKSW Research Group Department of Computer Science …

Dynamic ontology for service robots
S Kanjaruek – 2017 – uobrep.aws.openrepository.com
… XV P(x|y) Probability of concept x on concept y t A co-occurrence threshold value ( , ) … creating concepts focus on the identification of lexicons and on the measurement of the co-occurrence between lexicon units, with information obtained through an information retrieval process …

Modeling common sense knowledge via scripts
A Modi – 2017 – publikationen.sulb.uni-saarland.de
Page 1. Modeling Common Sense Knowledge via Scripts UNIVERSITÄT DES SAARLANDES Ashutosh Modi A dissertation submitted towards the degree Doctor of Engineering of the Faculty of Mathematics and Computer Science of Saarland University Saarbrücken, July 2017 …

A review of spatial reasoning and interaction for real-world robotics
C Landsiedel, V Rieser, M Walter, D Wollherr – Advanced Robotics, 2017 – Taylor & Francis
… interaction. Firstly, dialogue systems are an integral part of modern approaches to situated human–robot interaction … relationships. Dialogue systems for such grounded, situated human–robot interaction (HRI) are discussed in Section 2.1 …

11 Analyzing Multicodal Media Texts
U Fröhlich – Manual of Romance Languages in the Media, 2017 – books.google.com
… The co-occurrence of images and language can be described as multicodal (cf … Gibbon, Dafydd/Mertens, Inge/Moore, Roger K.(edd.)(2000), Handbook of multimodal and spoken dialogue systems: Resources, terminology and product evaluation, Dordrecht, Kluwer Academic …

Deep Reinforcement Learning in Natural Language Scenarios
J He – 2017 – digital.lib.washington.edu
… good/bad endings. Another example is a human-computer dialog system, where the action is the response generated by the dialog manager … and distributed. Distributional word representations are based on co-occurrence/context …

Automatic Neural Question Generation using Community-based Question Answering Systems
T Baghaee – 2017 – uleth.ca
Page 1. AUTOMATIC NEURAL QUESTION GENERATION USING COMMUNITY- BASED QUESTION ANSWERING SYSTEMS TINA BAGHAEE Bachelor of Science, Shahid Beheshti University, 2011 A Thesis Submitted to the …

Selected Distinguishing Properties of WisTech IGrC Models
A Jankowski – Interactive Granular Computations in Networks and …, 2017 – Springer
This assumption, among others, is understood in such a way that all interactions that are analyzed by us are reduced to physical phenomena.

Broad Discourse Context for Language Modeling
M Torres Garcia – 2017 – research-collection.ethz.ch
… An- other example are dialogue systems, where discourse understanding is needed to produce valid utterances for a given conversation context … co-occurences one word at a time (like word2vec), GloVe does dimensionality reduction on the whole co-occurrence counts matrix …

Towards a new possibilistic query translation tool for cross-language information retrieval
B Elayeb, WB Romdhane, NBB Saoud – Multimedia Tools and …, 2018 – Springer
… For example, Hull [62] used structured queries for disambiguation in CLIR task. Ballesteros and Croft [10] proved that translation ambiguity can be decreased due to the use of co-occurrence statistics from corpora. Hiemstra …

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
P Vougiouklis, H Elsahar, LA Kaffee, C Gravier… – arXiv preprint arXiv …, 2017 – arxiv.org
… Answering platforms whose users’ experience could be im- proved by the ability to automatically generate a textual description of an entity that is returned at a user’s query (eg the Google Knowledge Graph1 and the Wikidata Reasonator2), or dialogue systems in commercial …

Sentiment Analysis in the Bio-medical Domain: Techniques, Tools, and Applications
R Satapathy, E Cambria, A Hussain – 2018 – books.google.com
… bodily manifestations of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning … text in which opinions are explicitly expressed such as polarity terms, affect words and their co-occurrence frequencies …

Classification of Things in DBpedia using Deep Neural Networks
R Parundekar – arXiv preprint arXiv:1802.02528, 2018 – arxiv.org
… Semantic Graphs are also used in other domains like Spoken Dialog Systems [3], Social Networks [4], Scene Understanding [3], Virtual & … 7 create one combined single feature based on the co-occurrence of the presence of the attributes and relationships that the individual has …

Towards Building a Shallow Parsing Pipeline for English-Telugu Code Mixed Social Media Data
K Nelakuditi – 2017 – web2py.iiit.ac.in
Page 1. Towards Building a Shallow Parsing Pipeline for English-Telugu Code Mixed Social Media Data Thesis submitted in partial fulfillment of the requirements for the degree of MS by Research in Computational Linguistics by Kovida Nelakuditi 201125226 …

Explanation in artificial intelligence: Insights from the social sciences
T Miller – arXiv preprint arXiv:1706.07269, 2017 – arxiv.org
… counterfactuals, rather than dependence alone. Hume and Beauchamp argues that the co-occurrence of events C and E, observed from experience, do not give causal information that is useful. Instead, the cause should be …

Entity-Centric Discourse Analysis and Its Applications
X Wang – 2017 – repository.kulib.kyoto-u.ac.jp
Page 1. Title Entity-Centric Discourse Analysis and Its Applications( Dissertation_ ?? ) Author(s) Wang, Xun Citation Kyoto University (????) Issue Date 2017-11-24 URL https://dx.doi.org/10.14989/doctor.k20777 Right The …

Helping users learn about social processes while learning from users: developing a positive feedback in social computing
VSS Pillutla – 2017 – search.proquest.com
… LIST OF FIGURES. Figure Page. 2.1 A graph showing co-occurrence of words rendered using Spring layout … Goals may include word-sense disambiguation. [109], or text summarization [106]. Figure 2.1: A graph showing co-occurrence of words rendered using Spring layout …

Interactional Linguistics: An Introduction to Language in Social Interaction
E Couper-Kuhlen, M Selting – 2017 – books.google.com
Page 1. ELIZABETH GOUPER-KUHLEN AND MARGRE SELING INTERABLIUNAl?º Tººls N Page 2. INTERACTIONAL LINGUISTICS: STUDYING LANGUAGE IN SOCIAL INTERACTION The first textbook dedicated to interactional …

Painting Pictures with Words-From Theory to System
R Coyne – 2017 – search.proquest.com
… PAR allows instructions such as if you agree to go for a walk with someone, then follow them to be given and then triggered in the future. Ulysse [Godreaux et al., 1999] is an interactive spoken dialog system used to navigate in virtual worlds …

Computational models for semantic textual similarity
A González Aguirre – 2017 – addi.ehu.es
Page 1. UNIVERSITY OF THE BASQUE COUNTRY Computer Languages and Systems PhD Thesis Computational Models for Semantic Textual Similarity Aitor Gonzalez-Agirre 2017 (c)2017 AITOR GONZALEZ AGIRRE Page 2. Page 3 …

Natural Language Processing and Computational Linguistics 2: Semantics, Discourse and Applications
MZ Kurdi – 2017 – books.google.com
… Words have varied relationships on different levels. In addition to syntagmatic relations of co- occurrence, which are fundamentally syntactical, words have essentially semantic paradigmatic relations. These relations can be linear, hierarchical, or within clusters. 1.1.2.1 …

Can a machine generate humanlike language descriptions for a remote sensing image?
Z Shi, Z Zou – IEEE Transactions on Geoscience and Remote …, 2017 – ieeexplore.ieee.org
… previous results. Our model is designed based on a template-based approach with linguistic constraints, a technique that has been used for various practical applications such as summarization [37] and dialog systems [38]. Some …

Completion of Ontologies and Ontology Networks
Z Dragisic – 2017 – books.google.com
Page 1. Linköping Studies in Science and Technology Dissertation No. 1852 Completion of Ontologies and Ontology Networks Zlatan Dragisic Page 2. Linköping Studies in Science and Technology Dissertations. No. 1852 Completion …

Sabbiu Shah (070/BCT/531) Sagar Adhikari (070/BCT/533) Samip Subedi (070/BCT/536)
U Chalise – 2017 – researchgate.net
… human would behave as a conversational partner, thereby passing the Turing test. Chatterbots are typically used in dialog systems for various practical purposes including customer service or information acquisition. The classic …

New from Oxford University Press!
N Duffield – Canadian Modern Language Review/La Revue …, 2017 – linguistlist.org
… CALL into a Syllabus? BY Ibrahim Suliman Ahmed. Assessing user simulation for dialog systems using human judges and automatic evaluation measures BY Hua Ai AND Diane Litman. Providing graduated corrective feedback …

Multimodal Analysis of User-Generated Multimedia Content
R Shah, R Zimmermann – 2017 – Springer
… Examples of the second domain will include, but not limited to: computational and psychological models of emotions, bodily manifestations of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning …

Handling long-term dependencies and rare words in low-resource language modelling
M Singh – 2017 – publikationen.sulb.uni-saarland.de
Page 1. Handling long-term dependencies and rare words in low-resource language modelling A dissertation submitted towards the degree of Doctor of Engneering of the Faculty of Mathematics and Computer Science of Saarland University by Mittul Singh, (M.Sc.) …

Tag Recommendation for Short Arabic Text by Using Latent Semantic Analysis of Wikipedia
YKA Samra, IM Alagha – 2017 – mobt3ath.com
Page 1. Tag Recommendation for Short Arabic Text by Using Latent Semantic Analysis of Wikipedia Yousef K. Abu Samra Supervised By: Dr. Iyad M. Alagha Assistant Professor of Computer Science …

Automatic Text Simplification
H Saggion – Synthesis Lectures on Human Language …, 2017 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

Towards efficient Neural Machine Translation for Indian Languages
R Agrawal – 2017 – pdfs.semanticscholar.org
… The end-to-end nature of the training phase is also very conducive when dealing with sequences of unknown lengths beforehand, thereby making neural models an appropriate choice for other tasks like chatbots, speech recognition, dialogue systems, time series, question …

Computer Input of Morse Codes Using Finger Gesture Recognition
R Li – 2017 – aut.researchgateway.ac.nz
Page 1. 1 Computer Input of Morse Codes Using Finger Gesture Recognition Ricky Li A thesis submitted to the Auckland University of Technology in partial fulfilment of the requirements for the degree of Master of Computer and Information Sciences (MCIS) 2017 …

Computational Linguistic Creativity: Poetry generation given visual input
M Loller-Andersen – 2017 – brage.bibsys.no
Page 1. Computational Linguistic Creativity: Poetry generation given visual input Malte Loller-Andersen Master of Science in Computer Science Supervisor: Björn Gambäck, IDI Department of Computer Science Submission date: June 2017 …

Methods and Techniques for Clinical Text Modeling and Analytics
Y Ling – 2017 – search.proquest.com
Methods and Techniques for Clinical Text Modeling and Analytics. Abstract. This study focuses on developing and applying methods/techniques in different aspects of the system for clinical text understanding, at both corpus and document level …

(Visited 51 times, 1 visits today)