Cosine Similarity & Dialog Systems 2015


Cosine Similarity

Notes:

  • Conversational system

Resources:

Wikipedia:

References:

See also:

Abstractive Summarization 2013Language Computer Corporation (LCC)Lexical Chain & Dialog SystemsLSA (Latent Semantic Analysis) & Dialog Systems 2014LSM (Latent Semantic Mapping)NLP Tools & Dialog SystemsNLTK & Dialog SystemsOpenCalais 2012OpenEphyra (Ephyra Question Answering System)Porter StemmerQuora & Natural Language ProcessingSnowball 2013SVM (Support Vector Machine) & Dialog Systems 2014 | SVM (Support Vector Machine) & Dialog Systems 2015Text Summarization 2014TweetNLPVector Space & Dialog Systems 2014WordNet & Dialog Systems 2013WordNet & Dialog Systems 2014


The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems R Lowe, N Pow, I Serban, J Pineau – arXiv preprint arXiv:1506.08909, 2015 – arxiv.org … We seek a large dataset for research in dialogue systems with the following properties: • Two-way conversation, as opposed to multi- participant chat … Given a set of candidate response vectors, the one with the highest cosine similarity to the context vector is selected as the output … Cited by 17 Related articles All 12 versions

Learning OOV through semantic relatedness in spoken dialog systems M Sun, YN Chen, AI Rudnicky – Proc. The 16th Annual Conference of …, 2015 – cs.cmu.edu … Inevitably, a dialog system with static vocabulary has to face the OOV issue after deployment, eg, with the newly created words such as “selfie”. … Then the similarity be- tween words can be measured as the cosine similarity between their word embedding vectors. … Cited by 5 Related articles All 4 versions

Semeval-2015 task 2: Semantic textual similarity, english, spanish and pilot on interpretability E Agirrea, C Baneab, C Cardiec, D Cerd… – Proceedings of the 9th …, 2015 – aclweb.org … 2.1 English Subtask The English subtask dataset comprises pairs of sen- tences from news headlines (HDL), image descrip- tions (Images), answer pairs from a tutorial dialogue system (Answers-student), answer pairs … Vector similarity was computed using cosine similarity. … Cited by 66 Related articles All 12 versions

Matrix factorization with knowledge graph propagation for unsupervised spoken language understanding YN Chen, WY Wang, A Gershman… – Proceedings of ACL- …, 2015 – aclweb.org … frame-semantic context, not all the frames from the parsing re- sults can be used as the actual slots in the domain- specific dialogue systems. … word semantic rela- tions, we compute a matrix RS w = [Sim(wi,wj)]|W|×|W|, where Sim(wi,wj) is the cosine similarity between the de … Cited by 16 Related articles All 16 versions

Evaluating prerequisite qualities for learning end-to-end dialog systems J Dodge, A Gane, X Zhang, A Bordes, S Chopra… – arXiv preprint arXiv: …, 2015 – arxiv.org … The design of our tasks is such that all test one or more key characteristics a dialog system should have but also that an unambiguous answer is expected after each … In both cases the standard measure of similarity is tf-idf weighted cosine similarity between the bags of words. … Cited by 9 Related articles All 3 versions

A survey of available corpora for building data-driven dialogue systems IV Serban, R Lowe, L Charlin, J Pineau – arXiv preprint arXiv:1512.05742, 2015 – arxiv.org Page 1. A Survey of Available Corpora For Building Data-Driven Dialogue Systems Iulian Vlad Serban … In the area of dialogue systems, the trend is less obvious, and most practical systems are still built through significant engineering and expert knowledge. … Cited by 8 Related articles All 2 versions

Applying deep learning to answer selection: A study and an open task M Feng, B Xiang, MR Glass, L Wang… – 2015 IEEE Workshop …, 2015 – ieeexplore.ieee.org … 1. INTRODUCTION Natural language understanding based spoken dialog system has been a popular topic in the past years of artificial intelli- gence renaissance. … The last step is to calculate the cosine similarity between each ques- tion/candidate pair. … Cited by 11 Related articles All 4 versions

Improved deep learning baselines for ubuntu corpus dialogs R Kadlec, M Schmid, J Kleindienst – arXiv preprint arXiv:1510.03753, 2015 – arxiv.org … Because of its size, the corpus is well-suited for explorations of deep learning techniques in the context of dialogue systems. … Next, the cosine similarity between the context vector and each response vector is used to rank the responses. … Cited by 5 Related articles All 3 versions

Online adaptative zero-shot learning spoken language understanding using word-embedding E Ferreira, B Jabaian, F Lefèvre – 2015 IEEE International …, 2015 – ieeexplore.ieee.org … In dialogue systems, the Spoken Language Understanding (SLU) module extracts a list of semantic concept hypothe- ses from an input sentence transcription of the … 1) are then compared in terms of similarity (eg cosine similarity) to the known chunk vectors (black crosses in Fig. … Cited by 4 Related articles All 2 versions

Spoken language understanding in a nutrition dialogue system MB Korpusik – 2015 – dspace.mit.edu Page 1. Spoken Language Understanding in a Nutrition ARCVES Dialogue System by Mandy B. Korpusik … the lack of a specific nutrient. 1.1 Dialogue Systems Spoken dialogue systems like this one have become increasingly prevalent in today’s … Cited by 3 Related articles All 3 versions

Neural responding machine for short-text conversation L Shang, Z Lu, H Li – arXiv preprint arXiv:1503.02364, 2015 – arxiv.org … In this work, the whole 4.4 million Weibo pairs are used as the repository, 14 features, ranging from simple cosine similarity to some deep matching models (Ji et al., 2014) are used to determine the suitability of a post to … Njfun: a reinforce- ment learning spoken dialogue system. … Cited by 49 Related articles All 12 versions

Jointly modeling inter-slot relations by random walk on knowledge graphs for unsupervised spoken language understanding YN Chen, WY Wang… – Proceedings of NAACL- …, 2015 – pdfs.semanticscholar.org … and then selects a list of in- duced slots associated with their corresponding se- mantic decoders for use in domain-specific dialogue systems, where the … where Sim(xi,xj/t) is the cosine similarity be- tween the slot/word embeddings vxi and the context embeddings vxj/t after … Cited by 10 Related articles All 13 versions

Using summarization to discover argument facets in online idealogical dialog A Misra, P Anand, JEF Tree, MA Walker – NAACL HLT, 2015 – anthology.aclweb.org … Amita Misra, Pranav Anand, Jean Fox Tree, and Marilyn Walker UC Santa Cruz Natural Language and Dialogue Systems Lab 1156 N. High. … We used cosine similarity as the distance measure with average link- age criteria. … Cited by 4 Related articles All 7 versions

Tools for videogame discovery built using latent semantic analysis JO Ryan, E Kaltman, M Mateas… – Proc. Foundations of …, 2015 – users.soe.ucsc.edu … Eric Kaltman1, Michael Mateas1, and Noah Wardrip-Fruin1 1 Expressive Intelligence Studio 2 Natural Language and Dialogue Systems Lab University … existing games (from among GameNet’s 11,829 games) are most related to the game idea by using cosine similarity, just as … Cited by 2 Related articles All 4 versions

Automatic detection of miscommunication in spoken dialogue systems R Meena, JLG Skantze… – 16th Annual Meeting of …, 2015 – anthology.aclweb.org … Repetition: Two measures to estimate repetition in successive speaker turns were used:(i) cosine similarity, the cosine angle between vector repre … 6 Models and Method As mentioned earlier, the early and late models are aimed at online use in dialogue systems, whereas the … Cited by 2 Related articles All 15 versions

Classifying student dialogue acts with multimodal learning analytics A Ezen-Can, JF Grafsgaard, JC Lester… – Proceedings of the Fifth …, 2015 – dl.acm.org … Because in a tutorial dialogue system the tutor moves are system-generated, their dialogue acts are known. … For features other than the lexical features (task, dialogue-context and multimodal features) we use Cosine similarity, which captures similarity independent of the length … Cited by 2 Related articles All 6 versions

Conversational system for information navigation based on POMDP with user focus tracking K Yoshino, T Kawahara – Computer Speech & Language, 2015 – Elsevier … The fall-back is similar to collaborative response generation in the conversational spoken dialogue systems (Sadek, 1999), but it is intended for proactive information presentation using general documents … The relevance measure of predicates is calculated by cosine similarity,. … Cited by 2 Related articles All 3 versions

Learning Semantic Hierarchy with Distributed Representations for Unsupervised Spoken Language Understanding YN Chen, WY Wang, AI Rudnicky – Sixteenth Annual Conference of the …, 2015 – cs.cmu.edu … the semantic similarity is measured as the cosine similarity be- tween slot-fillers’ word embeddings trained on the large exter- nal data [3, 22]. The slot s with higher h(s) usually focuses on fewer topics, which is more specific and more likely to be a slot for dialogue systems. … Cited by 1 Related articles All 5 versions

A universal model for flexible item selection in conversational dialogs A Celikyilmaz, Z Feizollahi… – … IEEE Workshop on …, 2015 – ieeexplore.ieee.org … We have observed four types of referring expressions, however, real usage analysis of multi-model dialog systems have revealed that users mostly … Word Vector: This feature is the cosine similarity between the utterance and the item-title that measures the cosine of the angle … Cited by 1 Related articles All 2 versions

Learning Bidirectional Intent Embeddings by Convolutional Deep Structured Semantic Models for Spoken Language Understanding YN Chen, X He – Extended Abstract of The 29th Annual …, 2015 – research.microsoft.com … and bootstrap language understanding models [3, 4, 5, 6, 7]. These would then be used in human-machine dialogue systems that automate … We define a semantic score between an utterance U and an action I using the cosine similarity between their embeddings, yU and yI, as … Cited by 1 Related articles All 3 versions

Dialog State Tracking Challenge 4 S Kim, LF D’Haro, RE Banchs, J Williams… – 2015 – colips.org … In addition to this main task, we also propose a series of pilot tracks for the core components in developing end-to-end dialog systems based on the same dataset. … AM-FM: Weighted mean of (1) the cosine similarity between the system generated utterance and the reference … Cited by 1 Related articles All 2 versions

Fatal or not? Finding errors that lead to dialogue breakdowns in chat-oriented dialogue systems R Higashinaka, M Mizukami, K Funakoshi, M Araki… – Proc. EMNLP …, 2015 – aclweb.org … the details of the clus- ters one by one, each cluster seems to success- fully represent a certain error type in chat-oriented dialogue systems. … frequency vector of all comments con- tained in the cluster, and the similarity of the clus- ters was calculated by cosine similarity of word … Cited by 1 Related articles All 9 versions

Open-domain personalized dialog system using user-interested topics in system responses J Bang, S Han, K Lee, GG Lee – 2015 IEEE Workshop on …, 2015 – ieeexplore.ieee.org … Use of sentence embedding in an example-based dialog system achieved competitive evaluation result with respect to TF-IDF cosine similarity model and a superior result when the queries had out-of-vocabulary words [13]. … Related articles

Adaptive selection from multiple response candidates in example-based dialogue M Mizukami, H Kizuki, T Nomura… – … IEEE Workshop on …, 2015 – ieeexplore.ieee.org … However, these previous works use collaborative filtering only to evalu- ate the performance of the dialogue system or to predict user utterances. … Finally, the system estimates the satis- faction of each response by multiplying the cosine similarity between sest and su with the … Related articles All 2 versions

Adopting Semantic Similarity for Utterance Candidates Discovery from Human-to-Human Dialogue Corpus RY Shtykh, M Makita – International Workshop on Future and Emergent …, 2015 – Springer … microblogging services as Twitter, many have chosen the corpus-based (data-driven, or selection) approach for dialogue system construction, eg … syntactic-semantic similarity for response generation, and shows good results particularly in TF-IDF based cosine similarity retrieval. … Related articles All 4 versions

Non-speaker information reduction from Cosine Similarity Scoring in i-vector based speaker verification H Zeinali, A Mirian, H Sameti, B BabaAli – Computers & Electrical …, 2015 – Elsevier … Cover image Cover image. Non-speaker information reduction from Cosine Similarity Scoring in i-vector based speaker verification ?. … 4. Non-speaker information in cosine similarity. As mentioned earlier the i-vector contains different types of information. … Related articles All 3 versions

Humor Utterance Generation for Non-task-oriented Dialogue Systems S Fujikura, Y Ogawa, H Kikuchi – … of the 3rd International Conference on …, 2015 – dl.acm.org … A dialogue system must possess knowledge to generate a re- ply to the user. … We also express incongruity as word similarity and use cosine similarity using word2vec to construct vector representation from unsupervised learn- ing. … Related articles

Evaluation of a Fully Automatic Cooperative Persuasive Dialogue System T Hiraoka, G Neubig, S Sakti, T Toda… – … Dialog Systems and …, 2015 – Springer … Persuasive Dialogue System 163 2. Response candidates R are scored based on the following similarity score: cos.r:p:u; uinput/ D words.r:p:u/ words.uinput/ j words.r:p:u/ jj words.uinput/ j ; (15.7) uinput D ( u 0 sys .uuser D /; uuser .uuser ¤ /: The cosine similarity cos between … Related articles All 7 versions

A robust spoken Q&A system with scarce in-domain resources LF D’Haro, S Kim, RE Banchs – 2015 Asia-Pacific Signal and …, 2015 – ieeexplore.ieee.org … n-gram vectors from the surface forms of x and dx,i, where n is 1, 2, and 3. • Keyword Similarity: Cosine similarity between keyword vectors extracted from x and dx,i. • Question Type Similarity: Cosine similarity between question … “IRIS: a chat-oriented dialogue system based on … Related articles All 2 versions

Customized dialogue system based on biographical knowledge retrieval for elderly BH Su, PW Fu, JF Wang, TW Kuan… – … Conference on Orange …, 2015 – ieeexplore.ieee.org … Sentence Similarity Performance Evaluation In order to confirm that the computing performance of proposed PRCBRB method is fast on the dialogue system. Two sentence similarity algorithms are compared among PRCBRB, Cosine similarity [8], and the dynamic time warping …

Computing Semantic Textual Similarity Based on Partial Textual Entailment M V?ta – researchgate.net … Current approaches are based on a simple bag-of-words representation and a cosine similarity (in some cases improved by LSA application … Textual Entail- ment Challenge at SemEval-2013 Task 7. They were inspired by developments of tutorial dialogue systems (Dzikovska et … Related articles

Automatic ranking of swear words using word embeddings and pseudo-relevance feedback LF D’Haro, RE Banchs – 2015 Asia-Pacific Signal and …, 2015 – ieeexplore.ieee.org … The final ranking is generated by combining two baseline rankings: 1) using the normalized accumulated cosine similarity between the word embeddings of the swear word and the n-best list of closest neighborhoods, and 2 … “IRIS: a chat-oriented dialogue system based on the … Related articles All 2 versions

Improving Classification of Natural Language Answers to ITS Questions with Item-Specific Supervised Learning. BD Nye, MH Hajeer, Z Cai – FLAIRS Conference, 2015 – pdfs.semanticscholar.org … In this paper, we focus on evaluating the potential benefits of this approach to classifying human input to an ITS dialog system. … The most effective models con- sidered Latent Semantic Analysis (LSA) cosine similarity, item-specific regular expressions, and LSA match against the … Related articles All 2 versions

Statistical Response Method and Learning Data Acquisition using Gamified Crowdsourcing for a Non-task-oriented Dialogue Agent Y Enokibori, K Takahashi, K Mase – … 2014, Angers, France, March 6-8, …, 2015 – Springer … The number of words of a1 is 3 and a2 is 5. Therefore, the cosine similarity between a1 and a2 becomes 3÷( ? 3× ? 5)= 0. 77. … 15 (3–4), 331–340 (1994) 2. Chu-Carroll, J., Nickerson, JS: Evaluating automatic dialogue strategy adaptation for a spoken dialogue system. … Related articles All 2 versions

Content-Based Automated Assessment of Non-Native Spoken Language Proficiency in a Simulated Conversation K Evanini, S Singh, A Loukina, X Wang, CM Lee – aloukina.com … features in the context of an assessment of English for academic purposes, including LSA, Pointwise Mutual Information, and cosine similarity based on … a non-native speaker’s interactive speaking ability given the constraints of state-of-the-art spoken dialog systems (SDS) and … Related articles

Compilation and evaluation of paraphrase representation list of compound verbs: Toward development of “Control language for action” T Shirai, K Kanzaki, H Yabumoto… – … : Concepts, Theory and …, 2015 – ieeexplore.ieee.org … we performed a calculation of similarity between the compound verbs and verbs in a corpus by cosine similarity, and created a … Japanese-based controlled language for man-machine communication, aiming to verify its usefulness through experiments with the dialogue system. … Related articles

Neural Networks Revisited for Proper Name Retrieval from Diachronic Documents I Illina, D Fohr – LTC Language & Technology Conference, 2015 – hal.archives-ouvertes.fr … because proper names are essential for understanding the content of the speech (for example, for voice search, spoken dialog systems, broadcast news … D) Ranking of new PNs: The cosine-similarity metric is calculated between the projected vector of IV PNs found in the test … Related articles All 2 versions

Identification of Sympathy in Free Conversation T Fukuoka, K Shirai – 2015 – Citeseer … A set of 29 dialog acts including ’empathy’ was proposed toward an open-ended dialog system (Mi- nami et al., 2012). … The similar- ity between two samples (utterance) is measured by cosine similarity of the vector consisting of the word n-gram feature only. … Related articles All 8 versions

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems YN Chen – target, 2015 – cs.cmu.edu Page 1. Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems Yun-Nung (Vivian) Chen Ph.D. Thesis Proposal … 69 xiii Page 20. xiv Page 21. 1Introduction 1.1 Spoken Dialogue System … Related articles All 10 versions

The SENSEI Project: Making Sense of Human Conversations G Riccardi, F Bechet, M Danieli, B Favre… – … Workshop on Future …, 2015 – Springer … Three ways of ranking threads are the same as used in the baseline approaches and in addition we consider ranking threads by cosine similarity of the thread centroid to the original news article (computed using a standard vector space model with each comment modelled as a … Related articles All 2 versions

Content Finder Assistant R Laroche – Intelligence in Next Generation Networks (ICIN), …, 2015 – ieeexplore.ieee.org … It already goes further than performing question answering like Watson [7], but our ultimate goal is to generate low-cost spoken dialogue systems automatically that … on a Vector Space Model [24] and the relevance to a query q of any document d is given by the cosine similarity. … Related articles

Characterizing and Predicting Voice Query Reformulation A Hassan Awadallah, R Gurunath Kulkarni… – Proceedings of the 24th …, 2015 – dl.acm.org … There has been significant amount of research on spoken dialog systems in the last two decades [28] and recently partially observable … The similarity between any two queries is then computed by measuring the cosine similarity of the two vectors Phonetic Similarity: Voice query … Related articles

SpeakerLDA: Discovering Topics in Transcribed Multi-Speaker Audio Contents D Spina, JR Trippas, L Cavedon… – Proceedings of the Third …, 2015 – dl.acm.org … the topic distributions ?d, ?d over two given docu- ments d, d —for instance, by computing Hellinger distance [19] or cosine similarity between the … according to topic similarity may im- prove the application of current strategies for information presen- tation in dialog systems [8]. In … Related articles All 7 versions

A Perspective on Computer Assisted Assessment Techniques for Short Free-Text Answers S Roy, Y Narahari, OD Deshmukh – International Computer Assisted …, 2015 – Springer … If cosine similarity of a student response was greater than a threshold then the answer was considered correct. … 5(1), 36 (2006). 8. Dzikovska, M., Bell, P., Isard, A., Moore, JD: Evaluating language understanding accuracy with respect to objective outcomes in a dialogue system. … Related articles All 3 versions

Similarity computation using semantic networks created from web-harvested data E Iosif, A Potamianos – Natural Language Engineering, 2015 – Cambridge Univ Press … (2006) where the personalized PageRank algorithm (Haveliwala et al. 2002) was applied for the computation of a probability distribution for every target word. Word similarity was estimated via the cosine similarity between vectorized distributions. … Cited by 22 Related articles All 4 versions

Machine comprehension with syntax, frames, and semantics H Wang, MBKGD McAllester – Volume 2: Short Papers, 2015 – anthology.aclweb.org … feature B, instead of merely count- ing matches of the two bags of words, we also use cos (f+ qa, f+ w) and cos (f× qa, f× w) as features, where cos is cosine similarity. … Unsupervised induction and fill- ing of semantic slots for spoken dialogue systems using frame-semantic parsing … Cited by 7 Related articles All 11 versions

Weakly Supervised Natural Language Processing Framework for Abstractive Multi-Document Summarization: Weakly Supervised Abstractive Multi-Document … P Li, W Cai, H Huang – Proceedings of the 24th ACM International on …, 2015 – dl.acm.org … Given an affinity matrix W, the Laplacian is defined as L = D ? W, where D = diag(We), e = (1,…, 1)T . The way to learn affinity matrix will effect the final re- sults, thus in our experiments we test two popularly used methods: heat kernel and cosine similarity. … Related articles

Evaluation of Lexical-Based Approaches to the Semantic Similarity of Malay Sentences (the final version of this paper appeared in JOURNAL OF … SA Noah, N Omar, AY Amruddin – LINGUISTICS, 2015 – researchgate.net … based cosine similarity. They experimented with the corpus-based and knowledge-based approaches. … dialogue systems. Results from their experiments showed that the proposed method provides similarity measures that are fairly consistent with human knowledge. … Related articles

Large-Scale Question Answering with Joint Embedding and Proof Tree Decoding Z Wang, S Yan, H Wang, X Huang – … of the 24th ACM International on …, 2015 – dl.acm.org … QA on large scale structured KBs are critical to modern web search engines such as Bing and Google, spoken language dialog systems such as Cortana or Siri … 4. Cosine similarity score between the vector representations for input question and candidate utterance realization. … Related articles

Service personalisation of assistive robot for autism care R Khosla, K Nguyen, MT Chu – Industrial Electronics Society, …, 2015 – ieeexplore.ieee.org … Dialogue System Question Verbal/Non-verbal Analysis Answers of Elderly Matilda Remote PC Remote Touch Panel Image … Finally, the affect of the input text can be identified by computing the cosine similarity measure among the input vector and the affective anchor vectors. … Related articles

Hierarchical neural network generative models for movie dialogues IV Serban, A Sordoni, Y Bengio, A Courville… – arXiv preprint arXiv: …, 2015 – arxiv.org … Dialogue systems, also known as interactive con- versational agents, virtual agents and sometimes chatterbots, are used in a wide set of applications ranging from technical support services to lan- guage learning tools and entertainment (Young et al., 2013; Shawar and Atwell … Cited by 15 Related articles All 4 versions

Towards universal paraphrastic sentence embeddings J Wieting, M Bansal, K Gimpel, K Livescu – arXiv preprint arXiv: …, 2015 – arxiv.org … In this paper, we explore transferable compositional models that can encode arbitrary word sequences into a vector with the property that sequences with similar meaning have high cosine similarity, and that can, importantly, also transfer easily across domains. … Cited by 13 Related articles All 2 versions

Probabilistic features for connecting eye gaze to spoken language understanding A Prokofieva, M Slaney… – 2015 IEEE International …, 2015 – ieeexplore.ieee.org … These features include cosine similarity between term vectors of lk(t) and s(t), number of characters in the longest common subsequence of lk(t) and s(t), and a binary feature … [10] T. Misu, A. Raux, I. Lane, J. Devassy, and R. Gupta, “Situated multi-modal dialog system in vehicles … Cited by 2 Related articles All 11 versions

Data personalization G Koutrika – Data Management in Pervasive Systems, 2015 – Springer … Dialogue systems can support a broad range of applications in education, healthcare, and entertainment, such as responding to customers’ questions about … items ranked based on their similarity to F. The similarity may be computed as the inner product or cosine similarity of the … Cited by 2 Related articles All 3 versions

Evaluation of lexical-based approaches to the semantic similarity of Malay sentences SA Noah, N Omar, AY Amruddin – Journal of Quantitative …, 2015 – Taylor & Francis … information into measures of sentence similarity significantly increased the recognition likelihood as compared to the vector-based cosine similarity. … Their work focused on short sentences which are featured in applications such as conversational agents and dialogue systems. … Related articles All 4 versions

Learning to understand phrases by embedding the dictionary F Hill, K Cho, A Korhonen, Y Bengio – arXiv preprint arXiv:1504.00548, 2015 – arxiv.org … For the unseen evaluation, we randomly selected 500 words from WordNet and excluded all definitions of these 8Since we retrieve all answers from embedding spaces by cosine similarity, addition of word embeddings is equivalent to taking the mean. Page 6. … Cited by 9 Related articles All 10 versions

Adequacy–fluency metrics: Evaluating MT in the continuous space model framework RE Banchs, LF D’Haro, H Li – IEEE/ACM Transactions on Audio, …, 2015 – ieeexplore.ieee.org … Similar to the monolingual version of the metric, the AM component of the cross-language version is computed in the projected space by means of the cosine similarity between projected sentences. However, in this case, projections of the translation outputs … Cited by 6 Related articles All 3 versions

Fast single-and cross-show speaker diarization using binary key speaker modeling H Delgado, X Anguera, C Fredouille… – IEEE/ACM Transactions …, 2015 – dl.acm.org … (3) The cosine similarity formulation is considerably simpler than KL2 one, and its computation is faster. We also show in the experimental section that the cosine similarity is discriminant enough and suitable in our Gaussian selection algorithm. … Cited by 3 Related articles All 5 versions

Weakly supervised slot tagging with partially labeled sequences from web search click logs YB Kim, M Jeong, K Stratos… – Proceedings of the …, 2015 – msr-waypoint.com … define a measure- ment of dissimilarity between word tokens and slots, dist(wi,sj) = 1 ? sim(wi,sj) where sim(·,·) is cosine similarity over character … Log data is a set of queries created by actual users us- ing deployed spoken dialogue systems: thus it is di- rectly transcribed from … Cited by 4 Related articles All 12 versions

Explaining recommendations: Design and evaluation N Tintarev, J Masthoff – Recommender Systems Handbook, 2015 – Springer … The rec- ommender engine then infers a match between the item i and u’s needs. One 2The author does not specify which similarity metric was used, though it is likely to be a form of rating based similarity measure such as cosine similarity. Page 13. … Cited by 3 Related articles All 3 versions

Automatic assessment of syntactic complexity for spontaneous speech scoring S Bhat, SY Yoon – Speech Communication, 2015 – Elsevier … Currently, speech-enabled dialog systems allow learners to practice their speaking and listening with a virtual interlocutor (eg, SpeakESL), to receive … to a score class that has a similar POS distribution, where the similarity is captured by the cosine similarity function – the dot … Cited by 1 Related articles

Towards Universal Paraphrastic Sentence Embeddings JWMBK Gimpel, K Livescu – arXiv preprint arXiv: …, 2015 – pdfs.semanticscholar.org … In this paper, we explore transferable compositional models that can encode arbitrary word sequences into a vector with the property that sequences with similar meaning have high cosine similarity, and that can, importantly, also transfer easily across domains. … Related articles All 4 versions

Semantic similarity from natural language and ontology analysis S Harispe, S Ranwez, S Janaqi… – Synthesis Lectures on …, 2015 – 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 … Cited by 13 Related articles All 6 versions

EMNLP versus ACL: Analyzing NLP Research Over Time SD Gollapalli, XL Li – anthology.aclweb.org … 3. We apply Jensen-Shannon divergence and cosine similarity on our proposed venue rep- resentations to analyze the venues over … Topic ID Top Words 0 System, Dialogue, Dialogue System, Information, Speech Recognition, Speech, Dialogue Manager, Data Collection, User … Related articles All 10 versions

Four-participant group conversation: A facilitation robot controlling engagement density as the fourth participant Y Matsuyama, I Akiba, S Fujie, T Kobayashi – Computer Speech & …, 2015 – Elsevier … Many dialogue systems have dealt with turn-taking within two-participant engagement (Raux and Eskenazi, 2009 and Chao and Thomaz, 2012). … Fig. 1. (a) Two-participant conversation model, which has been focused upon by conventional dialogue systems. … Cited by 3 Related articles All 3 versions

A comparative study of evolving fuzzy grammar and machine learning techniques for text categorization NM Sharef, T Martin, KA Kasmiran, A Mustapha… – Soft Computing, 2015 – Springer … It has been utilized in many applications, such as dialogue systems, named entity recognition, information retrieval, and text categorization … Lexicographical similarity is often approached using a string similarity measure, such as edit distance and cosine similarity, while semantic … Related articles All 3 versions

Measuring Semantic Relatedness using Mined Semantic Analysis W Shalaby, W Zadrozny – arXiv preprint arXiv:1512.03465, 2015 – arxiv.org … structing such distributional vectors, relatedness is calculated using an appropriate vector similarity measure (eg, cosine similarity). … Natural language processing Indigenous Tweets Internet linguistics Statistical semantics Grammar induction Treebank Dialog systems Light verb … Related articles All 3 versions

Deep Reinforcement Learning with an Action Space Defined by Natural Language J He, J Chen, X He, J Gao, L Li… – arXiv preprint arXiv …, 2015 – pdfs.semanticscholar.org … In web search areas, Huang et al. (2013) developed the Deep Structured Semantic Model that uses deep neural networks to approximate this projection at a semantic level, and measure relevance by computing cosine similarity. … Cited by 3 Related articles

Improving the performance against force variation of emg controlled multifunctional upper-limb prostheses for transradial amputees A Al-Timemy, R Khushaba, G Bugmann, J Escudero – 2015 – ieeexplore.ieee.org … In the second step, we employ the cosine similarity to estimate the orientation between the extracted power spectrum Page 3. 1534-4320 (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. … Cited by 6 Related articles All 5 versions

Experiments in Information Retrieval KCÓ Kane – pdfs.semanticscholar.org Page 1. Experiments in Information Retrieval Kevin C. Ó Kane Professor Emeritus Computer Science Department University of Northern Iowa Cedar Falls, IA 50613 1 Page 2. Copyright © 2009, 2010, 2011, 2012, 2014 by Kevin C. Ó Kane. All rights reserved. … Related articles All 4 versions

[BOOK] Advances in Artificial Intelligence and Soft Computing G Sidorov, SN Galicia-Haro – 2015 – Springer Page 1. Grigori Sidorov Sofía N. Galicia-Haro (Eds.) 123 LNAI 9413 14th Mexican International Conference on Artificial Intelligence, MICAI 2015 Cuernavaca, Morelos, Mexico, October 25–31, 2015 Proceedings, Part I Advances in Artificial Intelligence and Soft Computing … Related articles All 2 versions

Speaker recognition by machines and humans: a tutorial review JHL Hansen, T Hasan – IEEE Signal Processing Magazine, 2015 – ieeexplore.ieee.org … human-to-machine: speech produced where the subject is directing his or her speech toward a piece of technology (eg, cell/smart/landline telephone and computer) —prompted speech: voice input to a computer —voice input for telephone/dialog system/computer input … Cited by 11 Related articles All 3 versions

Natural Language Processing for Social Media A Farzindar, D Inkpen – Synthesis Lectures on Human …, 2015 – 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 … Cited by 5 Related articles All 5 versions

Emotion recognition using semi-supervised feature selection with speaker normalization Y Sun, G Wen – International Journal of Speech Technology, 2015 – Springer … With the growth in the electronic and computer technologies, new spoken dialogue systems with emotion recognition capability are needed, for example, a nursing … if \(x\) is normalized to have unit norm, the dot product of two vectors is equivalent to the cosine similarity of the two … Related articles All 3 versions

Towards Large Scale Summarization JM Christensen – 2015 – digital.lib.washington.edu Page 1. c Copyright 2014 Janara Christensen Page 2. Page 3. Towards Large Scale Summarization Janara Christensen A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy University of Washington 2014 Reading … Cited by 1 Related articles All 3 versions

[BOOK] Advances in Artificial Intelligence and Its Applications: 14th Mexican International Conference on Artificial Intelligence, MICAI 2015, Cuernavaca, Morelos, … OP Lagunas, OH Alcántara, GA Figueroa – 2015 – books.google.com Page 1. Obdulia Pichardo Lagunas Oscar Herrera Alcántara Gustavo Arroyo Figueroa (Eds.) Advances in Artificial Intelligence and Its Applications 14th Mexican International Conference on Artificial Intelligence, MICAI 2015 … Related articles

Novel methods for text preprocessing and classification T Gasanova – 2015 – oparu.uni-ulm.de … 87 2.17 Co-Operation of Biology Related Algorithms (COBRA) . . . . 89 3.1 Overview of Spoken Dialogue Systems . . . . . 105 4.1 Common diagramm of text preprocessing and text classification . . . . . … Related articles All 3 versions

Spoken content retrieval—beyond cascading speech recognition with text retrieval L Lee, J Glass, H Lee, C Chan – IEEE/ACM Transactions on …, 2015 – ieeexplore.ieee.org Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 23, NO. 9, SEPTEMBER 2015 1389 Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval … Cited by 4 Related articles All 6 versions

Unsupervised extraction of semantic relations using discourse information J Conrath – 2015 – thesesups.ups-tlse.fr Page 1. THÈSE En vue de l’obtention du DOCTORAT DE L’UNIVERSITÉ DE TOULOUSE Présentée et soutenue le 14/12/2015 par : Juliette Conrath Unsupervised extraction of semantic relations using discourse information Directeurs de Thèse : … Related articles

Deep Neural Networks in Speech Recognition AL Maas – 2015 – stacks.stanford.edu … 115 7.1 Similarity of learned word vectors. Each target word is given with its five most similar words using cosine similarity of the vectors deter- mined by each model. … whether to call or email that contact. In a more complex dialog system, we may wish … Related articles

[BOOK] NLTK essentials N Hardeniya – 2015 – books.google.com … translation 63 Statistical machine translation 65 Information retrieval 65 Boolean retrieval 66 Vector space model 66 The probabilistic model 67 Speech recognition 68 Text classification 68 Information extraction 70 Question answering systems 70 Dialog systems 71 Word … All 6 versions