CNN (Convolutional Neural Network) & Dialog Systems 2015


Notes:

From 2014 to 2015 the number of papers on CNNs in dialog systems in tripled.

  • Deep neural networks (DNNs)

Wikipedia:

Convolutional neural network

See also:

100 Best GitHub: Sentence Boundary | Sentence Boundary Disambiguation & Dialog Systems | Sentence Extraction | Sentence Extraction Module | Sentence Extractor | Sentence Generation Module | Sentence Grammaticality | Sentence Parsers & Dialog Systems | Sentence Patterns & Dialog Systems | Sentence Planner | Sentence Recognition | Sentence Splitter 2011 | Sentence Splitting & Dialog Systems | Sentence Summarization


Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking TH Wen, M Gasic, D Kim, N Mrksic, PH Su… – arXiv preprint arXiv: …, 2015 – arxiv.org … The latter is par- ticularly important in spoken dialogue systems where frequent repetition of identical output forms t. The work reported in this paper is part of a larger … A convolutional neural network for modelling sentences … Convolutional neural networks for sentence classification … Cited by 24 Related articles All 19 versions

Deep Contextual Language Understanding in Spoken Dialogue Systems C Liu, P Xu, R Sarikaya – Sixteenth Annual Conference of …, 2015 – research.microsoft.com … non-contextual modeling framework for multi- task SLU based on convolutional neural networks (CNN). … Moreover, adding dialog system response as external features provides consistent further gains, being … [15] P. Xu and R. Sarikaya, “Convolutional neural network based trian … Cited by 3 Related articles All 4 versions

Natural Language Dialogue-Future Way of Accessing Information H Li – 2015 – hangli-hl.com … Recursive Neural Networks • Convolutional Neural Networks Page 33. Word Representation: Neural Word Embedding )()( … the cat sat on the mat Page 36. Convolutional Neural Network (CNN) (Hu et al. … Page 40. Natural Language Dialogue System – Retrieval based Approach … Related articles All 2 versions

Learning to Process Natural Language in Big Data Environment H Li – 2015 – hangli-hl.com … Page 37. Natural Language Dialogue System – Generation based Approach • Encoding messages to … Fandong Meng, Zhengdong Lu, Mingxuan Wang, Hang Li, Wenbin Jiang, Qun Liu. Encoding Source Language with Convolutional Neural Network for Machine Translation. … Related articles All 3 versions

Building memory with concept learning capabilities from large-scale knowledge base J Shi, J Zhu – arXiv preprint arXiv:1512.01173, 2015 – arxiv.org … system can ask users for description when meeting an unknown entity, which is a natural behavior even for human during conversations. References [1] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. … Cited by 2 Related articles All 4 versions

KILLE: Learning Objects and Spatial Relations with Kinect E de Graaf, S Dobnik – SEMDIAL 2015 goDIAL, 2015 – pubman.mpdl.mpg.de … Rules for the dialogue system are written in OpenDial’s own XML format. … As the scale increases, however, it might become feasible to implement recognition with deep convolutional neural networks in favour of SIFT feature detec- tion. References P. Lison. 2014. … Related articles All 5 versions

Learning from real users: Rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems PH Su, D Vandyke, M Gasic, D Kim, N Mrksic… – arXiv preprint arXiv: …, 2015 – arxiv.org … Index Terms: spoken dialogue systems, real users, reward pre- diction, dialogue success classification, neural network … 2.3. Convolutional neural network model Also investigated was a convolutional neural network (CNN) [25] which has been successfully used for image … Cited by 13 Related articles All 12 versions

From distributional semantics to distributional pragmatics M Purver, M Sadrzadeh – … of the IWCS 2015 Workshop on …, 2015 – iwcs2015.github.io … models, with their ability to represent distributions over both utterance mean- ings and contexts, have shown more success in practical applications such as human-computer dialogue systems; for one … Recurrent convolutional neural networks for discourse com- positionality. … Cited by 1 Related articles All 3 versions

Geometry of Meaning from Words to Dialogue Acts M Purver, M Sadrzadeh – eecs.qmul.ac.uk … Probabilistic dialogue models that represent distributions over both utterance meanings and contexts, have shown success in practical applications such as human-computer dialogue systems (eg Young et … Recurrent convolutional neural networks for discourse compositionality. … Related articles All 2 versions

Using recurrent neural networks for slot filling in spoken language understanding G Mesnil, Y Dauphin, K Yao, Y Bengio… – … on Audio, Speech, …, 2015 – ieeexplore.ieee.org … word. These neural word embeddings [26] may be trained a-priori on external data such as the Wikipedia, with a variety of models ranging from shallow neural networks [21] to convolutional neural networks [20] and RNNs [22]. … Cited by 70 Related articles All 16 versions

Distributional semantics in use R Bernardi, G Boleda, R Fernández… – Workshop on Linking …, 2015 – aclweb.org … Le (2015) and Sordoni et al.(2015) use neural models to generate responses for online dialogue systems and tweets … Convolutional neural network archi- tectures for matching natural language sentences. … Recurrent convolutional neural networks for discourse compo- sitionality. … Cited by 2 Related articles All 15 versions

Laughter and filler detection in naturalistic audio L Kaushik, A Sangwan, JHL Hansen – Proceedings of Interspeech …, 2015 – researchgate.net … The new system uses Convolutional Neural Networks (CNNs) followed by simple low-pass … verbal vocalisations in conversa- tional speech,” Perception in multimodal dialogue systems, pp … Abdel-Hamid, L. Deng, and D. Yu, “Exploring convolutional neural network structures and … Cited by 1 Related articles All 2 versions

Strategic dialogue management via deep reinforcement learning H Cuayáhuitl, S Keizer, O Lemon – arXiv preprint arXiv:1511.08099, 2015 – arxiv.org … Deep Reinforcement Learning as in [22], which approx- imates Q? using a multilayer convolutional neural network. … 2The code of this substantial extension with an illustrative dialogue system is available at the … Move evaluation in go using deep convolutional neural networks. … Cited by 10 Related articles All 4 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 … Index Terms— Answer Selection, Question Answering, Convolutional Neural Network (CNN), Deep Learning, Spo … Natural language understanding based spoken dialog system has been a popular … this paper, a QA framework based on Convolutional Neural Networks (CNN) is … Cited by 25 Related articles All 4 versions

A critical review of recurrent neural networks for sequence learning ZC Lipton, J Berkowitz, C Elkan – arXiv preprint arXiv:1506.00019, 2015 – arxiv.org … belief networks (DNNs), which are greedily built by stacking re- stricted Boltzmann machines, and convolutional neural networks, which exploit … Besides dialogue systems, modern interactive systems of economic importance include self-driving cars and robotic surgery, among … Cited by 39 Related articles All 10 versions

Deep Reinforcement Learning with an Unbounded Action Space J He, J Chen, X He, J Gao, L Li, L Deng… – arXiv preprint arXiv: …, 2015 – arxiv.org … Mnih et al., 2013; Mnih et al., 2015) and was shown to achieve human level performance by applying convolutional neural networks to the raw … In DQN, a deep neural network (DNN, or deep convolutional neural network for Atari games) is used for such a function approximation. … Cited by 6 Related articles All 3 versions

Negative Emotion Recognition in Spoken Dialogs X Zhang, H Wang, L Li, M Zhao, Q Li – Chinese Computational Linguistics …, 2015 – Springer … with a visual concept representation vector computed using a deep convolutional neural network. … Kiela, D., Bottou, L.: Learning image embeddings using convolutional neural networks for improved … Tür, D.: Using context to improve emotion detection in spoken dialog systems. … Related articles All 2 versions

16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015) SBST a Better – 2015 – pdfs.semanticscholar.org … Page 26 Mon-O-1-6 12:40 – 13:00 Convolutional Neural Networks for Acoustic Modeling of Raw Time Signal in LVCSR Pavel Golik, Zoltán … Page 120 Mon-O-5-1 11:00 – 11:20 Deep Contextual Language Understanding in Spoken Dialogue Systems Chunxi Liu 1, Puyang Xu 2 …

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 the DQN, a deep convolutional neural network is used to extract high- level features from images, which are further mapped into Q … Mnih et al., 2013; Mnih et al., 2015) and was shown to achieve human level performance by applying convolutional neural networks to the raw … Cited by 4 Related articles

Contextual spoken language understanding using recurrent neural networks Y Shi, K Yao, H Chen, YC Pan… – … on Acoustics, Speech …, 2015 – ieeexplore.ieee.org … identification, intent classification and slot filling [1]. SLU is a crit- ical component in spoken dialogue systems. … Another nov- elty is using Convolutional Neural Networks (CNNs) [21] to extract features. … [25] P. Xu and R. Sarikaya, “Convolutional neural network based triangular … Cited by 14 Related articles All 7 versions

Improved deep learning baselines for ubuntu corpus dialogs R Kadlec, M Schmid, J Kleindienst – arXiv preprint arXiv:1510.03753, 2015 – arxiv.org … References [1] R. Lowe, N. Pow, I. Serban, and J. Pineau, “The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems,” arXiv preprint arXiv:1506.08909, 2015. … 1735–1780, 1997. [5] Y. Kim, “Convolutional neural networks for sentence … Cited by 9 Related articles All 3 versions

Feedback of robot states for object detection in natural language controlled robotic systems J Bao, Y Jia, Y Cheng, H Tang… – 2015 IEEE International …, 2015 – ieeexplore.ieee.org … [13] extracted object features using transfer learning from deep convolutional neural networks in order … through combining state-of-the-art computer vision and a natural dialog system. … recognition and pose estimation based on pre-trained convolutional neural network fea- tures. … Cited by 1 Related articles

A language model based approach towards large scale and lightweight language identification systems BML Srivastava, HK Vydana, AK Vuppala… – arXiv preprint arXiv: …, 2015 – arxiv.org … An LID system is a vital module for a wide range of mul- tilingual applications like, call centers, multilingual Spoken Dialog Systems, emergency services and … Additionally, convolutional neural networks have been studied to develop an end-to-end LID system for 8 languages in[5 … Related articles All 3 versions

An Auto-Encoder for Learning Conversation Representation Using LSTM X Zhou, B Hu, Q Chen, X Wang – International Conference on Neural …, 2015 – Springer … Linguist. 26(3), 339–374 (2000)CrossRef. 4. Rieser, V., Lemon, O.: Natural language generation as planning under uncertainty for spoken dialogue systems. … Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. … Related articles

Robot learning from verbal interaction: a brief survey H Cuayáhuitl – Proceedings of the New Frontiers in Human-Robot …, 2015 – mahasalem.net … [4] Heriberto Cuayáhuitl and Nina Dethlefs,’Dialogue systems using on- line learning: Beyond … [23] Pawel Swietojanski, Arnab Ghoshal, and Steve Renals,’Convolutional neural networks for distant speech recognition’, IEEE Signal Process. Lett., 21 (9), 1120–1124,(2014). … Cited by 4 Related articles All 2 versions

Towards universal paraphrastic sentence embeddings J Wieting, M Bansal, K Gimpel, K Livescu – arXiv preprint arXiv: …, 2015 – arxiv.org … 2015), recursive networks based on hierarchical structure but not parses (Zhao et al., 2015; Chen et al., 2015b), convolutional neural networks (Kalchbrenner et … to state-of-the-art results using a tree-LSTM (0.8676) (Tai et al., 2015) or a convolutional neural network (0.8686) (He … Cited by 22 Related articles All 2 versions

State-clustering based multiple deep neural networks modeling approach for speech recognition P Zhou, H Jiang, LR Dai, Y Hu… – IEEE/ACM Transactions …, 2015 – ieeexplore.ieee.org Page 1. 2329-9290 (c) 2015 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This … Cited by 7 Related articles All 3 versions

Learning to trade in strategic board games H Cuayáhuitl, S Keizer, O Lemon – Workshop on Computer Games, 2015 – Springer … Other related work has been carried out in the context of automated non-cooperative dialogue systems, where an agent may act to satisfy its own goals rather … Maddison, CJ, Huang, A., Sutskever, I., Silver, D.: Move evaluation in go using deep convolutional neural networks. … Cited by 3 Related articles

How? Why? What? Where? When? Who? Grounding Ontology in the Actions of a Situated Social Agent S Lallee, PFMJ Verschure – Robotics, 2015 – mdpi.com Robotic agents are spreading, incarnated as embodied entities, exploring the tangible world and interacting with us, or as virtual agents crawling over the web, parsing and generating data. In both cases, they require: (i) processes to acquire information; (ii) structures to model and … Cited by 1 Related articles All 7 versions

Towards Universal Paraphrastic Sentence Embeddings JWMBK Gimpel, K Livescu – arXiv preprint arXiv: …, 2015 – pdfs.semanticscholar.org … ranging from those based on simple operations like addition (Mitchell & Lapata, 2010; Yu & Dredze, 2015; Iyyer et al., 2015) to those based on richly-structured functions like recursive neural networks (Socher et al., 2011), convolutional neural networks (Kalchbrenner et al … Related articles All 4 versions

Learning Deep State Representations With Convolutional Autoencoders G Barth-Maron – pdfs.semanticscholar.org … variety of tasks, from robotics [10, 5, 15] to sequential decision-making games [32, 11], and dialogue systems [27, 34]. … stacked autoencoders have been shown to be very useful in performing unsupervised dimensionality reduction [8]. Convolutional neural networks (CNNs) use … Related articles All 5 versions

Recurrent Models for Auditory Attention in Multi-Microphone Distance Speech Recognition S Kim, I Lane – arXiv preprint arXiv:1511.06407, 2015 – arxiv.org … 1 INTRODUCTION Many real-world speech recognition applications, including teleconferencing, robotics and in-car spoken dialog systems, must deal with speech from distant microphones in noisy environments. … Convolutional neural networks for distant speech recognition. … Cited by 3 Related articles All 3 versions

Deep neural network acoustic models for spoken assessment applications J Cheng, X Chen, A Metallinou – Speech Communication, 2015 – Elsevier … In addition to the educational systems discussed above, there is a variety of other CALL applications (eg Eskenazi, 2009) that make use of an ASR engine, for example spoken dialog systems, learning game systems, tutoring systems, etc. … Cited by 6 Related articles All 3 versions

Negative Emotion Recognition in Spoken Dialogs Q Li – … Linguistics and Natural Language Processing Based …, 2015 – books.google.com … which concatenated a skip-gram linguistic representation vector with a visual concept representation vector computed using a deep convolutional neural network. … Liscombe, J., Riccardi, G., Hakkani-Tür, D.: Using context to improve emotion detection in spoken dialog systems. … Related articles

Self-Configuring Ensemble of Neural Network Classifiers for Emotion Recognition in the Intelligent Human-Machine Interaction E Sopov, I Ivanov – Computational Intelligence, 2015 IEEE …, 2015 – ieeexplore.ieee.org … Much research has been done on building intelligent dialogue systems (DS) that are able to collect this kind of … The approach combined multiple deep neural networks including deep convolutional neural networks (CNNs) for analyzing facial expressions in video frames, deep … Related articles

New transfer learning techniques for disparate label sets YB Kim, K Stratos, R Sarikaya, M Jeong – ACL. Association for …, 2015 – aclweb.org Page 1. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 473–482, Beijing, China, July 26-31, 2015. cO2015 Association for Computational Linguistics … Cited by 14 Related articles All 9 versions

Semi-supervised slot tagging in spoken language understanding using recurrent transductive support vector machines Y Shi, K Yao, H Chen, YC Pan… – 2015 IEEE Workshop on …, 2015 – ieeexplore.ieee.org Page 1. SEMI-SUPERVISED SLOT TAGGING IN SPOKEN LANGUAGE UNDERSTANDING USING RECURRENT TRANSDUCTIVE SUPPORT VECTOR MACHINES Yangyang Shi, Kaisheng Yao, Hu Chen, Yi-Cheng Pan, Mei-Yuh Hwang Microsoft 1. INTRODUCTION … Related articles

Deep Neural Networks in Speech Recognition AL Maas – 2015 – stacks.stanford.edu … 94 5.3 Performance comparison of DNNs, deep convolutional neural networks (DCNNs), and deep local untied neural networks (DLUNNs). We eval- … whether to call or email that contact. In a more complex dialog system, we may wish … Related articles

Learning trading negotiations using manually and automatically labelled data H Cuayáhuitl, S Keizer, O Lemon – Tools with Artificial …, 2015 – ieeexplore.ieee.org … Other related work has been carried out in the context of automated non-cooperative dialogue systems, where an agent may act to satisfy its own goals rather than those of other participants [5]. The game-theoretic underpinnings of non-cooperative behaviour have also been … Cited by 1 Related articles All 3 versions

Detecting actionable items in meetings by convolutional deep structured semantic models YN Chen, D Hakkani-T, X He – 2015 IEEE Workshop on …, 2015 – ieeexplore.ieee.org … focus on analyzing task-oriented di- alogues such as in customer care centers, and aim to infer se- mantic representations and bootstrap language understanding mod- els [4, 5, 6, 7, 8, 9]. These would then be used in human-machine dialogue systems that automate the … Cited by 3 Related articles All 5 versions

Question Answering Dialogue System: A Brief Review L Sharma, V Dhir, K Kaur – ijcsit-apm.com … Open Domain Convolutional Neural Network based Semantic Model to answer single- relation question Entity linking model is not so robust. [45] 20. A Dialogue System for Telugu, a Resource-Poor Language Metric Avera ge ratting Speed 4 Timeout 5 Recognitio n 3.5 … Related articles

Neural Enquirer: Learning to Query Tables P Yin, Z Lu, H Li, B Kao – arXiv preprint arXiv:1512.00965, 2015 – arxiv.org … More specifically, for the entry in the m-th row and n-th column with 1Other choices of sentence encoder such as LSTM or even convolutional neural networks are possible too 3 Page 4. Reader table embedding read vectors pooling Annotator row annotations table annotation … Cited by 10 Related articles All 3 versions

[BOOK] Sentic computing: a common-sense-based framework for concept-level sentiment analysis E Cambria, A Hussain – 2015 – books.google.com … 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 … Cited by 50 Related articles All 2 versions

Neural Enquirer: Learning to Query Tables with Natural Language P Yin, Z Lu, H Li, B Kao – arXiv preprint arXiv:1512.00965, 2015 – pdfs.semanticscholar.org … 1Other choices of sentence encoder such as LSTM or even convolutional neural networks are possible too 3 Page 4. Reader table embedding row reading pooling Annotator row annotations table annotation Memory Layer-( -1) query embedding Memory Layer- … Related articles All 3 versions

Dialog Management with Deep Neural Networks L Zilka – pdfs.semanticscholar.org … 1 Introduction A dialog state tracker is an essential component of modern spoken dialog systems. … The standard mode of operation of a spoken dialog system is turn-by-turn, where the system always waits for the user to stop talking and only then gener- ates its response. … Related articles All 3 versions

Multitask learning of deep neural networks for low-resource speech recognition D Chen, BKW Mak – IEEE/ACM Transactions on Audio, Speech, …, 2015 – ieeexplore.ieee.org … For example, [37] applies MTL on a single convolutional neural network to produce state-of-the-art performance for several language processing predictions; [38] improves intent classification in goal-oriented human-machine spoken dialog systems which is particularly … Cited by 6 Related articles All 4 versions

Multi-task Learning Deep Neural Networks for Automatic Speech Recognition D Chen – 2015 – cse.ust.hk … dictions; [20] improves intent classification in goal-oriented human-machine spoken dialog systems which is particularly successful when the amount of labeled training data is limited; in [21], the MTL approach is used to perform multi-label learning in an 4 Page 19. … Related articles

Sentiment analysis: Detecting valence, emotions, and other affectual states from text SM Mohammad – Emotion Measurement, 2015 – books.google.com … Brand management, customer relationship management, and stock market: Sentiment analysis of blogs, tweets, and Facebook posts is already widely used to shape brand image, track customer response, and in developing automatic dialogue systems for handling cus … Cited by 23 Related articles All 4 versions

Deep learning approaches to problems in speech recognition, computational chemistry, and natural language text processing GE Dahl – 2015 – tspace.library.utoronto.ca Page 1. Deep learning approaches to problems in speech recognition, computational chemistry, and natural language text processing by George Edward Dahl A thesis submitted in conformity with the requirements for the degree … Cited by 3 Related articles All 5 versions

State of the art in hand and finger modeling and animation N Wheatland, Y Wang, H Song, M Neff… – Computer Graphics …, 2015 – Wiley Online Library Our site uses cookies to improve your experience. You can find out more about our use of cookies in About Cookies, including instructions on how to turn off cookies if you wish to do so. By continuing to browse this site you agree … Cited by 11 Related articles All 9 versions

Spoken term detection ALBAYZIN 2014 evaluation: overview, systems, results, and discussion J Tejedor, DT Toledano… – EURASIP …, 2015 – asmp.eurasipjournals.springeropen. … Skip to main content. … Cited by 5 Related articles All 7 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 14 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

Spoken Language Understanding in a Nutrition 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 … Related articles

[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

Robust Speech Processing & Recognition: Speaker ID, Language ID, Speech Recognition/Keyword Spotting, Diarization/Co-Channel/Environmental Characterization … JH Hansen – 2015 – DTIC Document … discriminative method for training). Finally, deep learning methods such as convolutional neural networks (CNNs) provide further gains on top of the best MMI systems developed by CRSS-UTDallas. The solution developed … Related articles

Spoken Term Detection and Spoken Word Sense Induction on Noisy Data J Chiu – 2015 – cs.cmu.edu … 11 2.1.1 Word Recurrence in Dialogue Systems . . . . . … 2.1.1 Word Recurrence in Dialogue Systems (Barnett, 1973) propose the “Thematic Memory” as the content-word equivalent of the user-state syntax model. … Related articles

[BOOK] Computational Linguistics and Intelligent Text Processing: 16th International Conference, CICLing 2015, Cairo, Egypt, April 14-20, 2015, Proceedings A Gelbukh – 2015 – books.google.com … 335 Alia El Bolock and Slim Abdennadher A Multi-strategy Approach for Lexicalizing Linked Open Data….. 348 Rivindu Perera and Parma Nand A Dialogue System for Telugu, a Resource-Poor Language….. 364 Mullapudi Ch. … Related articles All 2 versions