Advances and Applications of Deep Natural Language Processing
Deep Natural Language Processing (Deep NLP) is an emerging subfield of Artificial Intelligence (AI) and Natural Language Processing (NLP) that focuses on utilizing deep learning techniques to analyze and interpret human language at a more sophisticated level compared to traditional NLP approaches. While conventional NLP methods rely on handcrafted rules and shallow statistical models, Deep NLP leverages the power of neural networks and other deep learning architectures to capture the intricate nuances and complexities of natural language. This advanced approach enables computers to better understand and process human language, opening up new possibilities for various applications such as intelligent tutoring systems, machine translation, information extraction, and question answering.
Techniques and Components of Deep NLP
At the core of Deep NLP lie deep learning architectures specifically designed for processing natural language. Neural networks, particularly recurrent neural networks (RNNs) and transformers, have proven to be effective in capturing the sequential nature of language and learning meaningful representations of words, phrases, and sentences. These architectures form the foundation upon which various components of Deep NLP are built.
Syntactic parsing is one crucial component of Deep NLP, which involves analyzing the grammatical structure of sentences and identifying the relationships between words. Deep learning-based parsers have shown significant improvements over traditional rule-based or statistical parsers, enabling more accurate and robust syntactic analysis.
Semantic analysis is another essential aspect of Deep NLP, aiming to understand the meaning of words and sentences beyond their surface-level representations. Word sense disambiguation techniques, powered by deep learning, help in identifying the correct meaning of a word based on its context. Semantic role labeling, another important task, involves identifying the semantic relationships between predicates and their arguments in a sentence. Deep learning models have greatly enhanced the accuracy and efficiency of these semantic analysis tasks.
Discourse analysis and natural language inference are higher-level components of Deep NLP that deal with understanding the coherence and logical relationships between sentences and larger units of text. Deep learning approaches have enabled significant progress in these areas, allowing systems to better comprehend the overall structure and meaning of discourse.
The integration of knowledge bases is another crucial aspect of Deep NLP. By leveraging external sources of structured knowledge, such as ontologies and knowledge graphs, Deep NLP systems can incorporate real-world information and common sense reasoning capabilities, enhancing their understanding and generation of natural language.
Applications of Deep NLP
Deep NLP has found applications across various domains, revolutionizing the way computers interact with and process human language. One prominent application is in intelligent tutoring systems, where Deep NLP techniques are used to understand student responses, provide personalized feedback, and adapt the learning experience to individual needs. By analyzing the natural language input from students, these systems can identify misconceptions, provide targeted guidance, and engage in interactive dialogues to support learning.
Machine translation is another area where Deep NLP has made significant strides. Deep learning-based approaches, such as sequence-to-sequence models and transformer architectures, have greatly improved the quality and fluency of machine-translated text, enabling more accurate and natural translations between languages.
Deep NLP techniques have also been applied to grammar checking, helping to identify and correct grammatical errors in written text. By learning from large corpora of well-formed sentences, deep learning models can detect and suggest corrections for a wide range of grammatical mistakes.
Ontology learning, which involves automatically extracting structured knowledge from unstructured text, has benefited from Deep NLP approaches. By leveraging deep learning techniques, systems can identify key concepts, relationships, and hierarchies from natural language text, facilitating the construction of domain-specific ontologies.
Information extraction is another crucial application of Deep NLP, aiming to automatically extract structured information from unstructured text. Deep learning models have shown remarkable success in tasks such as named entity recognition, relation extraction, and event detection, enabling the extraction of valuable insights from large volumes of text data.
Question answering systems have also greatly benefited from Deep NLP techniques. By understanding the intent behind a user’s question and analyzing the relevant context, deep learning-based question answering systems can provide accurate and contextually appropriate answers, improving the user experience and information accessibility.
Text summarization is another important application of Deep NLP, which involves generating concise and coherent summaries of longer texts. There are two main approaches to text summarization: extractive summarization, which selects important sentences from the original text, and abstractive summarization, which generates new sentences that capture the key information. Deep learning models have shown promising results in both extractive and abstractive summarization, enabling the automatic generation of informative and readable summaries.
Challenges and Limitations
Despite the significant advances made in Deep NLP, there are still several challenges and limitations that need to be addressed. One major challenge is the complexity of deep NLP systems, which often require a large number of parameters and computational resources to train and deploy. This complexity can hinder the scalability and efficiency of deep NLP models, especially when dealing with large-scale datasets.
Another challenge is the need for large annotated datasets to train deep learning models effectively. Annotating natural language data is a time-consuming and labor-intensive task, requiring human expertise and effort. The lack of sufficient annotated data can limit the performance and generalization capabilities of deep NLP models.
Interpretability is another issue in deep learning-based NLP systems. Unlike traditional rule-based approaches, deep learning models often operate as “black boxes,” making it difficult to understand how they arrive at their predictions or decisions. This lack of interpretability can be problematic in scenarios where transparency and explainability are crucial, such as in legal or medical domains.
Handling out-of-vocabulary words and phrases is another challenge in Deep NLP. Deep learning models are typically trained on a fixed vocabulary, and they may struggle to handle rare or unseen words during inference. Techniques such as subword tokenization and character-level models have been proposed to mitigate this issue, but it remains an active area of research.
Abstractive summarization and natural language generation are particularly challenging tasks in Deep NLP. Generating coherent, grammatically correct, and semantically meaningful text requires a deep understanding of language structure, semantics, and context. While deep learning models have made progress in these areas, their ability to generate human-like text is still limited, and further research is needed to improve the quality and diversity of generated text.
Current Research Directions
To address the challenges and limitations of Deep NLP, researchers are actively exploring various directions to improve the efficiency, interpretability, and performance of deep learning models.
One active area of research is developing more efficient and scalable deep NLP models. Techniques such as model compression, knowledge distillation, and quantization are being investigated to reduce the computational requirements and memory footprint of deep learning models without sacrificing performance.
Incorporating commonsense reasoning and world knowledge into deep NLP systems is another important research direction. By integrating external knowledge sources and reasoning capabilities, deep NLP models can better understand the context and make more informed decisions. Research efforts are focused on developing methods to effectively represent and incorporate knowledge into deep learning architectures.
Explainable and interpretable deep NLP systems are also gaining attention in the research community. Techniques such as attention mechanisms, layer-wise relevance propagation, and post-hoc explanations are being explored to provide insights into the decision-making process of deep learning models. These approaches aim to make deep NLP systems more transparent and trustworthy.
Advancing abstractive summarization and natural language generation is another key research direction in Deep NLP. Researchers are investigating novel architectures, such as transformer-based models and generative adversarial networks (GANs), to improve the quality and coherence of generated text. Techniques like reinforcement learning and adversarial training are also being explored to enhance the diversity and human-likeness of generated text.
Applying deep NLP to low-resource languages is another important research area. Many languages have limited annotated data and linguistic resources, making it challenging to develop effective deep NLP models. Researchers are exploring techniques such as transfer learning, multi-lingual models, and unsupervised learning to leverage resources from high-resource languages and adapt them to low-resource scenarios.
Future Outlook and Potential Impact
The advancements in Deep NLP have the potential to revolutionize the way humans interact with computers and access information. With the development of more sophisticated natural language interfaces, users will be able to communicate with computers using everyday language, making technology more accessible and intuitive. Deep NLP-powered virtual assistants and chatbots will become more intelligent and context-aware, providing personalized and efficient assistance to users.
Deep NLP will also have a profound impact on information access and knowledge discovery. By enabling the automatic extraction of structured knowledge from vast amounts of unstructured text data, Deep NLP will facilitate the creation of comprehensive knowledge bases and intelligent information retrieval systems. This will empower users to quickly find relevant information and gain insights from large-scale text corpora.
However, as Deep NLP technologies become more powerful and pervasive, it is crucial to consider the ethical implications and ensure responsible development. Issues such as privacy, bias, and fairness need to be addressed to prevent the misuse or unintended consequences of deep NLP systems. Researchers and practitioners must work together to develop guidelines and best practices for the ethical deployment of Deep NLP technologies.
Conclusion
Deep Natural Language Processing represents a significant advancement in the field of AI and NLP, enabling computers to understand and process human language at an unprecedented level. By leveraging deep learning techniques, Deep NLP has made remarkable progress in various tasks such as syntactic parsing, semantic analysis, discourse understanding, and natural language generation.
The applications of Deep NLP span across diverse domains, including intelligent tutoring systems, machine translation, grammar checking, ontology learning, information extraction, question answering, and text summarization. These applications have the potential to transform the way we learn, communicate, and access information.
However, Deep NLP also faces several challenges and limitations, such as the complexity of models, the need for large annotated datasets, lack of interpretability, handling out-of-vocabulary words, and generating coherent and diverse text. Researchers are actively exploring various directions to address these challenges, focusing on improving efficiency, interpretability, and performance of deep NLP models.
As Deep NLP continues to evolve and mature, it holds immense potential for transformative impact across various domains. By enabling more natural and intelligent human-computer interaction, Deep NLP will make technology more accessible and user-friendly. It will also revolutionize information access and knowledge discovery, empowering users to extract valuable insights from vast amounts of text data.
However, the development of Deep NLP technologies must be accompanied by a strong emphasis on ethics and responsible AI practices. Researchers, practitioners, and policymakers must work together to ensure that Deep NLP systems are developed and deployed in a manner that benefits society while minimizing potential risks and unintended consequences.
In conclusion, Deep Natural Language Processing represents an exciting and rapidly evolving field with immense potential for transformative impact. Continued research and development in this area will undoubtedly lead to new breakthroughs and applications that will shape the future of human-computer interaction and knowledge discovery. As we move forward, it is crucial to foster collaboration between academia, industry, and policymakers to ensure the responsible and beneficial advancement of Deep NLP technologies.
See also:
Alchemy Open Source AI | DeepDive | YAGO2
- Alguliev, R. M., Aliguliyev, R. M., & Isazade, N. R. (2012). DESAMC+ DocSum: Differential evolution with self-adaptive mutation and crossover parameters for multi-document summarization. Knowledge-Based Systems, 33, 21-34.
- Alguliev, R. M., Aliguliyev, R. M., & Isazade, N. R. (2013). Multiple documents summarization based on evolutionary optimization algorithm. Expert Systems with Applications, 40(5), 1675-1689.
- Alguliev, R. M., Aliguliyev, R. M., & Isazade, N. R. (2013). An optimization approach to automatic generic document summarization. Computational Intelligence, 29(3), 394-430.
- Andreasen, T., & Bulskov, H. (2013). Summarization by domain ontology navigation. International Journal of Intelligent Systems, 28(1), 64-82.
- Azevedo, R. R. D., Freitas, F., Rocha, R., Menezes, J. A. A., & Rodrigues, C. M. O. (2014). Towards a framework for ontology learning from inter-actions in natural language and reasoning. Retrieved from https://faculty.uoit.ca/
- Azevedo, R. R., Freitas, F., & Rocha, R. (2014). Generating Description Logic ALC from Text in Natural. In Proceedings of Intelligent Systems (pp. 365-374). Springer, Cham.
- Azevedo, R. R., Freitas, F., & Rocha, R. (2014). Representing Knowledge in DL ALC from Text. Procedia Computer Science, 35, 998-1007.
- Azevedo, R. R., Freitas, F., Rocha, R. G., Menezes, J. A. A., & Rodrigues, C. M. O. (2014). An approach for automatic expressive ontology construction from natural language. In Intelligent Science and Intelligent Data Engineering (pp. 546-555). Springer, Berlin, Heidelberg.
- Azevedo, R. R., Freitas, F., Rocha, R., & Menezes, J. A. A. (2014). An approach for learning and construction of expressive ontology from text in natural language. In 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) (Vol. 1, pp. 149-156). IEEE.
- Babour, A., & Khan, J. I. (2014). Tweet sentiment analytics with context sensitive tone-word lexicon. In Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)-Volume 01 (pp. 392-399). IEEE Computer Society.
- Bhattacharya, S., & Toldo, L. (2012). Question answering for Alzheimer disease using information retrieval. In CLEF (Online Working Notes/Labs/Workshop) 2012 (Vol. 1178).
- Blaylock, N., de Beaumont, W., Allen, J., & Jung, H. (2011). Towards an OWL-based framework for extracting information from clinical texts. In Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium (pp. 61-70). ACM.
- Catlett, B. D. C. (2013). Using Clouds for Technical Computing. In Cloud Computing and Big Data (pp. 143-152). IOS Press.
- Cheng, X. Q., Du, P., Guo, J., Zhu, X., & Chen, Y. (2013). Ranking on data manifold with sink points. IEEE Transactions on Knowledge and Data Engineering, 25(1), 177-191.
- Chong, M. Y. M. (2013). A study on plagiarism detection and plagiarism direction identification using natural language processing techniques (Doctoral dissertation, University of Wolverhampton).
- Costa, F., & Branco, A. (2013). Full-fledged temporal processing: bridging the gap between deep linguistic processing and temporal extraction. Journal of Language Modelling, 1(1), 97-154.
- Cramer, M. (2013). Proof-checking mathematical texts in controlled natural language (Doctoral dissertation, Universität Bonn).
- Azevedo, R. R. D., Freitas, F., Rocha, R., Menezes, J. A. A., & Rodrigues, C. M. O. (2014). Towards a framework for ontology learning from inter-actions in natural language and reasoning. Retrieved from https://faculty.uoit.ca/
- Dadzie, A. S., Uren, V., & Ciravegna, F. (2011). Ontology-based knowledge capture & sharing in enterprise organisations. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 277-298). IGI Global.
- De Azevedo, R. R., Freitas, F., Rocha, R., & de Menezes, J. A. A. (2014). An approach for automatic expressive ontology construction from natural language. In Portuguese Conference on Artificial Intelligence (pp. 546-555). Springer, Cham.
- De Azevedo, R. R., Freitas, F., Rocha, R., & de Menezes, J. A. A. (2014). Generating description logic ALC from text in natural language. In Mexican International Conference on Artificial Intelligence (pp. 365-374). Springer, Cham.
- De Azevedo, R. R., Freitas, F., Rocha, R., & de Menezes, J. A. A. (2014). Representing knowledge in DL ALC from text. Procedia Computer Science, 35, 998-1007.
- Del Corro, L., & Gemulla, R. (2013). Clausie: clause-based open information extraction. In Proceedings of the 22nd international conference on World Wide Web (pp. 355-366).
- Eckert, K., Meusel, R., & Stuckenschmidt, H. (2011). User-centered maintenance of concept hierarchies. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 325-349). IGI Global.
- Epstein, E. A., Schor, M. I., Iyer, B. S., Lally, A., Brown, E. W., & Cwiklik, J. (2012). Making watson fast. IBM Journal of Research and Development, 56(3.4), 1-15.
- Fattah, M. A. (2014). A hybrid machine learning model for multi-document summarization. Applied Intelligence, 40(4), 592-600.
- Ferreira, J. Z., Rodrigues, J., Cristo, M., & de Oliveira, M. C. F. (2014). Multi-entity polarity analysis in financial documents. In Proceedings of the 20th Brazilian symposium on multimedia and the web (pp. 115-122).
- Foong, O. M., Yong, S. P., & Lee, A. L. (2014). Text summarization in android mobile devices. In Recent Advances in Information and Communication Technology (pp. 75-84). Springer, Cham.
- Galescu, L., & Blaylock, N. (2012). A corpus of clinical narratives annotated with temporal information. In Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium (pp. 715-720).
- Guo, C. (2011). Explore dissimilarity method for summarization. Journal of Convergence Information Technology, 6(5).
- Gomaa, W. H., & Fahmy, A. A. (2011). Tapping into the power of automatic scoring. In The Eleventh International Conference on Language Engineering, Ain Shams University, Cairo, Egypt.
- Gomaa, W. H., & Fahmy, A. A. (2012). Short answer grading using string similarity and corpus-based similarity. International Journal of Advanced Computer Science and Applications (IJACSA), 3(11), 115-121.
- Grappy, A., Grau, B., Falco, M. H., Ligozat, A. L., Robba, I., & Vilnat, A. (2011). Selecting answers to questions from Web documents by a robust validation process. In Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology-Volume 01 (pp. 55-62). IEEE Computer Society.
- Hafernik, C. (2011). Automatic methods to disambiguate geospatial queries (Doctoral dissertation, Mount Holyoke College).
- High, R. (2012). The era of cognitive systems: An inside look at ibm watson and how it works. IBM Corporation, Redbooks.
- Hjelm, H., & Volk, M. (2011). Cross-language ontology learning. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 272-292). IGI Global.
- Kerr, D., Mousavi, H., & Iseli, M. R. (2013). Automatic short essay scoring using natural language processing to extract semantic information in the form of propositions. Retrieved from https://semscape.cs.ucla.edu/
- Kim, J. B., & Yang, J. (2011). Symmetric and asymmetric properties in korean verbal coordination: A computational implementation. Language and Information, 15(2), 1.
- Kiyomarsi, F., & Esfahani, F. R. (2011). Optimizing persian text summarization based on fuzzy logic approach. In Proceedings of the International Conference on Intelligent Building and Management (Vol. 5, pp. 264-268). IACSIT Press.
- Kotis, K., & Papasalouros, A. (2011). Automated learning of social ontologies. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 293-324). IGI Global.
- Kotzias, D., Denil, M., De Freitas, N., & Smyth, P. (2015). From group to individual labels using deep features. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 597-606).
- Li, B., Wong, K. F., Zhou, L., & Feng, S. (2011). An efficient approach for sentence-based opinion retrieval. International Journal of Computer Processing of Languages, 23(02), 151-181.
- Lu, B., Tsou, B. K., Jiang, T., Zhu, J., & Kwong, O. Y. (2011). Mining parallel knowledge from comparable patents. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 247-271). IGI Global.
- Lukmana, I., Swanjaya, D., Kurniawardhani, A., Arifin, A. Z., & Purwarianti, A. (2014). Multi-document summarization based on sentence clustering improved using topic words. JUTI: Jurnal Ilmiah Teknologi Informasi, 12(2), 1-8.
- Macías-Galindo, D. (2014). Domain-sensitive topic management in a modular conversational agent framework (Doctoral dissertation, RMIT University).
- Mastora, A., & Kapidakis, S. (2012). Query rewriting using shallow language processing: Effects on keyword subject searches. In Proceedings of the First International Workshop on Supporting User’s Exploration on Digital Libraries (pp. 26-31).
- Mavrikis, M., Grawemeyer, B., Hansen, A., & Gutiérrez-Santos, S. (2014). Exploring the potential of speech recognition to support problem solving and reflection. In European Conference on Technology Enhanced Learning (pp. 263-276). Springer, Cham.
- Mazzei, A., Lesmo, L., Battaglino, C., Vendrame, M., & Bucciarelli, M. (2013). Deep natural language processing for italian sign language translation. In Proceedings of the XIII Conference of the Italian Association for Artificial Intelligence (pp. 193-204). Springer, Cham.
- Mazurek, C., Sielski, K., Stroi?ski, M., Walkowska, J., Werla, M., & W?glarz, J. (2012). Transforming a flat metadata schema to a semantic web ontology: The polish digital libraries federation and CIDOC CRM case study. In Intelligent tools for building a scientific information platform (pp. 153-178). Springer, Berlin, Heidelberg.
- Mizuno, J., Nichols, E., Watanabe, Y., & Inui, K. (2012). Organizing information on the web through agreement-conflict relation classification. In Information Retrieval Technology (pp. 90-101). Springer, Berlin, Heidelberg.
- Murdock, J. W., Fan, J., Lally, A., Shima, H., & Boguraev, B. (2012). Textual evidence gathering and analysis. IBM Journal of Research and Development, 56(3.4), 1-14.
- Niu, F., Zhang, C., Ré, C., & Shavlik, J. W. (2012). DeepDive: Web-scale knowledge-base construction using statistical learning and inference. In VLDS (pp. 25-28).
- Peñas, A., Hovy, E., Forner, P., Rodrigo, Á., Sutcliffe, R., Forascu, C., & Sporleder, C. (2011). Overview of qa4mre at clef 2011: Question answering for machine reading evaluation. In CLEF (Notebook Papers/Labs/Workshop).
- Pérez, C. G., & Cardeñosa, J. (2011). Knowledge extraction for question titling. In International Conference on Flexible Query Answering Systems (pp. 135-146). Springer, Berlin, Heidelberg.
- Plank, B., Sauer, T., & Schaefer, I. (2013). Supporting agile software development by natural language processing. In Evolving Software Systems (pp. 21-42). Springer, Berlin, Heidelberg.
- Plachouras, V., Rivière, M., & Vazirgiannis, M. (2012). Named entity recognition and identification for finding the owner of a home page. In Advances in Knowledge Discovery and Data Mining (pp. 370-381). Springer, Berlin, Heidelberg.
- Ramana, D. V. S. (2014). Extracting summary from documents using k-mean clustering algorithm. International Journal of Computer Science and Network Security (IJCSNS), 14(9), 51.
- Richter, M. M., & Weber, R. O. (2013). Conversational CBR. In Case-Based Reasoning (pp. 323-354). Springer, Berlin, Heidelberg.
- Rus, V., Baggett, W., Gire, E., Franceschetti, D., Conley, M., & Graesser, A. (2013). Towards learner models based on learning progressions (LPs) in DeepTutor. In AIED 2013 Workshops Proceedings (pp. 183-187).
- Rus, V., Baggett, W., Gire, E., Franceschetti, D., Conley, M., Graesser, A., & McNamara, D. (2013). Learner models based on learning progressions with DeepTutor. In Design recommendations for adaptive intelligent tutoring systems (pp. 183-192).
- Rus, V., D’Mello, S. K., Hu, X., & Graesser, A. C. (2013). Recent advances in conversational intelligent tutoring systems. AI Magazine, 34(3), 42-54.
- Saktel, P., & Shrawankar, U. (2012). Context based meaning extraction for HCI using WSD algorithm: A review. In 2012 Nirma University International Conference on Engineering (NUiCONE) (pp. 1-6). IEEE.
- Saktel, P., & Shrawankar, U. (2013). An improved approach for word ambiguity removal. arXiv preprint arXiv:1304.7282.
- Sayed, M. A. (2014). Utilizing graph-based representation of text in a hybrid approach to multiple documents summarization (Doctoral dissertation, The American University in Cairo).
- Schäfer, U., & Kiefer, B. (2011). Advances in deep parsing of scholarly paper content. In Advanced Language Technologies for Digital Libraries (pp. 135-161). Springer, Berlin, Heidelberg.
- Schedl, M., Widmer, G., Knees, P., & Pohle, T. (2011). A music information system automatically generated via web content mining techniques. Information Processing & Management, 47(3), 426-439.
- Shaalan, Y. M. (2011). Frequently asked questions web pages automatic text summarization (Doctoral dissertation, The American University in Cairo).
- Simões, G., Galhardas, H., & Matos, D. (2013). A labeled graph kernel for relationship extraction. arXiv preprint arXiv:1302.4874.
- Sondhi, P., & Zhai, C. X. (2014). Mining semi-structured online knowledge bases to answer natural language questions on community QA websites. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management (pp. 341-350).
- Steels, L. (2011). Why we need evolutionary semantics. In KI 2011: Advances in Artificial Intelligence (pp. 1-8). Springer, Berlin, Heidelberg.
- Steels, L. (2012). Grounding language through evolutionary language games. In Language grounding in robots (pp. 1-22). Springer, Boston, MA.
- Tanaka, K., Takiguchi, T., & Ariki, Y. (2012). Towards domain independent why text segment classification based on bag of function words. In AI 2012: Advances in Artificial Intelligence (pp. 395-406). Springer, Berlin, Heidelberg.
- Tanner-Davies, D., & McNaught, J. (2014). Using tweets to summarise news stories. University of Manchester.
- Thakur, A. (2013). Algorithm to resolve anaphoric ambiguity of text summarization (Doctoral dissertation).
- Thenmalar, S., & Geetha, T. V. (2014). Enhanced ontology-based indexing and searching. Aslib Journal of Information Management, 66(6), 678-696.
- Vela, M. (2012). Extraction of ontology schema components from financial news (Doctoral dissertation, Universität des Saarlandes).
- Verspoor, K., Cohn, J., Ravikumar, K., & Wall, M. (2012). Text mining improves prediction of protein functional sites. PLoS One, 7(2), e32171.
- Wang, D., & Li, T. (2012). Weighted consensus multi-document summarization. Information Processing & Management, 48(3), 513-523.
- Wang, D., Zhu, S., Li, T., & Gong, Y. (2012). Comparative document summarization via discriminative sentence selection. ACM Transactions on Knowledge Discovery from Data (TKDD), 6(3), 12.
- Wang, D., Zhu, S., Li, T., Chi, Y., & Gong, Y. (2011). Integrating document clustering and multidocument summarization. ACM Transactions on Knowledge Discovery from Data (TKDD), 5(3), 14.
- Wen, D., Cuzzola, J., Brown, L., & Kinshuk. (2012). Instructor-aided asynchronous question answering system for online education and distance learning. The International Review of Research in Open and Distributed Learning, 13(5), 102-125.
- Wen, D., Cuzzola, J., Brown, L., & Kinshuk. (2012). Exploiting semantic roles for asynchronous question answering in an educational setting. In Advances in Artificial Intelligence (pp. 374-379). Springer, Berlin, Heidelberg.
- Wong, W., Liu, W., & Bennamoun, M. (2011). Ontology learning and knowledge discovery using the web: Challenges and recent advances. IGI Global.
- Wong, W., Thangarajah, J., & Padgham, L. (2012). Contextual question answering for the health domain. Journal of the American Society for Information Science and Technology, 63(11), 2313-2327.
- Xiong, W. (2014). A better indicator for genre classification: Topic word or surface text feature: A case study of recognition of brief biography. In 2014 11th International Conference on Service Systems and Service Management (ICSSSM) (pp. 1-6). IEEE.
- Yamamoto, Y. (2012). Disputed sentence suggestion towards credibility-oriented web search. In Web Technologies and Applications (pp. 34-45). Springer, Berlin, Heidelberg.
- Yamamoto, Y., & Tanaka, K. (2011). Towards web search by sentence queries: Asking the web for query substitutions. In International Conference on Database Systems for Advanced Applications (pp. 473-474). Springer, Berlin, Heidelberg.
- Yang, X., Yang, J., & Chen, C. (2012). Tuple refinement method based on relationship keyword extension. In Web Information Systems and Mining (pp. 261-270). Springer, Berlin, Heidelberg.
- Yuan, L. (2013). Improved head-driven statistical models for natural language parsing. Journal of Central South University, 20, 1258-1263.
- Zhang, J., & El-Gohary, N. M. (2012). Automated information transformation for automated regulatory compliance checking in construction. Journal of Computing in Civil Engineering, 29(4), B4015001.
- Zhang, P., Li, W., Hou, Y., & Song, D. (2011). Developing position structure-based framework for chinese entity relation extraction. ACM Transactions on Asian Language Information Processing (TALIP), 10(3), 12.
- Zhang, Z., & Ciravegna, F. (2011). Named entity recognition for ontology population using background knowledge from Wikipedia. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 236-246). IGI Global.
- Zouaq, A. (2011). An overview of shallow and deep natural language processing for ontology learning. In Ontology Learning and Knowledge Discovery Using the Web: Challenges and Recent Advances (pp. 16-37). IGI Global.