Special Issue "Rich Linguistic Processing for Multilingual Text Mining"
Deadline for manuscript submissions: 11 January 2021.
Interests: natural language processing (NLP); multilingual and crosslingual NLP with an emphasis on low-resource languages; sentiment analysis and opinion mining on social media; information retrieval techniques applying NLP
Interests: My research interests lie mainly in the field of computational linguistics (or natural language processing). My main research focus is on natural language parsing algorithms, both from a theoretical and practical standpoint. I am especially interested in techniques to improve the speed of parsing algorithms, making them practical at the web scale, which is the focus of the ERC Starting Grant project FASTPARSE and the focal point of my current research; parsing beyond the “easy cases” such as non-projective dependency parsing (the search for parsing algorithms that can efficiently handle linguistic structures that contain crossing dependency links or, roughly equivalently, which contain discontinuous phrases), parsing morphologically rich languages, noisy text, etc.; and cognitive aspects of syntax, i.e., how the characteristics and constraints of the human brain shape the evolution of languages, and how we can take inspiration from the human language processing system to build better automatic parsers
Interests: My research interests are in the application of natural language processing techniques to improve text mining systems, including information retrieval/extraction and sentiment analysis tasks. More specifically, my research work includes lexical analysis (e.g., tokenization); morphological analysis; (shallow) parsing; information retrieval; cross-language information retrieval; character n-gram level processing; machine translation; microtext processing (e.g., tweets); Spanish and Galician language NLP
Natural language processing and text mining technologies have experienced a revolution in the last few years, with substantial improvements in accuracy mainly due to the use of deep-learning neural networks and large pretrained models relying on huge amounts of data. Explicit representations of linguistic knowledge (such as parse trees, semantic dependencies, lexicons, linguistic rules, etc.) have lost their protagonist role in systems where neural networks perform the bulk of the task, often in an end-to-end fashion. However, it is far from guaranteed that the accuracy improvement gains from the advances in neural architectures will not plateau, as in previous occasions, highlighting the need to combine them with rich linguistic processing. Furthermore, end-to-end neural systems have limitations, especially in a context of multilingualism where low-resource languages are involved: black-box nature with limited explainability, data-induced bias, reliance on large amounts of data that may be unavailable for many of the thousands of languages existing in the world, high computational requirements, and large energy usage and contribution to global warming.
For all these reasons, approaches utilizing explicit linguistic knowledge are highly relevant and should be pursued by the research community. In this Special Issue, we thus focus on approaches to natural language processing and text mining with an emphasis on multilingualism or low-resource languages, and which include rich linguistic processing, in the sense that explicit linguistic knowledge plays a relevant role in the approach, be it exclusively or in combination with machine learning and neural approaches.
Prof. Dr. Miguel A. Alonso
Prof. Dr. Carlos Gómez-Rodríguez
Prof. Dr. Jesús Vilares
- Natural language processing
- Multilingual language processing
- Language resources
- Linguistic knowledge
- Text mining
- Information retrieval
- Sentiment analysis
- Recommender systems
- Explainable artificial intelligence
- Data-induced bias in NLP systems