The Study on the Framework of Intelligence Information Processing

The technological progress in the field of artificial intelligence (AI) has brought new opportunities and challenges to the intelligent development and innovative research in fuzzy spatial relations, fuzzy theory is the basic theory of intelligent information processing, and the paper gives a brief analysis of fuzzy calculation method in spatial analysis and spatial relation calculation. In particular, the spatial relations of fuzzy objects are more difficult to express and describe accurately. This paper proposes a method to calculate the topological relations between fuzzy objects with 4-Intersection model and 9-Intersection model, in the analysis of spatial relations, the extension from deterministic entity to uncertain entity is realized with fuzzy set theory, the fuzzy space matrix is constructed, then fuzzy topological relations and fuzzy membership are calculated and output, the model simplifies many complex relations, and it can describe eight topological relations including disjoint, meet, overlap, covers, contains, covered-by, inside and equal. In practical application, the position of spatial objects can be controlled and adjusted according to topological relations. Through analysis of algorithm and fuzzy membership calculation, the model is effective in theory.

A model is considered in the paper as a communication link between natural intelligence and artificial one. It is both of cognitive and applied value, based on well-known facts of natural science and on cybernetic hypotheses necessary for its construction. It is shown in the paper that it is possible and expedient to use the model features in development of internal computer intelligence. The main principles of construction of a new class of intelligent solving machines are given as an example.

In this study, we explore the implications of dataset limitations in semantic knowledge-driven machine translation (MT) for intelligent virtual assistants (IVA). Our approach diverges from traditional single-best translation techniques, utilizing a multi-variant MT method that generates multiple valid translations per input sentence through a constrained beam search. This method extends beyond the typical constraints of specific verb ontologies, embedding within a broader semantic knowledge framework. We evaluate the performance of multi-variant MT models in translating training sets for Natural Language Understanding (NLU) models. These models are applied to semantically diverse datasets, including a detailed evaluation using the standard MultiATIS++ dataset. The results from this evaluation indicate that while multi-variant MT method is promising, its impact on improving intent classification (IC) accuracy is limited when applied to conventional datasets such as MultiATIS++. However, our findings underscore that the effectiveness of multi-variant translation is closely associated with the diversity and suitability of the datasets utilized. Finally, we provide an in-depth analysis focused on generating variant-aware NLU datasets. This analysis aims to offer guidance on enhancing NLU models through semantically rich and variant-sensitive datasets, maximizing the advantages of multi-variant MT.

The Seventh International Symposium on Neural Networks (ISNN 2010) was held on June 6–9, 2010 in Shanghai, China. The ISNN 2010 was a great success and provided a high-level international forum for scientists and engineers to present the latest research in neural networks, computational intelligence, cognitive systems, and related fields. To highlight the success of this conference, we edited this special issue for Cognitive Computation. We chose nine papers from over 591 papers submitted to ISNN 2010, which reflect the high quality of the presentations at the conference while capturing the spirit of our theme, ‘‘Advances in Computational Intelligence and Applications,’’ for this special issue. Our goal for this special issue is to present the latest research developments in computational intelligence with a focus on cognitive computation and their applications across a wide range of domains. Over the past decades, we have witnessed tremendous interest and developments in all aspects of computational intelligence research, ranging from both theoretical foundations, principles, to practical applications in different domains. To reflect a flavor of recent research activities in the community, we carefully selected these nine papers for this special issue. The selected papers can be organized into the following four coherent sections. The first section is directly related to neural network models and applications. The paper by Deng presents a new control strategy for the chaotic neural network, in which the refractoriness is tuned by using feedback control based on online averaging of network states. Simulation results demonstrate that the proposed model can achieve favorable performance in handling noisy, incomplete, and composite patterns, while also achieving either enhanced or comparable memory capacity compared with the classic Hopfield net and other chaotic neural network models. In the other paper, Gluge et al. discuss recurrent networks for implicit learning of temporal sequences, a very important area to understand high-level cognitive intelligence. The authors propose a recurrent network with backpropagation training algorithm that is adapted to the reinforcement learning scheme. The simulation results fit quantitatively as well as qualitatively to the behavioral results, suggesting the role of temporal context in associative learning scenarios. The second section is related to language processing and understanding, an important topic in cognitive science and computational intelligence. The paper by Murata et al. investigates the maximum entropy (ME) approach for natural language processing (NLP) problems including machine translation and information extraction. Comparative studies of the proposed approach with the existing techniques are illustrated in this paper. In related work to this field, the paper by Kaznatcheev investigates connectionist models on the interplay of nouns and pronouns in personal pronoun acquisition, a very interesting and important problem in psychology. For instance, the author discusses the learning in the shifting reference situation for children. It is reported that learning of two different noun-and-pronoun addressee patterns is consistent with Z. Zeng (&) Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, P. R. China e-mail: zgzeng@gmail.com

Part One: Machine translation: the early years Editor's Introduction 1 The linguistic basis of a mechanical thesaurus, and its application to English preposition classification 2 Linguistics and machine translation Part Two: Probabilistic grammar and the corpus Editor's Introduction 3 Towards probabilistic interpretations 4 Corpus studies and probabilistic grammar 5 Language as system and language as instance: the corpus as a theoretical construct 6 [with Z L James] A quantitative study of polarity and primary tense in the English Finite clause 7 Quantitative studies and probabilities in grammar 8 The spoken language corpus. Part Three: Towards 'intelligent computing' (computing with Meaning) Editor's Introduction 9 On language in relation to fuzzy logic and intelligent computing 10 Fuzzy grammatics: a systemic functional approach to fuzziness in neutral language 11 Computing meaning: some reflections on past experience and present prospects Appendix: Systems of the English clause: a trial grammar for the PENMAN text generation project. [Information Sciences Institute, University of Southern California].

The authors explore three topics in computational intelligence: machine translation, machine learning and user interface design and speculate on their effects on Web intelligence. Systems that can communicate naturally and learn from interactions will power Web intelligence's long term success. The large number of problems requiring Web-specific solutions demand a sustained and complementary effort to advance fundamental machine-learning research and incorporate a learning component into every Internet interaction. Traditional forms of machine translation either translate poorly, require resources that grow exponentially with the number of languages translated, or simplify language excessively. Recent success in statistical, nonlinguistic, and hybrid machine translation suggests that systems based on these technologies can achieve better results with a large annotated language corpus. Adapting existing computational intelligence solutions, when appropriate for Web intelligence applications, must incorporate a robust notion of learning that will scale to the Web, adapt to individual user requirements, and personalize interfaces.

Parallel machine translation (PMT) is a new machine translation paradigm that takes advantage of high-speed and large-memory computers and existing machine translation systems with different characteristics to solve the difficult machine translation problem. PMT is based on technologies of parallel computing, machine translation, and artificial intelligence. A PMT system consists of many machine translation procedures running in parallel, coordinated by a controller to dissolve various ambiguities in machine translation. We have designed and implemented a PMT system based on the above approach at a coarse parallel level. The system consists of four independent machine translation subsystems. Each subsystem is implemented using an existing machine translation technique and has its own characteristics. We present the principles and practice of PMT. We also present some results of experiments with our experimental PMT system and point out some future research on PMT.

In a multilingual diversity country like India, language translation plays a significant factor in the area of text processing application such as information extraction, machine learning, natural language understanding, information retrieval and machine translation. Thereexists many challenges and issues in translation between languages, especially the Dravidian language, such as ambiguities, lexical divergence, syntactic, lexical mismatches and semantic issues, etc. The n — gram language model (LM) performs very well machine translation. However the existing approach is not efficient for generating n — gram from large bi-lingual parallel corpora. Most existing approaches are limited to monolingual to minimize redundant n — gram. To overcome this, this work presents an efficient machine translation model using machine learning techniques. No prior work has considered machine translation of Kannada and Telugu. The experimentis conducted on Wikipedia dataset show significant performance in term of accuracy and computation complexity of alignment considering different threshold.

Idiomatic expressions have always been a bottleneck for language comprehension and natural language understanding, specifically for tasks like Machine Translation (MT). MT systems predominantly produce literal translations of idiomatic expressions as they do not exhibit generic and linguistically deterministic patterns which can be exploited for comprehension of the non-compositional meaning of the expressions. These expressions occur in parallel corpora used for training, but due to the comparatively high occurrences of the constituent words of idiomatic expressions in literal context, the idiomatic meaning gets overpowered by the compositional meaning of the expression. State of the art Metaphor Detection Systems are able to detect non-compositional usage at word level but miss out on idiosyncratic phrasal idiomatic expressions. This creates a dire need for a dataset with a wider coverage and higher occurrence of commonly occurring idiomatic expressions, the spans of which can be used for Metaphor Detection. With this in mind, we present our English Possible Idiomatic Expressions (EPIE) corpus containing 25,206 sentences labelled with lexical instances of 717 idiomatic expressions. These spans also cover literal usages for the given set of idiomatic expressions. We also present the utility of our dataset by using it to train a sequence labelling module and testing on three independent datasets with high accuracy, precision and recall scores.

Yorick Wilks is a central figure in the fields of Natural Language Processing and Artificial Intelligence. His influence extends to many areas and includes contributions to Machines Translation, word sense disambiguation, dialogue modeling and Information Extraction. This book celebrates the work of Yorick Wilks in the form of a selection of his papers which are intended to reflect the range and depth of his work. The volume accompanies a Festschrift which celebrates his contribution to the fields of Computational Linguistics and Artificial Intelligence. The papers include early work carried out at Cambridge University, descriptions of groundbreaking work on Machine Translation and Preference Semantics as well as more recent works on belief modeling and computational semantics. The selected papers reflect Yorick’s contribution to both practical and theoretical aspects of automatic language processing.

: If we want to build intelligent information retrieval systems, we will have to give them the capabilities of understanding Natural language, automatically organizing and reorganizing their memories, and using intelligent heuristics for searching their memories. These systems will have to analyze and understand both new text and Natural Language queries. In answering questions, they will have to direct memory search to reasonable places. This requires good organization of both the conceptual content of text and knowledge necessary for understanding those texts and accessing memory. The CYRUS and FRUMP systems (Kolodner (1978), Schank and Kolodner (1979), Dejong (1979)) comprise an information retrieval system called CyFr. Together, they have the analysis and retrieval capabilities mentioned above. FRUMP analysis news stories from the UPI wire for their conceptual content, and produces summaries of those stories. It sends summaries of stories about important people to CYRUS automatically adds those stories to its memory, and can then retrieve that information to answer question posed to it in natural language. This paper describes the problems involved in building such an intelligent system. It proposes solutions to some of those problems bases on recent research in Artificial Intelligence and Natural Language processing, and describes the CyFr system, which implements those solutions. The solutions we propose and implement are based on a model of human understanding and memory retrieval. (Author)

In the 1960s, the researchers of Harbin Institute of Technology (HIT) attempted to do relevant research on natural language processing. With more than 40-year’s effort, HIT has already established three research laboratories for Chinese information processing, i.e. the Machine Intelligence and Translation Laboratory (MI&T Lab), the Intelligent Technology and Natural Language Processing Laboratory (ITNLP) and the Information Retrieval Laboratory (IR-Lab). At present, it has a well-balanced research team of over 200 persons, and the research interests have extended to language processing, machine translation, text retrieval and other fields. Harbin Institute of Technology has accumulated a batch of key techniques and data resources, won many prizes in the technical evaluations at home and abroad. Harbin Institute of Technology has become one of the most important natural language processing bases for teaching and scientific research in China now. This paper gives an introduction to the achievements on NLP in HIT.

Clinical reasoning assessment is an essential component of determining a health professional’s competence. Clinical reasoning cannot be assessed directly. It must be gleaned from a health professional’s choices and decisions. Clinical knowledge and knowledge organization, rather than a general problem solving process, serve as the substrate for clinical reasoning ability. Unfortunately, the lack of a gold standard for the clinical reasoning process and the observation of context specificity make it difficult to assess clinical reasoning. Information processing theory, which focuses on the way the brain processes and organizes knowledge, has provided valuable insights into the cognitive psychology of diagnostic and therapeutic reasoning but failed to explain the variance in health professional’s diagnostic performance. Situativity theory has emerged suggesting that this variance relates to context-specific factors that impact a health professional’s clinical reasoning performance. Both information processing and situativity theory inform the way in which we assess clinical reasoning. Current assessment methods focus on standardized testing of knowledge to maximize psychometric parameters and work-based assessments which evaluate clinical reasoning under authentic, uncertain conditions that can decrease the reliability of these measurements. Issues of inter-rater reliability and context specificity require that multiple raters assess multiple encounters in multiple contexts to optimize validity and reliability. No single assessment method can assess all aspects of clinical reasoning; therefore, in order to improve the quality of assessments of clinical reasoning ability, different combinations of methods that measure different components of the clinical reasoning process are needed.

LLMs have become a go-to solution not just for text generation, but also for natural language understanding (NLU) tasks.Acquiring extensive knowledge through language modeling on web-scale corpora, they excel on English NLU, yet struggle to extend their NLU capabilities to underrepresented languages.In contrast, machine translation models (MT) produce excellent multilingual representations, resulting in strong translation performance even for lowresource languages.MT encoders, however, lack the knowledge necessary for comprehensive NLU that LLMs obtain through language modeling training on immense corpora.In this work, we get the best both worlds by integrating MT encoders directly into LLM backbones via sample-efficient self-distillation.The resulting MT-LLMs preserve the inherent multilingual representational alignment from the MT encoder, allowing lower-resource languages to tap into the rich knowledge embedded in English-centric LLMs.Merging the MT encoder and LLM in a single model, we mitigate the propagation of translation errors and inference overhead of MT decoding inherent to discrete translation-based cross-lingual transfer (e.g., translate-test).Evaluation spanning three prominent NLU tasks and 127 predominantly low-resource languages renders MT-LLMs highly effective in cross-lingual transfer.MT-LLMs substantially and consistently outperform translate-test based on the same MT model, showing that we truly unlock multilingual language understanding for LLMs. Experimental Setup Tasks and LanguagesWe evaluate on two established classification tasks and one multiple-choice machine reading compre-

We are studying an intelligent perceptual information processing system in which plural processing can run in parallel. Our proposed mathematical Activation-Input-Modulation (AIM) model controls each execution frequency of plural processing independently based on degrees of stimuli detected by external sensors. When external stimuli are detected by some of external sensors, information processing tasks related to the sensors have a priority to be executed, and the stimuli are stored in a memory system. When no external stimulus is detected, the execution frequencies of almost external information processing decrease, and information stored in the memory system is organized by internal information processors. The memory system consists of following three kinds of memories. One is a working memory for storing perceptual information for a few seconds at all times. Another is a short-term memory for storing external information detected as stimuli temporarily. The third is a long-term memory for storing important information permanently. By functions of internal information storing processors and these three kinds of memories, both dynamical and gradual changes can be stored in the memories. The advantage of our proposed method is that resources of a computing machine are made effective use of.