Tiansi Dong

A natural language question answering system as a participant in human Q&A portals

LogAnswer is a question answering (QA) system for the German language, aimed at providing concise and correct answers to arbitrary questions. For this purpose LogAnswer is designed as an embedded artificial intelligence system which integrates methods from several fields of AI, namely natural language processing, machine learning, knowledge representation and automated theorem proving. We intend to employ LogAnswer as a virtual user within Internet-based QA forums, where it must be able to identify the questions that it cannot answer correctly, a task that normally receives little attention in QA research compared to the actual answer derivation. The paper presents a machine learning solution to the wrong answer avoidance (WAA) problem, applying a meta classifier to the output of simple term-based classifiers and a rich set of other WAA features. Experiments with a large set of real-world questions from a QA forum show that the proposed method significantly improves the WAA characteristics of our system.

A COMMENT ON RCC: FROM RCC TO RCC++

The Region Connection Calculus (RCC theory) is a well-known spatial representation of topological relations between regions. It claims that the connection relation is primitive in the spatial domain. We argue that the connection relation is indeed primitive to the spatial relations, although in RCC theory there is no room for distance relations. We first analyze some aspects of the RCC theory, e.g. the two axioms in the RCC theory are not strong enough to govern the connection relation, regions in the RCC theory cannot be points, the uniqueness of the

A Novel Machine Translation Method for Learning Chinese as a Foreign Language

\iota

Cognitive Prism - More Than a Metaphor of Metaphor

operation in the theory is not guaranteed, etc. To solve some of the problems, we propose an extension to the RCC theory by introducing the notion of region category and adding a new axiom which governs the characteristic property of the connection relation. The extended theory is named as RCC++. We support the claim that the connection relation is primitive to spatial domain by showing how distance relations, size relations are developed in RCC++. At last we revisit a sub-family of un-intended models in RCC theory, argue that RCC++ is more suitable than RCC with regards to its original intended model, and discuss the representation limitation of the RCC, as well as RCC++.

Cognitive prism: A bridge between meta cognitive model and higher cognitive models

This paper reviews related work in cognitive psychology, philosophy, and a bunch of independent research work in spatial knowledge representation, sets some criteria for potential spatial representations for cognitive informatics(CI), i.e. an expected theory of spatial knowledge for the meta representation layer of cognitive informatics shall take region as primitive, and be able to develop other spatial concepts. The paper critically points out the limitations of one dominant theory in spatial cognition, the RCC theory. It then introduces internal relations among different kinds of spatial knowledge, outlines a basic connection calculus for extended objects, and shows how notions of orientation relations, distance relations are developed in this calculus. The paper briefly presents how the notion of point can be further developed. By showing this we argue that this calculus meets the criteria for being a potential spatial representation for meta cognitive process layer of CI.

SNAPVis and SPANVis: ontologies for recognizing variable vista spatial environments

It is not easy for western people to learn Chinese. Native German speakers find it difficult to understand how Chinese sentences convey meanings without using cases. Statistical machine translation tools may deliver correct German-Chinese translations, but would not explain educational matters. This article reviews some interdisciplinary research on bilingualism, and expounds on how translation is carried out through cross-linguistic cue switching processes. Machine translation approaches are revisited from the perspective of cue switching concluding that: the word order cue is explicitly simulated in all machine translation approaches, and the case cue being implicitly simulated in statistical machine translation approaches can be explicitly simulated in rule-based and example-based machine translation approaches. A convergent result of machine translation research is to advocate an explicit deep-linguistic representation. Here, a novel machine translation method is motivated by blending existing machine translation methods from the viewpoint of cue-switching, and is firstly aimed as an educational tool. This approach takes a limited amount of German-Chinese translations in textbooks as examples, whose cues can be manually obtained, and for which we have developed MultiNet-like deep linguistic representations and cross-linguistic cue-switching processes. Based on this corpus, our present tool is aimed at helping native German speakers to learn Chinese more efficiently, and shall later be expanded to a more comprehensive machine translation system.

LogAnswer IN QUESTION ANSWERING FORUMS

A dialogue system, Richard, for free communication on daily issues is under construction. Daily issues are classified into tree-structured event knowledge-base. For each event topic, we retrieve dialogue examples from the Internet. Basic-level Upper Ontologies (BLUO) are proposed to categorize words of these examples. Event identification is realized by comparing the similarity between BLUOs of an input sentence and BLUOs of example sentences in the event knowledge-base. Cosine similarity algorithm is adopted to select the most possible event domain. BLUOs of an input sentence are combined to the sentence ID. A difference distance acts as a metric to determine the most similar ID in the script with input sentence ID. An example of free dialogue within Greeting-Shopping-Restaurant domains is described. On-going work on meaning-based dialogue system and dialogue-based learning is outlined.

Modeling Human Intelligence as A Slow Intelligence System.

In this chapter we address a basic question in the functional model of the mind: with which mechanism a cognitive agent can understand new concepts? and propose an answer: the cognitive prism mechanism. This mechanism is rooted in the information process of a neuron. Research results in cognitive psychology and linguistics support that such mechanism is used in concept-understanding in our everyday-life. We show that this mechanism is used to integrate spatial environments existing at different temporal points and form a spatial concept. Lakoff’s theory in concept-understanding can be reformulated in terms of the cognitive prism mechanism. The classic mathematical logic, as well as fuzzy logic, can be understood as the (prism) mapping from language to true or false values. In Chinese medicine, human-body structure is referenced to spatial concepts through certain cognitive prism mechanism. We argue that metaphor is not only the mechanism to relate concepts in non-physical domain to physical ones, but also the mechanism to relate concepts within the physical domain. We briefly criticize the current theory of joke and propose a novel perspective to the understanding of jokes in term of ‘potential tension’ of cognitive prism. We conclude that equipped with the cognitive prism mechanism and concepts of spatial environment cognitive agents shall understand quite a lot of spatial/non-spatial concepts.