Assembling Actor-based Mind-Maps from Text Stream

Assembling Actor-based Mind-Maps from Text Streams Claudine Brucks and Christoph Schommer University of Luxembourg, Campus Kirchberg. Dept. of Computer Science and Communication, ILIAS Laboratory 6, Rue Richard Coudenhove-Kalergi, L-1359 Luxembourg Email: { claudine.brucks, christoph.schommer } @ uni.lu October 22, 2018 Abstract For human beings, the processing of text streams of unknown size leads generally to problems because e.g. noise must be selected out, information be tested for its relevance or redundancy, and linguistic phenomenon like ambiguity or the resolution of pronouns be advanced. Putting this into simulation by using an artificial mind-map is a challenge, which offers the gate for a wide field of applications like automatic text summarization or punctual retrieval. In this work we present a framework that is a first step towards an automatic intellect. It aims at assembling a mind-map based on incoming text streams and on a subject-verb-object strategy, having the verb as an interconnection between the adjacent nouns. The mind-map’s performance is enriched by a pronoun resolution engine that bases on the work of [9]. 1 Introduction A text stream is a data flow that is lost once it is read. Such a stream occurs very often in practice, for example while reading a text or listening to a story, probably told by someone else. In both cases, human beings store the major incidents rather associative. First, they remove noise and then extract information out of it, which can either be relevant or redundant/obvious. Then, relevant information is connected very adaptively, meaning that if the same information is read or listened again, the association between co-occurred words increases (or decreases, in case it is not). With such a performance, inconsiderable information gets lost whereas important facts can be kept. This is quite important, because a constructive processing - like the generation of a summarisation of the text and a retrieve of contents - becomes manageable. Incremental-adaptive mind-maps serve in a similar way as they simulate such a human per- formance: through their associative, incremental, and adaptive architecture they process incoming data streams, adapt internal structures depending on the given input, strengthen or weaken internal connections, and send longer-established connections to a simulating 1 arXiv:0810.4616v1 [cs.CL] 25 Oct 2008 short- and/or long-term memory. In this respect, we base on a work given by [14] that argues for a real-time approach for finding associative relationships between categorical entities from transactional data streams. Technically, these categorical entities are rep- resented as connectionist cells while associations are represented by links between them. These links may become stronger over time or degrade, according to whether the associa- tion re-occurs after a while or not is observed for a while. The work suggests a three-layer architecture: in the first layer, the short-term memory treats the incoming signals and con- structs the associations. The second layer, which is called the long-term memory, stores associations that have a strong connection and that may be useful for a further analysis. The last layer, the action layer serves as a communication interface with the user over which he can consult the actual state of the system and interact with it. The generation of such a mind-map becomes complicated by the fact that the incoming text can be corrupt or even ambiguous. For example, pronouns produce an ambiguity between existing/referenced persons in the text: having The President of United States has said that . . . and a succeeding Furthermore, he has mentioned that . . . leads undoubtedly to the same person but the recognition of such relationships is not natural. If we keep such relationships unsolved, the mind-map can become ineffective or even wrong. In this respect, a meaningful part of the intended mind-map described in this work concerns with the resolution of pronouns. For this, we are inspired by some earlier work, notably a syntax based approach [11]. All possible candidates for a pronoun are evaluated on a set of salience factors, as for example recency or subject emphasis. The candidate with the highest salience weight will be chosen as antecedent. [12] presents a similar approach where the candidates are evaluated on indicators, but no syntactic or semantic information on the sentence are needed. Furthermore, the mind-map concerns with a temporal management of text streams to construct an actor-based structure. 2 Architecture of the Mind-map The motivation of pronoun resolution for the semantic network learning is to find the correct antecedent for each pronoun. This is important to construct complete mind-maps for each actor in a text. For this, the text stream is treated by a sliding window, which first buffers and processes a certain number of sentences with the consequence that the information - once it is read - gets lost

…(Full text truncated)…

This content is AI-processed based on ArXiv data.