Session Program


  • 11 July 2017
  • 01:30PM - 03:30PM
  • Room: Borbonica
  • Chairs: Joao Paulo Carvalho and Keeley Crockett

Fuzzy Natural Language Processing II

Abstract - Memory-based Collaborative filtering solutions are dominant in the Recommendation Systems domain, due to their low implementation effort and service maintenance, when compared to Model-based approaches. Memory-based systems often rely on similarity metrics to compute similarities between items (or users) using ratings, in what is often named neighbor-based Collaborative filtering. This paper applies Fuzzy Fingerprints to create a novel similarity metric. In it, the Fuzzy Fingerprint of each item is described with a ranking of users ratings, combined with words obtained from the items' description. This allows the presented similarity metric to use fewer neighbors than other well-known metrics such as Cosine similarity or Pearson Correlation. Our proposal is able to reduce RMSE by at least 0.030 and improve NDCG10 by at least 0.017 when compared with the best baseline here presented.
Abstract - Back in 1967 the Croat linguist Z. Muljacic had used a fuzzy generalization of the Hamming distance between binary strings to classify Romance languages. In 1956 Cl. Shannon had introduced the notion of codeword distinguishability in zero-error information theory. Distance and distinguishability are subtly different notions, even if, with distances as those usually met in coding theory (ruling out zero-error information theory, which is definitely non-metric), the need for string distinguishabilities evaporates, since the distinguishability turns out to be an obvious and trivial function of the distance. Fuzzy Hamming distinguishabilities derived from Muljacic distances, instead, are quite relevant and must be considered explicitly. They are very easy to compute, however, and we show how they could be applied in coding theory to channels with erasures and blurs. Fuzzy Hamming distinguishabilities appear to be quite a promising tool to extend Muljacic approach from linguistic classification to linguistic evolution.
Abstract - In the recent past, domestic service robots have come under close scrutiny among researchers. When collaborating with humans, robots should be able to clearly understand the instructions conveyed by the human users. Voice interfaces are frequently used as a mean of interaction interface between users and robots, as it requires minimum amount of work overhead from the users. However, the information conveyed through the voice instructions are often ambiguous and cumbersome due to the inclusion of imprecise information. The voice instructions are often accompanied with gestures especially when referring objects, locations, directions etc. in the environment. However, the information conveyed solely through these gestures is also imprecise. Therefore, it is more effective to consider a multimodal interface rather than a unimodal interface in order to understand the user instructions. Moreover, the information conveyed through the gestures can be used to improve the understanding of the user instructions related to object placements. This paper proposes a method to enhance the interpretation of user instructions related to the object placements by interpreting the information conveyed through voice and gestures. Furthermore, the proposed system is capable of adapting the understanding, according to the spatial arrangement of the workspace of the robot. Fuzzy logic system is proposed in order to evaluate the information conveyed through these two modalities while considering the arrangement of the workspace. Experiments have been carried out in order to evaluate the performance of the proposed system. The experimental results validate the performance gain of the proposed multimodal system over the unimodal systems.
Abstract - Question answering (QA) is a challenging task and has received considerable attention in the last years. Answer selection among candidate answers is one of the main phases for QA and the best answer to be returned is determined in this phase. A common approach consists in considering the selection of the final answer(s) as a ranking problem. So far, different methods have been proposed, mainly oriented to produce a single best ranking model operating in the same way on all the question types. Differently, this paper proposes a fuzzy approach for ranking and selecting the correct answer among a list of candidates in a state-of-the-art QA system operating with factoid and description questions on Italian corpora pertaining a closed domain. Starting from the consideration that this ranking problem can be reduced to a classification one, the proposed approach is based on the Likelihood-Fuzzy Analysis (LFA), applied in this case for mining fuzzy rule-based models able to discern correct (True) from incorrect answers (False). Such fuzzy models are mined as specifically tailored to each question type, and, thus, can be individually applied to produce a more robust and accurate final ranking. An experimental session over a collection of questions pertaining the Cultural Heritage domain, using a manually annotated gold-standard dataset, shows that considering specific fuzzy ranking models for each question type improves the accuracy of the best answer returned back to the user.
Abstract - One of the proclaims often emphasized in papers on fuzzy sets and fuzzy logic is their ability to model semantics of certain linguistic expressions because their inherent vagueness can be captured by fuzzy sets. This direction of research was initiated by L. A. Zadeh already in his early papers and since then, most of the applications of fuzzy sets emphasize presence of natural language, at least in hidden form. Still, this ability is not generally accepted by linguists. In this paper we try to show that capturing linguistic semantics requires more sophisticated models. One possibility has been elaborated in the concept of {$\backslash$}emph\{fuzzy natural logic\} (FNL) that is a mathematical theory whose roots lay in the concept of natural logic developed by linguists and logicians. We also argue that it is reasonable to develop a simplified model that would capture the main features of the semantics of natural language and thus make it possible to realize sophisticated technical applications. In the paper, we outline how model of the meaning of basic constituents of natural language (nouns, adjectives, adverbs, verbs) has been elaborated in FNL.
Abstract - This paper aims to establish a link between linguistics and fuzzy phenomena.Throughout the history, linguistics has been relying on discrete descriptions to explain Natural Language Processing. This fact has a negative impact in various areas of language and technology since linguistics rejects all the inputs which are out from a discrete rule. Although this paper might approach the subject more from a linguistic than from a mathematical point of view, we present the theoretical considerations and reasoning used in elaborating a formal characterization of fuzziness in natural language grammars. Property Grammars will be used as the formal theory in order to explain Natural Language fuzziness and variability.