Social communication tools such as Twitter or Facebook spread the web service ability. Using their APIs, we can gather many users’ comments easily. Such comments are usually short sentences but they also have many emotional comments. In this paper, we propose emotion estimation methods for multilabeled short comments of web news. Our methods can be applied to sentiment analysis and opinion mining. At first, we show the performance evaluation of a naive Bayes classifier and an SVM classifier. Then, we propose two improved methods. The first is an improved naive Bayes method which classifies each emotion label into two opposite emotions and uses their weights. We call this the weighting method. The second method consists of two stages of classifiers. The first stage distinguishes these oppositely classes, and the second stage selects one emotion from the opposite emotions. From our evaluation, we conclude that the weighting method is better among the naive Bayes classifiers and its performance is as good as SVM’s.
This paper proposes a generation method for feature-structure-based unification grammars. As compared with fixed arity term notation. feature structure notation is more flexible for representing knowledge needed to generate idiomatic structures as well as general constructions. The method enables feature structure retrieval via multiple indices. The indexing mechanism, when used with a semantic head driven generation algorithm, attains efficient generation even when a large amount of generation knowledge must be considered. Our method can produce all possible structures in parallel, using structure sharing among ambiguous substructures.
This paper describes a natural language generation system developed for a spoken language translation system. Our system employs Feature‐structure‐based Tree Adjoining Grammar (FTAG) for generation knowledge representation. Each elementary tree of our grammar is paired with a semantic feature structure which is consistent with semantics defined in Head‐driven Phrase Structure Grammar. Feature structures attached to nodes of elementary trees are unrestricted. Thus our formalism allows HPSG style phrase structure description as well as TAG style description. The advantage of our generation knowledge representation is the ability of incorporating HPSG style “core” grammar and TAG style case‐based grammar. The system generates a syntactic tree by combining elementary trees so as to satisfy an input semantic structure. The generation algorithm is an application of a semantic head‐driven generation. To carry out an adjoining operation. an elementary tree with an adjunction node is dynamically split at the adjunction node during generation.
