The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Annotating complicated noun phrases is a difficulty in semantic analysis. In this paper we investigate the annotation methods of noun phrases in Nombank, Chinese Nombank and Sinica Treebank trying to propose an annotation scheme based on semantic dependency graph for noun phrases.
This study examines the challenging issues in the semantic annotation of the characteristics of verbal information of Mandarin Chinese. It proposes a frame-based constructional approach that aligns with linguistic premises in Frame Semantics, Construction Grammar and Cognitive Grammar. Given that semantic processing has a lot to do with human cognitive capacities, semantic transfer and profile on...
The subtree kernel and the information tree kernel proposed here measure the syntactic similarity of sentences. For two syntactic trees, these kernels are defined, respectively, as the total number of common subtrees in the syntactic trees and the total information content contained in their common subtrees, where the information content of a common subtree is calculated using its probability. Analyses...
In this paper, we propose a question representation based on entity labeling and question classification for a automatic question answering system of Chinese Gaokao history question. A CRF model is used for the entity labeling and SVM/ CNN/LSTM models are tested for question classification. Our experiments show that CRF model provides a high performance when used to label informative entities out...
Attributes are the way we describe the world. A simple classification on attributes' object host or event host is not enough for explaining appearance of both object attributes and event attributes. Thus we propose a presentation and explanation for attributes which introduce single and group host criterion for object attributes and linguistic valence for event attributes. Especially, we argue that...
In this paper, we first discuss the thematic properties of the yu phrases in both active and passive contexts in Archaic Chinese. We argue that the function of the yu phrase is actually determined by the properties of the main verb and the so-called Agent in passives can be understood as other thematic roles. Second, we provide syntactic analysis of the yu passives. We assume that these yu passives...
Influenced by the grammatical system of western languages, there are more and more syntactic structures in modern Chinese that can be translated into English attributive clauses. But for the great differences of the syntactic structures, parsing Chinese by western grammatical rules usually does not lead to satisfactory results, which will result in poor translation performance in complex syntactic...
The essence of Imperative Speech Act is to encourage the listener to take the speaker-desired action by applying linguistic strategies. In the process of communication, various strategies are frequently used to secure the realization of the imperative action. Imperative strategies include syntactic and pragmatic strategies, specific elements involve in the application of which are studied. The principle...
This paper discusses word of Haodai from the perspective of language information processing. The meaning and usages of Haodai are very complex in Mandarin. Its functions and usages in simple sentence and compound sentence have been carefully examined with explanation and appropriate examples.
There are different opinions on the names and quantity of semantic roles. In order to analyze the deep meaning of human language, we did two parts of tasks based on Chinese Semantic Dependency Graph Bank, which is a corpus analyzed by semantic dependency graph (SDG). After calculating the frequency of each role, we normalized the roles' names and distinguished the differences between each other. There...
Automatic Question Answering (QA) is a hot topic in both Natural Language Processing (NLP) and Information Retrieval (IR). And question classification is the key step of a successful automatic QA system. In this paper, an SVM-based approach is firstly proposed as our baseline system. Then two additional features, i.e., top-words and dependency relations, are introduced to improve the performance of...
Patents constitute one of the most challenging domains for machine translation because patent sentences can be quite long with complex structures. This paper presents a hierarchical reordering method based on three-level parsing for Chinese-English patent MT. After integrating into a Phrase based SMT system, our method improves the BLEU score by 1.92. There are also improvements in NIST and METEOR...
Patent documents involve many professional fields and include multiple paragraphs, which have brought great difficulties for patent machine translation. This paper presents a hybrid strategy for patent machine translation, which combines the template-based machine translation (TBMT), the semantic rule-based machine translation (RBMT) and the statistics-based machine translation (SMT). The TBMT and...
The study of intonation in a tonal language presents a challenge. The challenge is to see how a language succeeds in encoding the functions which is shown by means of intonation in non-tonal languages. This paper demonstrates most of the intonational marking in tonal language in Yichang.
In order to better serve the international Chinese teaching, according to the sentence-based syntactic system and Chinese syntax structure characteristics, the paper builds a basic sentence-pattern instance database based on the international Chinese textbook Treebank. Based on the instance database, the paper adds an index for the predicate, and then extracts the relevant knowledge and information...
The classifier-noun construction in Mandarin is different from the numeral-classifier-noun construction in the aspects of syntactic distribution and semantic interpretation. This paper analyzes the syntactic classifier-noun construction in the perspective of Generative Grammar. Under the discussion of the morphosyntactic property of Chinese classifiers, the paper argues that in the classifier-noun...
Word Sense Disambiguation (WSD) methods based on supervised learning usually convert WSD to a classification problem. Traditional WSD methods based on supervised learning often only consider the word, position, part of speech and some other superficial morphological and syntactic features. However, for a certain kind of polysemous words, their different senses usually appear in characteristic contexts...
The constitutive role is one of qualia roles, this paper presents an approach for the automatic acquisition of constitutive role for Chinese nouns. In our methods, we get the shortest dependency path as a constitutive role extraction pattern, and calculate the credibility of each pattern. Then according to the co-occurrence information of nouns, we will mine the (Error! Reference source not found...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.