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.
Considering of the features' distribution but not just the counts of features' appearances in sequence makes exponential language models more powerful to capture the global language phenomena. This paper constructs an exponential language model with binary variables' distributions of features, and uses minimum sample risk training method to train model by utilizing more features and adjusting their...
In this paper, we present a new method to extract product entity from Chinese customer reviews. The approach requires no segmentation, no domain dictionary and little prior domain knowledge, which is more suitable for domain with resource-limited. Quite different from the previous work, the proposed method first get the entity candidates use a general version bootstrapping algorithm and then distribute...
This paper presents a novel application of incorporating Alternating Structure Optimization (ASO) to conduct the task of text chunking of Semantic Role Labeling (SRL) in Chinese texts. ASO is a competent linear algorithm based on the theory of multi-task learning. In this paper, by constructing several SRL tasks to constitute a multi-task, we are able to encode the inference obtained by ASO algorithm...
This paper presents an exponential language model (ELM) for modeling and managing knowledge elements. The model has been developed based on minimum sample risk (MSR) algorithm, which is a discriminative training method. ELM uses features to capture global, domain, or sentential language phenomena that is composed of name entities, part of speech strings, personal usage words, positions of words, sentence...
This paper proposes an novel approach to annotate function tags for unparsed text. What distinguishes our work from other attempts in such task is that we assign function tags directly basing on lexical information other than on parsed trees. In order to demonstrate the effectiveness and versatility of our method, we investigate two statistical models for automatic annotation, one is log-linear maximum...
Chinese Pinyin-to-character conversion is a key technology in Chinese Pinyin input system. In sentence based Pinyin-to-character conversion, segmentation of Pinyin string has important influence on performance of Pinyin-to-character conversion. There are lots of ambiguities in segmentation of Pinyin string. This paper classifies them into overlap and combinational ambiguities, and proposes disambiguation...
Recent years have seen great process in studying English question classification. In our research, we learn Chinese question classification by exploiting the result of lexical, syntactic and semantic parsing on question sentences. Support vector machines are adopted to train a classifier on 6 coarse categories using single and combination of different parsing results as features. We find that even...
Chinese named entity recognition (NER) is studied in two directions: inner structure and outer surroundings. Inner structural analyses induce constitutions of person, location and organization name from the point of linguistics. However inner structural rules for named entities only provide necessary conditions for a sequence of Chinese characters being an entity name but not sufficient. Whether a...
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.