Báo cáo khoa học: "Building a Large Knowledge Base for a Natural Language System" doc

... arbitrarily detailed world knowledge and that a sophisticated natural language sys- tem must have a large knowledge base. But heretofore, the knowledge bases in natural language systems have either ... Building a Large Knowledge Base for a Natural Language System Jerry R. Hobbs Artificial Intelligence Center SRI International and Center for the S...

Ngày tải lên: 17/03/2014, 19:21

... manually format the re- source) so as to get reliable and usable results; semi-automatic rather than fully automatic ap- proach is adopted to ensure accuracy; corpus analysis based information ... paraphrases are defined at semantic level. For example, '~rhe base plan called for one fiber ac- tivation at CSA 2100" and "There was one fiber activation at CSA 2100&qu...

Ngày tải lên: 31/03/2014, 04:20

... features='participant;human' state='active'/> <segment id='2' start='207' end='214' features='participant;organisation;company' state='active'/> ... developed to facilitate the human annotation of text. These have been necessary where software for automatic annotation has not been available, e.g., for...

Ngày tải lên: 20/02/2014, 09:20

... Pitman-Yor Language Modeling Daichi Mochihashi Takeshi Yamada Naonori Ueda NTT Communication Science Laboratories Hikaridai 2-4, Keihanna Science City, Kyoto, Japan {daichi,yamada,ueda}@cslab.kecl.ntt.co.jp Abstract In ... tran- scripts and standard datasets for Chinese and Japanese word segmentation. Our model is also considered as a way to con- struct an accurate word n-gram language...

Ngày tải lên: 17/03/2014, 01:20

... cla im that any form of negation is likely to remove relevant as well as irrelevant results, the damage done was only around 3% for post-retrieval filtering and 25% for constant and vector negation. • ... widespread use in information retrieval (Salton and McGill, 1983; Baeza -Yates and ∗ This research was supported in part by the Research Collaboration between the NTT Communication Scienc...

Ngày tải lên: 17/03/2014, 06:20

... pending plans for utterances. We argue that in domains where salience information is already available, such thorough deliberations are often unnecessary, and that a straight-forward enumeration ... speaker's knowledge of their language consist 9 in large part of a catalog of wnat might be saia and the effects it is likely to have on the audience; and that, according...

Ngày tải lên: 17/03/2014, 19:21

... USA {kapil,kathy}@cs.columbia.edu Abstract The task of aligning corresponding phrases across two related sentences is an important component of approaches for natural language problems such as textual inference, paraphrase detection ... pre- sented a phrase-based monolingual aligner for NLI (MANLI) that has been shown to significantly out- perform a token-based NLI aligner (Chamber...

Ngày tải lên: 30/03/2014, 21:20

... Target Generation for Hierarchical Phrase-based Translation Taro Watanabe Hajime Tsukada Hideki Isozaki 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto, JAPAN 619-0237 {taro,tsukada,isozaki}@cslab.kecl.ntt.co.jp Abstract We ... against a phrase-based translation system. 1 Introduction In a classical statistical machine translation, a for- eign language sentence f J 1 = f 1 , f 2 , f...

Ngày tải lên: 31/03/2014, 01:20

... of languages. A second form of evaluation is to use some data that has been manually or semi-automatically an- notated with part of speech (POS) tags, and to use some information theoretic measure ... parts-of-speech, that is to say lexical categories corresponding to traditional notions of, for example, nouns and verbs. As is often the case in machine learning of natural language, the...

Ngày tải lên: 31/03/2014, 20:20

... into our natural language understanding system. Client- server architecture was used to make a large volume of lexical information and a large knowledge base available to the system at development ... semantic analysis, and pragmatic analysis. Each stage has been designed to use linguistic data such as the lexicon and grammar, which are maintained separately from the en...

Ngày tải lên: 20/02/2014, 18:20