Chinese Computational Linguistics and Natural Language by Kaixu Zhang, Jinsong Su, Changle Zhou (auth.), Maosong Sun,

By Kaixu Zhang, Jinsong Su, Changle Zhou (auth.), Maosong Sun, Min Zhang, Dekang Lin, Haifeng Wang (eds.)

This publication constitutes the refereed complaints of the twelfth China nationwide convention on Computational Linguistics, CCL 2013, and of the 1st overseas Symposium on ordinary Language Processing in response to certainly Annotated sizeable facts, NLP-NABD 2013, held in Suzhou, China, in October 2013. The 32 papers offered have been conscientiously reviewed and chosen from 252 submissions. The papers are geared up in topical sections on observe segmentation; open-domain query answering; discourse, coreference and pragmatics; statistical and desktop studying equipment in NLP; semantics; textual content mining, open-domain info extraction and computer examining of the net; sentiment research, opinion mining and textual content type; lexical semantics and ontologies; language assets and annotation; computer translation; speech popularity and synthesis; tagging and chunking; and large-scale wisdom acquisition and reasoning.

Show description

Read Online or Download Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data: 12th China National Conference, CCL 2013 and First International Symposium, NLP-NABD 2013, Suzhou, China, October 10-12, 2013. Proceedings PDF

Best chinese books

Thirty Years in a Red House: A Memoir of Childhood and Youth in Communist China

The wrenching saga of a patriotic Communist family members in China. this is often the private account of Zhu Xiao Di, born in Nanjing in 1958, the son of idealistic, expert mom and dad. on the middle of this narrative are the rigors of a family members stuck within the crosscurrents of history--from the early sights of the Communist revolution to the nationwide catastrophe that and the next odyssey of restoration.

The Eater's Guide to Chinese Characters

Lauded by way of Calvin Trillin as a guy who "does no longer need to make to with translations like 'Shredded 3 types' in chinese language restaurants," within the Eater's advisor to chinese language Characters, James D. McCawley bargains everybody a consultant to interpreting the mysteries of chinese language menus and the chance to take pleasure in new consuming studies.

Productive Performance in Chinese Enterprises: An Empirical Study

Because the rural township, village and personal businesses have gotten extra major within the chinese language economic climate, this article makes a speciality of the comparability of the agricultural (non-state) and nation corporations when it comes to functionality. The research relies at the empirical effects from estimating a number of creation services utilized to cross-section and panel facts.

Encoding and Decoding of Emotional Speech: A Cross-Cultural and Multimodal Study between Chinese and Japanese

​This publication addresses the topic of emotional speech, in particular its encoding and deciphering method in the course of interactive verbal exchange, in response to a more robust model of Brunswik’s Lens version. the method is proven to be encouraged via the speaker’s and the listener’s linguistic and cultural backgrounds, in addition to through the transmission channels used.

Extra info for Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data: 12th China National Conference, CCL 2013 and First International Symposium, NLP-NABD 2013, Suzhou, China, October 10-12, 2013. Proceedings

Sample text

2. Boundary Segmentation and Manual Segmentation Fig. 3. 3 indicates the good performance in named entity recognition, especially in long sentences, using punctuations and implicit BICs. , are characters (single character word) with strong boundary strength. They are quite worthy to be used in boundary computing. As for future work, it would be natural for researchers to enhance the implicit Natural Annotation utilization as well as modeling both cohesion and autonomy of a string. 3 Segmentation Examples (a) ⊏⌭≁ ᵾ呿 ҄⸣ ᵡ䮅ส ᵾ⪎⧟ ࡈॾ␵ ሹ‫ڕ‬㹼 ᵾዊ␵ оз਽ 俆䜭 ਴⭼ 㗔Շ ઼ࣣࣘ ⁑㤳 ԓ㺘 а䎧 䗎ᰗ䗾ᯠ (b) ᵜᣕ䇟 ᒯь咔ኡᐲ ⴤ䗮 俉⑟ ҍ嗉Ⲵ 䊚ॾᇒ䖖у㓯 ᰕࡽᔰ 䙊 (c) ᚝෾⪦᯿㠚⋫৯ ᨀ‫׋‬Ҷ ᡀ࣏ Ⲵ㓿傼 (d) ࡊࡊ൘ 㤡ഭ 俆䜭 Ֆᮖ Ѫҹਆ 㤡ഭ ᭯ᓌ 䟺᭮ Ც࡙ ࡽᙫ㔏 Ⳟ䈪࠷⢩ 䘋㹼Ҷ йཙ ⑨䈤 ⍫ࣘⲴ Ც࡙ ཆ䮯 ഐ㣿ቄ㩘 ሶҾ nᰕ 䎦䎤 㾯⨝⢉ 俆䜭 傜ᗧ䟼 Chinese Natural Chunk Research Based on Natural Annotations in Massive Scale Corpora 6 23 Summary and Future Work A natural sentence is made up of words, among which exist cohesion and transition relations.

1 Semi-supervised K-means Cluster To avoid the shortcomings of Brown clustering algorithm, we propose a semisupervised K-means clustering method to map each character to its corresponding concepts based on its context. Chinese Word Segmentation with Character Abstraction 39 Table 1. Top Clusters derived with Brown algorithm. ) 㕆ᓧᕅⸯ䱯ᡚ≹৸ௌᗞࡈ‫ޛ‬൓ᗵ㓿ഭेԜˎ䍴‫ޜ‬ 䗁‫ڕ‬੨➔Ժ⭊↖ত⅒ঊᶘг䈎享⍾ѝӜᡁᴸᣅਨ Different with unsupervised clustering methods, we first use HowNet Knowledge Database[7] as a initial guide for semantic concepts, then we use k-means algorithm to cluster on large-scale unlabeled texts.

References 1. : A hybrid markov/semi-markov conditional random field for sequence segmentation. In: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pp. 465–472. Association for Computational Linguistics (2006) 2. : Class-based n-gram models of natural language. Computational Linguistics 18(4), 467–479 (1992) 3. : Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (2002) 4.

Download PDF sample

Rated 4.36 of 5 – based on 34 votes