Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03最新文献
We investigate single-view algorithms as an alternative to multi-view algorithms for weakly supervised learning for natural language processing tasks without a natural feature split. In particular, we apply co-training, self-training, and EM to one such task and find that both self-training and FS-EM, a new variation of EM that incorporates feature selection, outperform co-training and are comparatively less sensitive to parameter changes.
{"title":"Weakly Supervised Natural Language Learning Without Redundant Views","authors":"Vincent Ng, Claire Cardie","doi":"10.3115/1073445.1073468","DOIUrl":"https://doi.org/10.3115/1073445.1073468","url":null,"abstract":"We investigate single-view algorithms as an alternative to multi-view algorithms for weakly supervised learning for natural language processing tasks without a natural feature split. In particular, we apply co-training, self-training, and EM to one such task and find that both self-training and FS-EM, a new variation of EM that incorporates feature selection, outperform co-training and are comparatively less sensitive to parameter changes.","PeriodicalId":277518,"journal":{"name":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121424680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a derivation of the alignment template model for statistical machine translation and an implementation of the model using weighted finite state transducers. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard FSM operations involving these transducers. One of the benefits of using this framework is that it obviates the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We evaluate the implementation of the model on the French-to-English Hansards task and report alignment and translation performance.
{"title":"A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation","authors":"Shankar Kumar, W. Byrne","doi":"10.3115/1073445.1073464","DOIUrl":"https://doi.org/10.3115/1073445.1073464","url":null,"abstract":"We present a derivation of the alignment template model for statistical machine translation and an implementation of the model using weighted finite state transducers. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard FSM operations involving these transducers. One of the benefits of using this framework is that it obviates the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We evaluate the implementation of the model on the French-to-English Hansards task and report alignment and translation performance.","PeriodicalId":277518,"journal":{"name":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130585204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Riezler, Tracy Holloway King, Dick Crouch, A. Zaenen
We present an application of ambiguity packing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation. Our system incorporates a linguistic parser/generator for LFG, a transfer component for parse reduction operating on packed parse forests, and a maximum-entropy model for stochastic output selection. Furthermore, we propose the use of standard parser evaluation methods for automatically evaluating the summarization quality of sentence condensation systems. An experimental evaluation of summarization quality shows a close correlation between the automatic parse-based evaluation and a manual evaluation of generated strings. Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator.
{"title":"Statistical Sentence Condensation using Ambiguity Packing and Stochastic Disambiguation Methods for Lexical-Functional Grammar","authors":"S. Riezler, Tracy Holloway King, Dick Crouch, A. Zaenen","doi":"10.3115/1073445.1073471","DOIUrl":"https://doi.org/10.3115/1073445.1073471","url":null,"abstract":"We present an application of ambiguity packing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation. Our system incorporates a linguistic parser/generator for LFG, a transfer component for parse reduction operating on packed parse forests, and a maximum-entropy model for stochastic output selection. Furthermore, we propose the use of standard parser evaluation methods for automatically evaluating the summarization quality of sentence condensation systems. An experimental evaluation of summarization quality shows a close correlation between the automatic parse-based evaluation and a manual evaluation of generated strings. Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator.","PeriodicalId":277518,"journal":{"name":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127013024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a neural network method for inducing representations of parse histories and using these history representations to estimate the probabilities needed by a statistical left-corner parser. The resulting statistical parser achieves performance (89.1% F-measure) on the Penn Treebank which is only 0.6% below the best current parser for this task, despite using a smaller vocabulary size and less prior linguistic knowledge. Crucial to this success is the use of structurally determined soft biases in inducing the representation of the parse history, and no use of hard independence assumptions.
{"title":"Inducing History Representations for Broad Coverage Statistical Parsing","authors":"James Henderson","doi":"10.3115/1073445.1073459","DOIUrl":"https://doi.org/10.3115/1073445.1073459","url":null,"abstract":"We present a neural network method for inducing representations of parse histories and using these history representations to estimate the probabilities needed by a statistical left-corner parser. The resulting statistical parser achieves performance (89.1% F-measure) on the Penn Treebank which is only 0.6% below the best current parser for this task, despite using a smaller vocabulary size and less prior linguistic knowledge. Crucial to this success is the use of structurally determined soft biases in inducing the representation of the parse history, and no use of hard independence assumptions.","PeriodicalId":277518,"journal":{"name":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125463010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper investigates the problem of determining grammatical gender for the nouns of a language starting with minimal resources: a very small list of seed nouns for which gender is known or via translingual projection of natural gender. We show that through a bootstrapping process that uses contextual clues from an unannotated corpus and morphological clues modeled with suffix tries, accurate gender predictions can be induced for five diverse test languages.
{"title":"Minimally Supervised Induction of Grammatical Gender","authors":"Silviu Cucerzan, David Yarowsky","doi":"10.3115/1073445.1073451","DOIUrl":"https://doi.org/10.3115/1073445.1073451","url":null,"abstract":"This paper investigates the problem of determining grammatical gender for the nouns of a language starting with minimal resources: a very small list of seed nouns for which gender is known or via translingual projection of natural gender. We show that through a bootstrapping process that uses contextual clues from an unannotated corpus and morphological clues modeled with suffix tries, accurate gender predictions can be induced for five diverse test languages.","PeriodicalId":277518,"journal":{"name":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122100975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：