Word alignment methods can gain valuable guidance by ensuring that their alignments maintain cohesion with respect to the phrases specified by a monolingual dependency tree. However, this hard constraint can also rule out correct alignments, and its utility decreases as alignment models become more complex. We use a publicly available structured output SVM to create a max-margin syntactic aligner with a soft cohesion constraint. The resulting aligner is the first, to our knowledge, to use a discriminative learning method to train an ITG bitext parser.
{"title":"Soft Syntactic Constraints for Word Alignment through Discriminative Training","authors":"Colin Cherry, Dekang Lin","doi":"10.3115/1273073.1273087","DOIUrl":"https://doi.org/10.3115/1273073.1273087","url":null,"abstract":"Word alignment methods can gain valuable guidance by ensuring that their alignments maintain cohesion with respect to the phrases specified by a monolingual dependency tree. However, this hard constraint can also rule out correct alignments, and its utility decreases as alignment models become more complex. We use a publicly available structured output SVM to create a max-margin syntactic aligner with a soft cohesion constraint. The resulting aligner is the first, to our knowledge, to use a discriminative learning method to train an ITG bitext parser.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123618558","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}
Siwei Shen, Dragomir R. Radev, Agam Patel, Günes Erkan
Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase identification. Prior work falls into two categories, depending on the type of input used: (a) parallel corpora (e.g., multiple translations of the same text) or (b) comparable texts (non-parallel but on the same topic). So far, only techniques based on parallel texts have successfully used syntactic information to guide alignments. In this paper, we describe an algorithm for incorporating syntactic features in the alignment process for non-parallel texts with the goal of generating novel paraphrases of existing texts. Our method uses dynamic programming with alignment decision based on the local syntactic similarity between two sentences. Our results show that syntactic alignment outrivals syntax-free methods by 20% in both grammaticality and fidelity when computed over the novel sentences generated by alignment-induced finite state automata.
{"title":"Adding Syntax to Dynamic Programming for Aligning Comparable Texts for the Generation of Paraphrases","authors":"Siwei Shen, Dragomir R. Radev, Agam Patel, Günes Erkan","doi":"10.3115/1273073.1273169","DOIUrl":"https://doi.org/10.3115/1273073.1273169","url":null,"abstract":"Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase identification. Prior work falls into two categories, depending on the type of input used: (a) parallel corpora (e.g., multiple translations of the same text) or (b) comparable texts (non-parallel but on the same topic). So far, only techniques based on parallel texts have successfully used syntactic information to guide alignments. In this paper, we describe an algorithm for incorporating syntactic features in the alignment process for non-parallel texts with the goal of generating novel paraphrases of existing texts. Our method uses dynamic programming with alignment decision based on the local syntactic similarity between two sentences. Our results show that syntactic alignment outrivals syntax-free methods by 20% in both grammaticality and fidelity when computed over the novel sentences generated by alignment-induced finite state automata.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123178856","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 show that we can automatically classify semantically related phrases into 10 classes. Classification robustness is improved by training with multiple sources of evidence, including within-document cooccurrence, HTML markup, syntactic relationships in sentences, substitutability in query logs, and string similarity. Our work provides a benchmark for automatic n-way classification into WordNet's semantic classes, both on a TREC news corpus and on a corpus of substitutable search query phrases.
{"title":"N Semantic Classes are Harder than Two","authors":"Ben Carterette, R. Jones, W. Greiner, C. Barr","doi":"10.3115/1273073.1273080","DOIUrl":"https://doi.org/10.3115/1273073.1273080","url":null,"abstract":"We show that we can automatically classify semantically related phrases into 10 classes. Classification robustness is improved by training with multiple sources of evidence, including within-document cooccurrence, HTML markup, syntactic relationships in sentences, substitutability in query logs, and string similarity. Our work provides a benchmark for automatic n-way classification into WordNet's semantic classes, both on a TREC news corpus and on a corpus of substitutable search query phrases.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"29 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131805042","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}
Pub Date : 2006-07-17DOI: 10.21437/Interspeech.2006-251
Ryoji Hamabe, Kiyotaka Uchimoto, Tatsuya Kawahara, H. Isahara
Japanese dependency structure is usually represented by relationships between phrasal units called bunsetsus. One of the biggest problems with dependency structure analysis in spontaneous speech is that clause boundaries are ambiguous. This paper describes a method for detecting the boundaries of quotations and inserted clauses and that for improving the dependency accuracy by applying the detected boundaries to dependency structure analysis. The quotations and inserted clauses are determined by using an SVM-based text chunking method that considers information on morphemes, pauses, fillers, etc. The information on automatically analyzed dependency structure is also used to detect the beginning of the clauses. Our evaluation experiment using Corpus of Spontaneous Japanese (CSJ) showed that the automatically estimated boundaries of quotations and inserted clauses helped to improve the accuracy of dependency structure analysis.
{"title":"Detection of Quotations and Inserted Clauses and Its Application to Dependency Structure Analysis in Spontaneous Japanese","authors":"Ryoji Hamabe, Kiyotaka Uchimoto, Tatsuya Kawahara, H. Isahara","doi":"10.21437/Interspeech.2006-251","DOIUrl":"https://doi.org/10.21437/Interspeech.2006-251","url":null,"abstract":"Japanese dependency structure is usually represented by relationships between phrasal units called bunsetsus. One of the biggest problems with dependency structure analysis in spontaneous speech is that clause boundaries are ambiguous. This paper describes a method for detecting the boundaries of quotations and inserted clauses and that for improving the dependency accuracy by applying the detected boundaries to dependency structure analysis. The quotations and inserted clauses are determined by using an SVM-based text chunking method that considers information on morphemes, pauses, fillers, etc. The information on automatically analyzed dependency structure is also used to detect the beginning of the clauses. Our evaluation experiment using Corpus of Spontaneous Japanese (CSJ) showed that the automatically estimated boundaries of quotations and inserted clauses helped to improve the accuracy of dependency structure analysis.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"394 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122886898","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}
C. Creswell, Matthew J. Beal, John Chen, T. Cornell, L. Nilsson, R. Srihari
Most approaches to event extraction focus on mentions anchored in verbs. However, many mentions of events surface as noun phrases. Detecting them can increase the recall of event extraction and provide the foundation for detecting relations between events. This paper describes a weakly-supervised method for detecting nominal event mentions that combines techniques from word sense disambiguation (WSD) and lexical acquisition to create a classifier that labels noun phrases as denoting events or non-events. The classifier uses boot-strapped probabilistic generative models of the contexts of events and non-events. The contexts are the lexically-anchored semantic dependency relations that the NPs appear in. Our method dramatically improves with bootstrapping, and comfortably outperforms lexical lookup methods which are based on very much larger hand-crafted resources.
{"title":"Automatically Extracting Nominal Mentions of Events with a Bootstrapped Probabilistic Classifier","authors":"C. Creswell, Matthew J. Beal, John Chen, T. Cornell, L. Nilsson, R. Srihari","doi":"10.3115/1273073.1273095","DOIUrl":"https://doi.org/10.3115/1273073.1273095","url":null,"abstract":"Most approaches to event extraction focus on mentions anchored in verbs. However, many mentions of events surface as noun phrases. Detecting them can increase the recall of event extraction and provide the foundation for detecting relations between events. This paper describes a weakly-supervised method for detecting nominal event mentions that combines techniques from word sense disambiguation (WSD) and lexical acquisition to create a classifier that labels noun phrases as denoting events or non-events. The classifier uses boot-strapped probabilistic generative models of the contexts of events and non-events. The contexts are the lexically-anchored semantic dependency relations that the NPs appear in. Our method dramatically improves with bootstrapping, and comfortably outperforms lexical lookup methods which are based on very much larger hand-crafted resources.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125369270","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 investigate the use of machine learning in combination with feature engineering techniques to explore human multimodal clarification strategies and the use of those strategies for dialogue systems. We learn from data collected in a Wizard-of-Oz study where different wizards could decide whether to ask a clarification request in a multimodal manner or else use speech alone. We show that there is a uniform strategy across wizards which is based on multiple features in the context. These are generic runtime features which can be implemented in dialogue systems. Our prediction models achieve a weighted f-score of 85.3% (which is a 25.5% improvement over a one-rule baseline). To assess the effects of models, feature discretisation, and selection, we also conduct a regression analysis. We then interpret and discuss the use of the learnt strategy for dialogue systems. Throughout the investigation we discuss the issues arising from using small initial Wizard-of-Oz data sets, and we show that feature engineering is an essential step when learning from such limited data.
{"title":"Using Machine Learning to Explore Human Multimodal Clarification Strategies","authors":"Verena Rieser, Oliver Lemon","doi":"10.3115/1273073.1273158","DOIUrl":"https://doi.org/10.3115/1273073.1273158","url":null,"abstract":"We investigate the use of machine learning in combination with feature engineering techniques to explore human multimodal clarification strategies and the use of those strategies for dialogue systems. We learn from data collected in a Wizard-of-Oz study where different wizards could decide whether to ask a clarification request in a multimodal manner or else use speech alone. We show that there is a uniform strategy across wizards which is based on multiple features in the context. These are generic runtime features which can be implemented in dialogue systems. Our prediction models achieve a weighted f-score of 85.3% (which is a 25.5% improvement over a one-rule baseline). To assess the effects of models, feature discretisation, and selection, we also conduct a regression analysis. We then interpret and discuss the use of the learnt strategy for dialogue systems. Throughout the investigation we discuss the issues arising from using small initial Wizard-of-Oz data sets, and we show that feature engineering is an essential step when learning from such limited data.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114761334","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}
Short Messaging Service (SMS) texts behave quite differently from normal written texts and have some very special phenomena. To translate SMS texts, traditional approaches model such irregularities directly in Machine Translation (MT). However, such approaches suffer from customization problem as tremendous effort is required to adapt the language model of the existing translation system to handle SMS text style. We offer an alternative approach to resolve such irregularities by normalizing SMS texts before MT. In this paper, we view the task of SMS normalization as a translation problem from the SMS language to the English language and we propose to adapt a phrase-based statistical MT model for the task. Evaluation by 5-fold cross validation on a parallel SMS normalized corpus of 5000 sentences shows that our method can achieve 0.80702 in BLEU score against the baseline BLEU score 0.6958. Another experiment of translating SMS texts from English to Chinese on a separate SMS text corpus shows that, using SMS normalization as MT preprocessing can largely boost SMS translation performance from 0.1926 to 0.3770 in BLEU score.
{"title":"A Phrase-Based Statistical Model for SMS Text Normalization","authors":"AiTi Aw, Min Zhang, Juan Xiao, Jian Su","doi":"10.3115/1273073.1273078","DOIUrl":"https://doi.org/10.3115/1273073.1273078","url":null,"abstract":"Short Messaging Service (SMS) texts behave quite differently from normal written texts and have some very special phenomena. To translate SMS texts, traditional approaches model such irregularities directly in Machine Translation (MT). However, such approaches suffer from customization problem as tremendous effort is required to adapt the language model of the existing translation system to handle SMS text style. We offer an alternative approach to resolve such irregularities by normalizing SMS texts before MT. In this paper, we view the task of SMS normalization as a translation problem from the SMS language to the English language and we propose to adapt a phrase-based statistical MT model for the task. Evaluation by 5-fold cross validation on a parallel SMS normalized corpus of 5000 sentences shows that our method can achieve 0.80702 in BLEU score against the baseline BLEU score 0.6958. Another experiment of translating SMS texts from English to Chinese on a separate SMS text corpus shows that, using SMS normalization as MT preprocessing can largely boost SMS translation performance from 0.1926 to 0.3770 in BLEU score.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126142151","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}
In this paper, we describe an empirical study of Chinese chunking on a corpus, which is extracted from UPENN Chinese Treebank-4 (CTB4). First, we compare the performance of the state-of-the-art machine learning models. Then we propose two approaches in order to improve the performance of Chinese chunking. 1) We propose an approach to resolve the special problems of Chinese chunking. This approach extends the chunk tags for every problem by a tag-extension function. 2) We propose two novel voting methods based on the characteristics of chunking task. Compared with traditional voting methods, the proposed voting methods consider long distance information. The experimental results show that the SVMs model outperforms the other models and that our proposed approaches can improve performance significantly.
本文对UPENN Chinese Treebank-4 (CTB4)中的语料库进行了汉语分块的实证研究。首先，我们比较了最先进的机器学习模型的性能。然后，我们提出了两种方法来提高中文分块的性能。1)提出了一种解决汉语分块问题的方法。这种方法通过标记扩展函数为每个问题扩展块标记。2)基于分块任务的特点，提出了两种新的投票方法。与传统的投票方法相比，本文提出的投票方法考虑了远距离信息。实验结果表明，支持向量机模型的性能优于其他模型，我们提出的方法可以显著提高性能。
{"title":"An Empirical Study of Chinese Chunking","authors":"Wenliang Chen, Yujie Zhang, H. Isahara","doi":"10.3115/1273073.1273086","DOIUrl":"https://doi.org/10.3115/1273073.1273086","url":null,"abstract":"In this paper, we describe an empirical study of Chinese chunking on a corpus, which is extracted from UPENN Chinese Treebank-4 (CTB4). First, we compare the performance of the state-of-the-art machine learning models. Then we propose two approaches in order to improve the performance of Chinese chunking. 1) We propose an approach to resolve the special problems of Chinese chunking. This approach extends the chunk tags for every problem by a tag-extension function. 2) We propose two novel voting methods based on the characteristics of chunking task. Compared with traditional voting methods, the proposed voting methods consider long distance information. The experimental results show that the SVMs model outperforms the other models and that our proposed approaches can improve performance significantly.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114303874","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}
In this paper we present word sense disambiguation (WSD) experiments on ten highly polysemous verbs in Chinese, where significant performance improvements are achieved using rich linguistic features. Our system performs significantly better, and in some cases substantially better, than the baseline on all ten verbs. Our results also demonstrate that features extracted from the output of an automatic Chinese semantic role labeling system in general benefited the WSD system, even though the amount of improvement was not consistent across the verbs. For a few verbs, semantic role information actually hurt WSD performance. The inconsistency of feature performance is a general characteristic of the WSD task, as has been observed by others. We argue that this result can be explained by the fact that word senses are partitioned along different dimensions for different verbs and the features therefore need to be tailored to particular verbs in order to achieve adequate accuracy on verb sense disambiguation.
{"title":"Aligning Features with Sense Distinction Dimensions","authors":"Nianwen Xue, Jinying Chen, Martha Palmer","doi":"10.3115/1273073.1273191","DOIUrl":"https://doi.org/10.3115/1273073.1273191","url":null,"abstract":"In this paper we present word sense disambiguation (WSD) experiments on ten highly polysemous verbs in Chinese, where significant performance improvements are achieved using rich linguistic features. Our system performs significantly better, and in some cases substantially better, than the baseline on all ten verbs. Our results also demonstrate that features extracted from the output of an automatic Chinese semantic role labeling system in general benefited the WSD system, even though the amount of improvement was not consistent across the verbs. For a few verbs, semantic role information actually hurt WSD performance. The inconsistency of feature performance is a general characteristic of the WSD task, as has been observed by others. We argue that this result can be explained by the fact that word senses are partitioned along different dimensions for different verbs and the features therefore need to be tailored to particular verbs in order to achieve adequate accuracy on verb sense disambiguation.","PeriodicalId":287679,"journal":{"name":"Proceedings of the COLING/ACL on Main conference poster sessions -","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132066435","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}
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：