This paper describes SimpleNLG, a realisation engine for English which aims to provide simple and robust interfaces to generate syntactic structures and linearise them. The library is also flexible in allowing the use of mixed (canned and non-canned) representations.
{"title":"SimpleNLG: A Realisation Engine for Practical Applications","authors":"Albert Gatt, Ehud Reiter","doi":"10.3115/1610195.1610208","DOIUrl":"https://doi.org/10.3115/1610195.1610208","url":null,"abstract":"This paper describes SimpleNLG, a realisation engine for English which aims to provide simple and robust interfaces to generate syntactic structures and linearise them. The library is also flexible in allowing the use of mixed (canned and non-canned) representations.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124408322","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}
Present-day sentence generators are often incapable of producing a wide variety of well-formed elliptical versions of coordinated clauses, in particular, of combined elliptical phenomena (Gapping, Forward and Backward Conjunction Reduction, etc.). The applicability of the various types of clausal coordinate ellipsis (CCE) presupposes detailed comparisons of the syntactic properties of the coordinated clauses. These nonlocal comparisons argue against approaches based on local rules that treat CCE structures as special cases of clausal coordination. We advocate an alternative approach where CCE rules take the form of postediting rules applicable to nonelliptical structures. The advantage is not only a higher level of modularity but also applicability to languages belonging to different language families. We describe a language-neutral module (called Elleipo; implemented in JAVA) that generates as output all major CCE versions of coordinated clauses. Elleipo takes as input linearly ordered nonelliptical coordinated clauses annotated with lexical identity and coreferentiality relationships between words and word groups in the conjuncts. We demonstrate the feasibility of a single set of postediting rules that attains multilingual coverage.
{"title":"Generating Clausal Coordinate Ellipsis Multilingually: A Uniform Approach Based on Postediting","authors":"Karin Harbusch, G. Kempen","doi":"10.3115/1610195.1610219","DOIUrl":"https://doi.org/10.3115/1610195.1610219","url":null,"abstract":"Present-day sentence generators are often incapable of producing a wide variety of well-formed elliptical versions of coordinated clauses, in particular, of combined elliptical phenomena (Gapping, Forward and Backward Conjunction Reduction, etc.). The applicability of the various types of clausal coordinate ellipsis (CCE) presupposes detailed comparisons of the syntactic properties of the coordinated clauses. These nonlocal comparisons argue against approaches based on local rules that treat CCE structures as special cases of clausal coordination. We advocate an alternative approach where CCE rules take the form of postediting rules applicable to nonelliptical structures. The advantage is not only a higher level of modularity but also applicability to languages belonging to different language families. We describe a language-neutral module (called Elleipo; implemented in JAVA) that generates as output all major CCE versions of coordinated clauses. Elleipo takes as input linearly ordered nonelliptical coordinated clauses annotated with lexical identity and coreferentiality relationships between words and word groups in the conjuncts. We demonstrate the feasibility of a single set of postediting rules that attains multilingual coverage.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126540295","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. Wubben, Antal van den Bosch, E. Krahmer, E. Marsi
For developing a data-driven text rewriting algorithm for paraphrasing, it is essential to have a monolingual corpus of aligned paraphrased sentences. News article headlines are a rich source of paraphrases; they tend to describe the same event in various different ways, and can easily be obtained from the web. We compare two methods of aligning headlines to construct such an aligned corpus of paraphrases, one based on clustering, and the other on pairwise similarity-based matching. We show that the latter performs best on the task of aligning paraphrastic headlines.
{"title":"Clustering and Matching Headlines for Automatic Paraphrase Acquisition","authors":"S. Wubben, Antal van den Bosch, E. Krahmer, E. Marsi","doi":"10.3115/1610195.1610216","DOIUrl":"https://doi.org/10.3115/1610195.1610216","url":null,"abstract":"For developing a data-driven text rewriting algorithm for paraphrasing, it is essential to have a monolingual corpus of aligned paraphrased sentences. News article headlines are a rich source of paraphrases; they tend to describe the same event in various different ways, and can easily be obtained from the web. We compare two methods of aligning headlines to construct such an aligned corpus of paraphrases, one based on clustering, and the other on pairwise similarity-based matching. We show that the latter performs best on the task of aligning paraphrastic headlines.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126778756","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 describe a new realiser developed for the TUNA 2009 Challenge, and present its evaluation scores on the development set, showing a clear increase in performance compared to last year's simple realiser.
{"title":"Realizing the Costs: Template-Based Surface Realisation in the GRAPH Approach to Referring Expression Generation","authors":"I. Brugman, M. Theune, E. Krahmer, J. Viethen","doi":"10.3115/1610195.1610225","DOIUrl":"https://doi.org/10.3115/1610195.1610225","url":null,"abstract":"We describe a new realiser developed for the TUNA 2009 Challenge, and present its evaluation scores on the development set, showing a clear increase in performance compared to last year's simple realiser.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127934327","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}
Philipp Spanger, Masaaki Yasuhara, R. Iida, T. Tokunaga
In order to pursue research on generating referring expressions in a situated collaboration task, we set up a data-collection experiment based on the Tangram puzzle. For a pair of participants we recorded every utterance in synchronisation with the current state of the puzzle as well as all operations by the participants. Referring expressions were annotated with their referents in order to build a referring expression corpus in Japanese. We provide preliminary results on the analysis of the corpus from various standpoints, focussing on action-mentioning expressions.
{"title":"A Japanese Corpus of Referring Expressions Used in a Situated Collaboration Task","authors":"Philipp Spanger, Masaaki Yasuhara, R. Iida, T. Tokunaga","doi":"10.3115/1610195.1610213","DOIUrl":"https://doi.org/10.3115/1610195.1610213","url":null,"abstract":"In order to pursue research on generating referring expressions in a situated collaboration task, we set up a data-collection experiment based on the Tangram puzzle. For a pair of participants we recorded every utterance in synchronisation with the current state of the puzzle as well as all operations by the participants. Referring expressions were annotated with their referents in order to build a referring expression corpus in Japanese. We provide preliminary results on the analysis of the corpus from various standpoints, focussing on action-mentioning expressions.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121313664","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}
The background for this paper is the aim to build robotic assistants that can "naturally" interact with humans. One prerequisite for this is that the robot can correctly identify objects or places a user refers to, and produce comprehensible references itself. As robots typically act in environments that are larger than what is immediately perceivable, the problem arises how to identify the appropriate context, against which to resolve or produce a referring expression (RE). Existing algorithms for generating REs generally bypass this problem by assuming a given context. In this paper, we explicitly address this problem, proposing a method for context determination in large-scale space. We show how it can be applied both for resolving and producing REs.
{"title":"A Situated Context Model for Resolution and Generation of Referring Expressions","authors":"H. Zender, G. Kruijff, Ivana Kruijff-Korbayová","doi":"10.3115/1610195.1610217","DOIUrl":"https://doi.org/10.3115/1610195.1610217","url":null,"abstract":"The background for this paper is the aim to build robotic assistants that can \"naturally\" interact with humans. One prerequisite for this is that the robot can correctly identify objects or places a user refers to, and produce comprehensible references itself. As robots typically act in environments that are larger than what is immediately perceivable, the problem arises how to identify the appropriate context, against which to resolve or produce a referring expression (RE). Existing algorithms for generating REs generally bypass this problem by assuming a given context. In this paper, we explicitly address this problem, proposing a method for context determination in large-scale space. We show how it can be applied both for resolving and producing REs.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130560982","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}
Kotaro Funakoshi, Philipp Spanger, Mikio Nakano, T. Tokunaga
This paper presents a probabilistic model both for generation and understanding of referring expressions. This model introduces the concept of parts of objects, modelling the necessity to deal with the characteristics of separate parts of an object in the referring process. This was ignored or implicit in previous literature. Integrating this concept into a probabilistic formulation, the model captures human characteristics of visual perception and some type of pragmatic implicature in referring expressions. Developing this kind of model is critical to deal with more complex domains in the future. As a first step in our research, we validate the model with the TUNA corpus to show that it includes conventional domain modeling as a subset.
{"title":"A Probabilistic Model of Referring Expressions for Complex Objects","authors":"Kotaro Funakoshi, Philipp Spanger, Mikio Nakano, T. Tokunaga","doi":"10.3115/1610195.1610229","DOIUrl":"https://doi.org/10.3115/1610195.1610229","url":null,"abstract":"This paper presents a probabilistic model both for generation and understanding of referring expressions. This model introduces the concept of parts of objects, modelling the necessity to deal with the characteristics of separate parts of an object in the referring process. This was ignored or implicit in previous literature. Integrating this concept into a probabilistic formulation, the model captures human characteristics of visual perception and some type of pragmatic implicature in referring expressions. Developing this kind of model is critical to deal with more complex domains in the future. As a first step in our research, we validate the model with the TUNA corpus to show that it includes conventional domain modeling as a subset.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126306182","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}
Many studies in natural language processing are concerned with how to generate definite descriptions that evoke a discourse entity already introduced in the context. A solution to this problem has been initially proposed by Dale (1989) in terms of distinguishing descriptions and distinguishable entities. In this paper, we give a formal definition of the terms "distinguishable entity" in non trivial cases and we show that its properties lead us to the definition of a distance between entities. Then, we give a polynomial algorithm to compute distinguishing descriptions.
{"title":"Distinguishable Entities: Definitions and Properties","authors":"Monique Rolbert, P. Préa","doi":"10.3115/1610195.1610201","DOIUrl":"https://doi.org/10.3115/1610195.1610201","url":null,"abstract":"Many studies in natural language processing are concerned with how to generate definite descriptions that evoke a discourse entity already introduced in the context. A solution to this problem has been initially proposed by Dale (1989) in terms of distinguishing descriptions and distinguishable entities. In this paper, we give a formal definition of the terms \"distinguishable entity\" in non trivial cases and we show that its properties lead us to the definition of a distance between entities. Then, we give a polynomial algorithm to compute distinguishing descriptions.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114745013","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 Wizard-of-Oz environment for data collection on Referring Expression Generation (REG) in a real situated spoken dialogue task. The collected data will be used to build user simulation models for reinforcement learning of referring expression generation strategies.
{"title":"A Wizard-of-Oz Environment to Study Referring Expression Generation in a Situated Spoken Dialogue Task","authors":"S. Janarthanam, Oliver Lemon","doi":"10.3115/1610195.1610209","DOIUrl":"https://doi.org/10.3115/1610195.1610209","url":null,"abstract":"We present a Wizard-of-Oz environment for data collection on Referring Expression Generation (REG) in a real situated spoken dialogue task. The collected data will be used to build user simulation models for reinforcement learning of referring expression generation strategies.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116003084","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 propose the use of evolutionary algorithms (EAs) (Holland, 1992) to deal with the attribute selection task of referring expression generation. Evolutionary algorithms operate over a population of individuals (possible solutions for a problem) that evolve according to selection rules and genetic operators. The fitness function is a metric that evaluates each of the possible solutions, ensuring that the average adaptation of the population increases each generation. Repeating this process hundreds or thousands of times leads to very good solutions for the problem.
{"title":"Evolutionary and Case-Based Approaches to REG: NIL-UCM-EvoTAP, NIL-UCM-ValuesCBR and NIL-UCM-EvoCBR","authors":"Raquel Hervás, Pablo Gervás","doi":"10.3115/1610195.1610227","DOIUrl":"https://doi.org/10.3115/1610195.1610227","url":null,"abstract":"We propose the use of evolutionary algorithms (EAs) (Holland, 1992) to deal with the attribute selection task of referring expression generation. Evolutionary algorithms operate over a population of individuals (possible solutions for a problem) that evolve according to selection rules and genetic operators. The fitness function is a metric that evaluates each of the possible solutions, ensuring that the average adaptation of the population increases each generation. Repeating this process hundreds or thousands of times leads to very good solutions for the problem.","PeriodicalId":307841,"journal":{"name":"European Workshop on Natural Language Generation","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133431454","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：