Add to ORKGReasoning about how much to generate when space is limited is a challenge for generation systems. This paper presents two algorithms that exploit the discourse structure to decide which content to drop when there are space restrictions, in the context of producing documents from pre-authored text fragments. We analyse the effectiveness of both algorithms and show that the second is near optimal.
International audienceThis paper focuses on the task that consists in automatically structuring free...
In this thesis we develop models for sentence compression. This text rewriting task has recently att...
We introduce a new type of discourse con-straints for the interaction of discourse re-lations with t...
Reasoning about how much to generate when space is limited is a challenge for generation systems. Th...
If a generation system is to produce text in response to a given communicative goal, it must be able...
In this paper, I present a natural language generation system aimed at constructing a turn within an...
Sentence compression holds promise for many applications ranging from summarisation to subtitle gene...
Recently, the view of Natural Language Generation (NLG) as a Constraint Satisfaction Problem (CSP) h...
This paper outlines a number of ways in which defeasible rules can contribute to the content selecti...
In this paper we present a content planning system which takes into consideration a user's bore...
this paper we propose an architecture for generation that combines these two approaches, capitalizin...
Existing paraphrase systems either create successive drafts from an underlying representation, or th...
In this paper we consider the problem of analysing sentence-level discourse structure. We introduce ...
A method for saving storage space for text strings, such as compiler diagnostic messages, is describ...
National audienceThis poster describes a new approach to constrained text generation using NLP and C...
International audienceThis paper focuses on the task that consists in automatically structuring free...
In this thesis we develop models for sentence compression. This text rewriting task has recently att...
We introduce a new type of discourse con-straints for the interaction of discourse re-lations with t...
Reasoning about how much to generate when space is limited is a challenge for generation systems. Th...
If a generation system is to produce text in response to a given communicative goal, it must be able...
In this paper, I present a natural language generation system aimed at constructing a turn within an...
Sentence compression holds promise for many applications ranging from summarisation to subtitle gene...
Recently, the view of Natural Language Generation (NLG) as a Constraint Satisfaction Problem (CSP) h...
This paper outlines a number of ways in which defeasible rules can contribute to the content selecti...
In this paper we present a content planning system which takes into consideration a user's bore...
this paper we propose an architecture for generation that combines these two approaches, capitalizin...
Existing paraphrase systems either create successive drafts from an underlying representation, or th...
In this paper we consider the problem of analysing sentence-level discourse structure. We introduce ...
A method for saving storage space for text strings, such as compiler diagnostic messages, is describ...
National audienceThis poster describes a new approach to constrained text generation using NLP and C...
International audienceThis paper focuses on the task that consists in automatically structuring free...
In this thesis we develop models for sentence compression. This text rewriting task has recently att...
We introduce a new type of discourse con-straints for the interaction of discourse re-lations with t...