Finetuning an NLG system through experiments with human subjects

the case of vague descriptions.

Kees van Deemter

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Abstract. This discussion paper describes a sequence of experiments
with human subjects aimed at nding out how an nlg system should
choose between the dierent forms of a gradable adjective. This case
study highlights some general questions that one faces when trying to
base nlg systems on empirical evidence: one question is what task to set
a subject so as to obtain the most useful information about that subject,
another question has to do with dierences between subjects.
Original languageEnglish
Title of host publicationProc. of 3rd International Conference on Natural Language Generation
EditorsAnja Belz, Roger Evans, Paul Piwek
Place of PublicationBerlin and Heidelberg
PublisherSpringer Lecture Notes
Number of pages10
Publication statusPublished - 2004

Fingerprint

experiment
evidence

Keywords

  • Vague adjectives.
  • Experiments with human subjects.

Cite this

van Deemter, K. (2004). Finetuning an NLG system through experiments with human subjects: the case of vague descriptions. In A. Belz, R. Evans, & P. Piwek (Eds.), Proc. of 3rd International Conference on Natural Language Generation Berlin and Heidelberg: Springer Lecture Notes.

Finetuning an NLG system through experiments with human subjects : the case of vague descriptions. / van Deemter, Kees.

Proc. of 3rd International Conference on Natural Language Generation. ed. / Anja Belz; Roger Evans; Paul Piwek. Berlin and Heidelberg : Springer Lecture Notes, 2004.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

van Deemter, K 2004, Finetuning an NLG system through experiments with human subjects: the case of vague descriptions. in A Belz, R Evans & P Piwek (eds), Proc. of 3rd International Conference on Natural Language Generation. Springer Lecture Notes, Berlin and Heidelberg.
van Deemter K. Finetuning an NLG system through experiments with human subjects: the case of vague descriptions. In Belz A, Evans R, Piwek P, editors, Proc. of 3rd International Conference on Natural Language Generation. Berlin and Heidelberg: Springer Lecture Notes. 2004
van Deemter, Kees. / Finetuning an NLG system through experiments with human subjects : the case of vague descriptions. Proc. of 3rd International Conference on Natural Language Generation. editor / Anja Belz ; Roger Evans ; Paul Piwek. Berlin and Heidelberg : Springer Lecture Notes, 2004.
@inproceedings{ed82236e0b8547b2b831ddd3810f2b95,
title = "Finetuning an NLG system through experiments with human subjects: the case of vague descriptions.",
abstract = "Abstract. This discussion paper describes a sequence of experiments with human subjects aimed at nding out how an nlg system should choose between the dierent forms of a gradable adjective. This case study highlights some general questions that one faces when trying to base nlg systems on empirical evidence: one question is what task to set a subject so as to obtain the most useful information about that subject, another question has to do with dierences between subjects.",
keywords = "Vague adjectives., Experiments with human subjects.",
author = "{van Deemter}, Kees",
year = "2004",
language = "English",
editor = "Anja Belz and Roger Evans and Paul Piwek",
booktitle = "Proc. of 3rd International Conference on Natural Language Generation",
publisher = "Springer Lecture Notes",

}

TY - GEN

T1 - Finetuning an NLG system through experiments with human subjects

T2 - the case of vague descriptions.

AU - van Deemter, Kees

PY - 2004

Y1 - 2004

N2 - Abstract. This discussion paper describes a sequence of experiments with human subjects aimed at nding out how an nlg system should choose between the dierent forms of a gradable adjective. This case study highlights some general questions that one faces when trying to base nlg systems on empirical evidence: one question is what task to set a subject so as to obtain the most useful information about that subject, another question has to do with dierences between subjects.

AB - Abstract. This discussion paper describes a sequence of experiments with human subjects aimed at nding out how an nlg system should choose between the dierent forms of a gradable adjective. This case study highlights some general questions that one faces when trying to base nlg systems on empirical evidence: one question is what task to set a subject so as to obtain the most useful information about that subject, another question has to do with dierences between subjects.

KW - Vague adjectives.

KW - Experiments with human subjects.

M3 - Conference contribution

BT - Proc. of 3rd International Conference on Natural Language Generation

A2 - Belz, Anja

A2 - Evans, Roger

A2 - Piwek, Paul

PB - Springer Lecture Notes

CY - Berlin and Heidelberg

ER -

Access to Document