Automatic Evaluation of Text Coherence: Models and Representations

Maria Lapata; Regina Barzilay

Automatic Evaluation of Text Coherence: Models and Representations

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

Abstract / Description of output

This paper investigates the automatic evaluation of text coherence for machine-generated texts. We introduce a fully-automatic, linguistically rich model of local coherence that correlates with human judgments.Our modeling approach relies on shallow text properties and is relatively inexpensive. We present experimental results that assess the predictive power of various discourse representations proposed in the linguistic literature. Our results demonstrate that certain models capture complementary aspects of coherence and thus can be combined to improve performance.

Original language	English
Title of host publication	IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Publisher	Morgan Kaufmann Publishers Inc.
Pages	1085-1090
Number of pages	6
Publication status	Published - 2005

Access to Document

http://www.ijcai.org/Proceedings/05/Papers/0505.pdf

Statistical model for text-to-text generation
Lapata, M.
EPSRC
1/02/05 → 28/02/11
Project: Research

Cite this

@inproceedings{58ba929fa0094ac784b0b5844b279b69,

title = "Automatic Evaluation of Text Coherence: Models and Representations",

abstract = "This paper investigates the automatic evaluation of text coherence for machine-generated texts. We introduce a fully-automatic, linguistically rich model of local coherence that correlates with human judgments.Our modeling approach relies on shallow text properties and is relatively inexpensive. We present experimental results that assess the predictive power of various discourse representations proposed in the linguistic literature. Our results demonstrate that certain models capture complementary aspects of coherence and thus can be combined to improve performance.",

author = "Maria Lapata and Regina Barzilay",

year = "2005",

language = "English",

pages = "1085--1090",

booktitle = "IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence",

publisher = "Morgan Kaufmann Publishers Inc.",

}

TY - GEN

T1 - Automatic Evaluation of Text Coherence: Models and Representations

AU - Lapata, Maria

AU - Barzilay, Regina

PY - 2005

Y1 - 2005

N2 - This paper investigates the automatic evaluation of text coherence for machine-generated texts. We introduce a fully-automatic, linguistically rich model of local coherence that correlates with human judgments.Our modeling approach relies on shallow text properties and is relatively inexpensive. We present experimental results that assess the predictive power of various discourse representations proposed in the linguistic literature. Our results demonstrate that certain models capture complementary aspects of coherence and thus can be combined to improve performance.

AB - This paper investigates the automatic evaluation of text coherence for machine-generated texts. We introduce a fully-automatic, linguistically rich model of local coherence that correlates with human judgments.Our modeling approach relies on shallow text properties and is relatively inexpensive. We present experimental results that assess the predictive power of various discourse representations proposed in the linguistic literature. Our results demonstrate that certain models capture complementary aspects of coherence and thus can be combined to improve performance.

M3 - Conference contribution

SP - 1085

EP - 1090

BT - IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

PB - Morgan Kaufmann Publishers Inc.

ER -

Automatic Evaluation of Text Coherence: Models and Representations

Abstract / Description of output

Access to Document

Fingerprint

Projects

Statistical model for text-to-text generation

Cite this