Generating Faithful Text From a Knowledge Graph with Noisy Reference Text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hashem, Tahsina, Wang, Weiqing, Wijaya, Derry Tanti, Ali, Mohammed Eunus, Li, Yuan-Fang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913492467974144
author Hashem, Tahsina
Wang, Weiqing
Wijaya, Derry Tanti
Ali, Mohammed Eunus
Li, Yuan-Fang
author_facet Hashem, Tahsina
Wang, Weiqing
Wijaya, Derry Tanti
Ali, Mohammed Eunus
Li, Yuan-Fang
contents Knowledge Graph (KG)-to-Text generation aims at generating fluent natural-language text that accurately represents the information of a given knowledge graph. While significant progress has been made in this task by exploiting the power of pre-trained language models (PLMs) with appropriate graph structure-aware modules, existing models still fall short of generating faithful text, especially when the ground-truth natural-language text contains additional information that is not present in the graph. In this paper, we develop a KG-to-text generation model that can generate faithful natural-language text from a given graph, in the presence of noisy reference text. Our framework incorporates two core ideas: Firstly, we utilize contrastive learning to enhance the model's ability to differentiate between faithful and hallucinated information in the text, thereby encouraging the decoder to generate text that aligns with the input graph. Secondly, we empower the decoder to control the level of hallucination in the generated text by employing a controllable text generation technique. We evaluate our model's performance through the standard quantitative metrics as well as a ChatGPT-based quantitative and qualitative analysis. Our evaluation demonstrates the superior performance of our model over state-of-the-art KG-to-text models on faithfulness.
format Preprint
id arxiv_https___arxiv_org_abs_2308_06488
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
Hashem, Tahsina
Wang, Weiqing
Wijaya, Derry Tanti
Ali, Mohammed Eunus
Li, Yuan-Fang
Computation and Language
Artificial Intelligence
Knowledge Graph (KG)-to-Text generation aims at generating fluent natural-language text that accurately represents the information of a given knowledge graph. While significant progress has been made in this task by exploiting the power of pre-trained language models (PLMs) with appropriate graph structure-aware modules, existing models still fall short of generating faithful text, especially when the ground-truth natural-language text contains additional information that is not present in the graph. In this paper, we develop a KG-to-text generation model that can generate faithful natural-language text from a given graph, in the presence of noisy reference text. Our framework incorporates two core ideas: Firstly, we utilize contrastive learning to enhance the model's ability to differentiate between faithful and hallucinated information in the text, thereby encouraging the decoder to generate text that aligns with the input graph. Secondly, we empower the decoder to control the level of hallucination in the generated text by employing a controllable text generation technique. We evaluate our model's performance through the standard quantitative metrics as well as a ChatGPT-based quantitative and qualitative analysis. Our evaluation demonstrates the superior performance of our model over state-of-the-art KG-to-text models on faithfulness.
title Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2308.06488