Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs
Most Knowledge Graph-based Question Answering (KGQA) systems rely on training data to reach their optimal performance. However, acquiring training data for supervised systems is both time-consuming and resource-intensive. To address this, in this paper, we propose <bold>Tree-KGQA</bold>,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9770789/ |
| _version_ | 1798038415754657792 |
|---|---|
| author | Md Rashad Al Hasan Rony Debanjan Chaudhuri Ricardo Usbeck Jens Lehmann |
| author_facet | Md Rashad Al Hasan Rony Debanjan Chaudhuri Ricardo Usbeck Jens Lehmann |
| author_sort | Md Rashad Al Hasan Rony |
| collection | DOAJ |
| description | Most Knowledge Graph-based Question Answering (KGQA) systems rely on training data to reach their optimal performance. However, acquiring training data for supervised systems is both time-consuming and resource-intensive. To address this, in this paper, we propose <bold>Tree-KGQA</bold>, an unsupervised KGQA system leveraging pre-trained language models and tree-based algorithms. Entity and relation linking are essential components of any KGQA system. We employ several pre-trained language models in the entity linking task to recognize the entities mentioned in the question and obtain the contextual representation for indexing. Furthermore, for relation linking we incorporate a pre-trained language model previously trained for language inference task. Finally, we introduce a novel algorithm for extracting the answer entities from a KG, where we construct a forest of interpretations and introduce tree-walking and tree disambiguation techniques. Our algorithm uses the linked relation and predicts the tree branches that eventually lead to the potential answer entities. The proposed method achieves 4.5% and 7.1% gains in F1 score in entity linking tasks on LC-QuAD 2.0 and LC-QuAD 2.0 (KBpearl) datasets, respectively, and a 5.4% increase in the relation linking task on LC-QuAD 2.0 (KBpearl). The comprehensive evaluations demonstrate that our unsupervised KGQA approach outperforms other supervised state-of-the-art methods on the WebQSP-WD test set (1.4% increase in F1 score) - without training on the target dataset. |
| first_indexed | 2024-04-11T21:39:54Z |
| format | Article |
| id | doaj.art-fdf21c405acd4a01b7517871f7ff53a7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T21:39:54Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fdf21c405acd4a01b7517871f7ff53a72022-12-22T04:01:37ZengIEEEIEEE Access2169-35362022-01-0110504675047810.1109/ACCESS.2022.31733559770789Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge GraphsMd Rashad Al Hasan Rony0https://orcid.org/0000-0003-0665-389XDebanjan Chaudhuri1Ricardo Usbeck2https://orcid.org/0000-0002-0191-7211Jens Lehmann3Smart Data Analytics Research Group, University of Bonn, Bonn, GermanySmart Data Analytics Research Group, University of Bonn, Bonn, GermanySemantic Systems Group, University of Hamburg, Hamburg, GermanySmart Data Analytics Research Group, University of Bonn, Bonn, GermanyMost Knowledge Graph-based Question Answering (KGQA) systems rely on training data to reach their optimal performance. However, acquiring training data for supervised systems is both time-consuming and resource-intensive. To address this, in this paper, we propose <bold>Tree-KGQA</bold>, an unsupervised KGQA system leveraging pre-trained language models and tree-based algorithms. Entity and relation linking are essential components of any KGQA system. We employ several pre-trained language models in the entity linking task to recognize the entities mentioned in the question and obtain the contextual representation for indexing. Furthermore, for relation linking we incorporate a pre-trained language model previously trained for language inference task. Finally, we introduce a novel algorithm for extracting the answer entities from a KG, where we construct a forest of interpretations and introduce tree-walking and tree disambiguation techniques. Our algorithm uses the linked relation and predicts the tree branches that eventually lead to the potential answer entities. The proposed method achieves 4.5% and 7.1% gains in F1 score in entity linking tasks on LC-QuAD 2.0 and LC-QuAD 2.0 (KBpearl) datasets, respectively, and a 5.4% increase in the relation linking task on LC-QuAD 2.0 (KBpearl). The comprehensive evaluations demonstrate that our unsupervised KGQA approach outperforms other supervised state-of-the-art methods on the WebQSP-WD test set (1.4% increase in F1 score) - without training on the target dataset.https://ieeexplore.ieee.org/document/9770789/Knowledge based systemsinformation retrievalquestion answeringentity linkingrelation linkingindexing |
| spellingShingle | Md Rashad Al Hasan Rony Debanjan Chaudhuri Ricardo Usbeck Jens Lehmann Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs IEEE Access Knowledge based systems information retrieval question answering entity linking relation linking indexing |
| title | Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs |
| title_full | Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs |
| title_fullStr | Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs |
| title_full_unstemmed | Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs |
| title_short | Tree-KGQA: An Unsupervised Approach for Question Answering Over Knowledge Graphs |
| title_sort | tree kgqa an unsupervised approach for question answering over knowledge graphs |
| topic | Knowledge based systems information retrieval question answering entity linking relation linking indexing |
| url | https://ieeexplore.ieee.org/document/9770789/ |
| work_keys_str_mv | AT mdrashadalhasanrony treekgqaanunsupervisedapproachforquestionansweringoverknowledgegraphs AT debanjanchaudhuri treekgqaanunsupervisedapproachforquestionansweringoverknowledgegraphs AT ricardousbeck treekgqaanunsupervisedapproachforquestionansweringoverknowledgegraphs AT jenslehmann treekgqaanunsupervisedapproachforquestionansweringoverknowledgegraphs |