Improving and evaluating complex question answering over knowledge bases by constructing strongly supervised data

Cao, Xing; Zhao, Yingsi; Shen, Bo

doi:10.1007/s00521-022-07965-0

Cited by 8 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To generate the language they looked at fine-tuning for retrieval-assisted generation models by combining pre-trained parametric and non-parametric memory. Authors [31] proposed a cross-lingual training approach that utilizes the generative architecture with resource-rich language. Authors [32] explored the direction of creating a dataset by the utilization of generative pre-trained language models in unsupervised environment followed by model fine-tuning by leveraging the guidance provided by the synthesized dataset.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Low-Resource Question-Answering Performance Through Word Seeding and Customized Refinement

Pandya,

Bhatt

2024

IJACSA

View full text Add to dashboard Cite

The state-of-the-art approaches in Question-Answering (QA) systems necessitate extensive supervised training datasets. In low-resource languages (LRL), the scarcity of data poses a bottleneck, and the manual annotation of labeled data is a rigorous process. Addressing this challenge, some recent efforts have explored cross-lingual or multilingual QA learning by leveraging training data from resource-rich languages (RRL). However, the efficiency of such approaches relies on syntactic compatibility between languages. The paper introduces the innovative method that involves seeding LRL data into RRL to create a bilingual supervised corpus while preserving the syntactical structure of RRL. The method employs the translation and transliteration of selected parts-of-speech (POS) category words. Additionally, the paper also proposes a customized approach to fine-tune the models using bilingual data. Employing the bilingual data and the proposed fine-tuning approach, the most successful model has achieved a 75.62 F1 score on the XQuAD Hindi dataset and a 68.92 F1 score on the MLQA Hindi dataset in a zero-shot architecture. In the experiments conducted using few-shot learning setup, the highest F1 scores of 79.17 on the XQuAD Hindi dataset and 70.42 on the MLQA Hindi dataset have been achieved.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Low-Resource Question-Answering Performance Through Word Seeding and Customized Refinement

Pandya,

Bhatt

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Others have proposed dynamic graphs [8], which form a joint subgraph of the question and the entity for reasoning, and regard the entire quetion as a node of the subgraph, but in the end it did not solve the above-mentioned reasoning path error to a great extent. Other studies [14,15] Specifically, RCAANet first adopts a pre-trained model to obtain question embedding and relation embedding. At each hop, we utilize the input module to acquire attention word features and semantic features.…”

Section: Introductionmentioning

confidence: 99%

Relation Cross-fusion Attention Assistance Networks for Multi-hop Question Answering over Knowledge Graphs

Lv,

Bao,

et al. 2024

Preprint

View full text Add to dashboard Cite

Multi-hop knowledge graph question answering aims to find answer entities from the knowledge graph based on natural language questions. This is a challenging task as it requires precise reasoning about entity relationships at each step. When humans perform multi-hop reasoning, they usually focus on specific relations between different hops and determine the next entity. However, most algorithms often choose the wrong specific relations, causing the system to deviate from the correct reasoning path. In multi-hop question answering, the specific relation between each hop is crucial. The existing TransferNet model mainly relies on question representation for relational reasoning, but cannot accurately calculate the specific relational distribution, which will profoundly affect question answering performance. On this basis, this paper proposes an interpretable assiatance framework, which makes full use of relation embedding and question semantics, and uses the attention mechanism to cross-fuse the relevant information of them to assist in calculating the relation distribution of each hop. Extensive experiments are conducted on two English datasets, WebQSP and CWQ, demonstrating that the proposed model outperforms state-of-the-art models by a large margin.

show abstract

“…These triplets can be abbreviated as

(h, r, t)

, where

h

and

t

represent entities and

r

denotes the relationship between them. In recent years, KGs have proven useful in a variety of downstream applications, including question‐answering (Cao et al, 2023), recommendation systems (Hsu et al, 2022), and support for robot actions (Daruna et al, 2022). KGs are classified into dynamic and static knowledge graphs, with the difference lying in the inclusion of temporal information in the former.…”

Section: Introductionmentioning

confidence: 99%

A semantic guide‐based embedding method for knowledge graph completion

Zhang,

Shen,

Wang

et al. 2024

Expert Systems

Self Cite

View full text Add to dashboard Cite

Knowledge graph embedding aims to map entities and relations into a low‐dimensional vector space for easy manipulation. However, frequent entities are updated more often than infrequent ones during training, leading to inadequate representation of the latter's embeddings, which, in turn, affects the model's overall performance in downstream tasks. To address this issue, we propose a semantic information guide and enhance (SGE) method. The SGE tackles the heterogeneity in the frequency of entities through semantic reconstruction and a guidance network. The semantic reconstruction strengthens the semantic relevance among all entities and connects entities with different frequencies in semantic space. The guidance network extends these connections to knowledge space, enhancing the expression abilities of infrequent entities’ embeddings without compromising the embeddings of frequent entities. Experiments with four commonly used benchmark datasets show that the SGE method improves the performance of baseline models in most cases and that the method is model‐independent.

show abstract

Improving and evaluating complex question answering over knowledge bases by constructing strongly supervised data

Cited by 8 publications

References 45 publications

Enhancing Low-Resource Question-Answering Performance Through Word Seeding and Customized Refinement

Enhancing Low-Resource Question-Answering Performance Through Word Seeding and Customized Refinement

Relation Cross-fusion Attention Assistance Networks for Multi-hop Question Answering over Knowledge Graphs

A semantic guide‐based embedding method for knowledge graph completion

Contact Info

Product

Resources

About