Case-based Reasoning for Natural Language Queries over Knowledge Bases

Das, Raj; Zaheer, Manzil; Thai, Dung; Godbole, Ameya; Perez, Ethan; Lee, Jay-Yoon; Tan, Lizhen; Polymenakos, Lazaros; McCallum, Andrew

doi:10.48550/arxiv.2104.08762

Cited by 5 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sun et al 4 used a pipeline of subtasks, including question split and span prediction, for skeleton parsing. Das et al 33 used the pretrained T5 encoder-decoder model to directly produce a coarse skeleton.…”

Section: Related Workmentioning

confidence: 99%

Marie and BERT─A Knowledge Graph Embedding Based Question Answering System for Chemistry

Zhou,

Zhang,

Agarwal

et al. 2023

ACS Omega

View full text Add to dashboard Cite

This paper presents a novel knowledge graph question answering (KGQA) system for chemistry, which is implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the system operates on multiple embedding spaces, which use various embedding methods and queries the embedding spaces in parallel. With the answers returned from multiple embedding spaces, the system leverages a score alignment model to adjust the answer scores and rerank the answers. Further, the system implements an algorithm to derive implicit multihop relations to handle the complexities of deep ontologies and improve multihop question answering. The system also implements a BERT-based bidirectional entity-linking model to enhance the robustness and accuracy of the entity-linking module. The system uses a joint numerical embedding model to efficiently handle numerical filtering questions. Further, it can invoke semantic agents to perform dynamic calculations autonomously. Finally, the KGQA system handles numerous chemical reaction mechanisms using semantic parsing supported by a Linked Data Fragment server. This paper evaluates the accuracy of each module within the KGQA system with a chemistry question data set.

show abstract

Section: Related Workmentioning

confidence: 99%

Marie and BERT─A Knowledge Graph Embedding Based Question Answering System for Chemistry

Zhou,

Zhang,

Agarwal

et al. 2023

ACS Omega

View full text Add to dashboard Cite

show abstract

“…CBR-KBQA Models utilizing case-based reasoning methods [Aamodt and Plaza, 1994] first retrieve similar cases which are then used in synthesising the current answer. For question answering, such an architecture has been proposed by Das et al [2021]. The retrieved similar queries also contain their logical forms (e.g.…”

Section: Encodermentioning

confidence: 99%

Artefact Retrieval: Overview of NLP Models with Knowledge Base Access

Zouhar¹,

Mosbach²,

Biswas³

et al. 2022

Preprint

View full text Add to dashboard Cite

Many NLP models gain performance by having access to a knowledge base. A lot of research has been devoted to devising and improving the way the knowledge base is accessed and incorporated into the model, resulting in a number of mechanisms and pipelines. Despite the diversity of proposed mechanisms, there are patterns in the designs of such systems. In this paper, we systematically describe the typology of artefacts (items retrieved from a knowledge base), retrieval mechanisms and the way these artefacts are fused into the model. This further allows us to uncover combinations of design decisions that had not yet been tried. Most of the focus is given to language models, though we also show how question answering, fact-checking and knowledgable dialogue models fit into this system as well. Having an abstract model which can describe the architecture of specific models also helps with transferring these architectures between multiple NLP tasks.

show abstract

“…Therefore, we focus on fast online adaptation of Textto-SQL models without parameter updates, until the next cycle of finetuning is deemed feasible. Recently, case-based reasoning (CBR), which utilizes a memory of past labeled examples as cases, has emerged as a promising paradigm of inference-time adaptation without finetuning (Das et al 2020(Das et al , 2021Pasupat, Zhang, and Guu 2021;Gupta et al 2021). CBR has been found effective for tasks like knowledge graph completion (KGC) (Das et al 2020), question answering over knowledge bases (KBQA) (Das et al 2021), task-oriented semantic parsing (Pasupat, Zhang, and Guu 2021;Gupta et al 2021), translation (Khandelwal et al 2021), and text-based games (Atzeni et al 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Recently, case-based reasoning (CBR), which utilizes a memory of past labeled examples as cases, has emerged as a promising paradigm of inference-time adaptation without finetuning (Das et al 2020(Das et al , 2021Pasupat, Zhang, and Guu 2021;Gupta et al 2021). CBR has been found effective for tasks like knowledge graph completion (KGC) (Das et al 2020), question answering over knowledge bases (KBQA) (Das et al 2021), task-oriented semantic parsing (Pasupat, Zhang, and Guu 2021;Gupta et al 2021), translation (Khandelwal et al 2021), and text-based games (Atzeni et al 2022). However, many prior CBR approaches designed around Seq2Seq architectures simply concatenate input-output cases with the current input at the encoder (Das et al 2021;Pasupat, Zhang, and Guu 2021;Gupta et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers

Awasthi

Chakrabarti

Sarawagi

2023

AAAI

View full text Add to dashboard Cite

Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cases) from the new domain at the encoder’s input in a Seq-to-Seq model. Such methods cannot adequately leverage the structure of logical forms in the case examples. We propose StructCBR, a structured case-based reasoning approach, which leverages subtree-level similarity between logical forms of cases and candidate outputs, resulting in better decoder decisions. For the task of adapting Text-to-SQL models to unseen schemas, we show that exploiting case examples in a structured manner via StructCBR offers consistent performance improvements over prior inference-time adaptation methods across five different databases. To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.

show abstract

Case-based Reasoning for Natural Language Queries over Knowledge Bases

Cited by 5 publications

References 0 publications

Marie and BERT─A Knowledge Graph Embedding Based Question Answering System for Chemistry

Marie and BERT─A Knowledge Graph Embedding Based Question Answering System for Chemistry

Artefact Retrieval: Overview of NLP Models with Knowledge Base Access

Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers

Contact Info

Product

Resources

About