Knowledge Base Question Answering with Topic Units

Lan, Yunshi; Wang, Shuohang; Jiang, Jing

doi:10.24963/ijcai.2019/701

Cited by 36 publications

(26 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we compare with existing staged query graph generation methods (Yih et al, 2015;Bao et al, 2016;Luo et al, 2018), which cannot handle multi-hop questions. Next, we compare with (Lan et al, 2019a), which handles constraints and considers multi-hop relation paths, but uses neither beam search nor constraints to reduce the search space. We also compare with (Chen et al, 2019), which uses beam search with a beam size of 1 to handle multi-hop questions but does not handle constraints.…”

Section: Methods For Comparisonmentioning

confidence: 99%

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases

Lan

Jiang

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

140

105

View full text Add to dashboard Cite

Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that early incorporation of constraints into query graphs can more effectively prune the search space, we propose a modified staged query graph generation method with more flexible ways to generate query graphs. Our experiments clearly show that our method achieves the state of the art on three benchmark KBQA datasets.

show abstract

Section: Methods For Comparisonmentioning

confidence: 99%

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases

Lan

Jiang

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

140

105

View full text Add to dashboard Cite

show abstract

“…For conversational KBQA, the initial question q 0 in a conversation c can be answered directly using an existing single-turn KBQA approach (Yu et al, 2017;Luo et al, 2018;Yih et al, 2016;Lan et al, 2019). When the single-turn KBQA system is used for answering follow-up questions, we make the following modifications: First, we assume that a focal entity distribution (which is the core of our method and will be presented in detail below) is derived from the conversation history.…”

Section: Pipeline For Single-turn Kbqamentioning

confidence: 99%

Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering

Lan¹,

Jiang²

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Conversational KBQA is about answering a sequence of questions related to a KB. Follow-up questions in conversational KBQA often have missing information referring to entities from the conversation history. In this paper, we propose to model these implied entities, which we refer to as the focal entities of the conversation. We propose a novel graph-based model to capture the transitions of focal entities and apply a graph neural network to derive a probability distribution of focal entities for each question, which is then combined with a standard KBQA module to perform answer ranking. Our experiments on two datasets demonstrate the effectiveness of our proposed method.

show abstract

“…Methods like bottom-up semantic parser [2], question syntax dependency [35] and staged query graph [38], are applied for question semantic analysis. Later, semantic query graph (SQG) [1,5,6,15,16,30] and Graph Neural Network [10,26] are used to enhance the semantic parsing performance.…”

Section: Related Work 21 Knowledge Based Question Answeringmentioning

confidence: 99%

Calculating Question Similarity is Enough: A New Method for KBQA Tasks

Zhao¹,

Yuan²,

Jiahong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with the help of an external knowledge base. The core idea is to find the link between the internal knowledge behind questions and known triples of the knowledge base. The KBQA task pipeline contains several steps, including entity recognition, relationship extraction, and entity linking. This kind of pipeline method means that errors in any procedure will inevitably propagate to the final prediction. In order to solve the above problem, this paper proposes a Corpus Generation -Retrieve Method (CGRM) with Pre-training Language Model (PLM) and Knowledge Graph (KG). Firstly, based on the mT5 model, we designed two new pre-training tasks: knowledge masked language modeling and question generation based on the paragraph to obtain the knowledge enhanced T5 (kT5) model. Secondly, after preprocessing triples of knowledge graph with a series of heuristic rules, the kT5 model generates natural language QA pairs based on processed triples. Finally, we directly solve the QA by retrieving the synthetic dataset. We test our method on NLPCC-ICCPOL 2016 KBQA dataset, and the results show that our framework improves the performance of KBQA and the out straight-forward method is competitive with the state-of-the-art.

show abstract

Knowledge Base Question Answering with Topic Units

Cited by 36 publications

References 13 publications

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases

Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering

Calculating Question Similarity is Enough: A New Method for KBQA Tasks

Contact Info

Product

Resources

About