Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

Plepi, Joan; Kacupaj, Endri; Singh, K. M.; Thakkar, Harsh; Lehmann, Jens

doi:10.1007/978-3-030-77385-4_21

Cited by 29 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The short answer section presents early Conversational QA (ConvQA) systems then discusses the transition to more recent Transformer architectures based on pre-trained language models. Section 5.1.5 then examines how ConvQA is performed over structured knowledge graphs including systems that use key-value networks (Saha et al, 2018), generative approaches, and logical query representations (Plepi et al, 2021). Following this, we discuss open retrieval from large text corpora as part of the QA process.…”

Section: Determining Next Utterancesmentioning

confidence: 99%

“…For instance, Shen et al (2019) presented the Multi-task Semantic Parsing (MaSP) model, performing both entity typing and coreference resolution together with semantic parsing. A subsequent multi-task model is CARTON (Context trAns-formeR sTacked pOinter Networks) (Plepi et al, 2021), with an encoder and decoder model to model the conversational representations. A series of three stacked pointer networks focus on the logical form needed for execution (types, predicates, and entities).…”

Section: Conversational Qa On Knowledge Graphsmentioning

confidence: 99%

See 1 more Smart Citation

Conversational Information Seeking

Zamani¹,

Trippas²,

Dalton³

et al. 2022

Preprint

View full text Add to dashboard Cite

Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is to provide an overview of past research related to CIS, introduce the current state-of-the-art in CIS, highlight the challenges still being faced in the community. and suggest future directions.

show abstract

Section: Determining Next Utterancesmentioning

confidence: 99%

Section: Conversational Qa On Knowledge Graphsmentioning

confidence: 99%

Conversational Information Seeking

Zamani¹,

Trippas²,

Dalton³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For the logical forms, we employ a grammar that can be used to capture the entire context of the question with the minimum number of actions. We prefer not to reinvent the wheel, and therefore we adopted the grammar from existing stateof-the-art question answering systems (Kacupaj et al, 2021b;Plepi et al, 2021). However, we do not employ all the actions from these works; Table 7 illustrates the complete grammar with all the defined actions that we used for all three answer verbalization datasets.…”

Section: A Appendixmentioning

confidence: 99%

“…This work argues that leveraging content from both sources allows the model for better convergence and provides new, improved results. Furthermore, we complement our hypothesis with multi-task learning paradigms, since multi-task learning has been quite efficient for different system architectures (Cipolla et al, 2018), including question answering systems (Plepi et al, 2021;Kacupaj et al, 2021b). Our framework can receive two (e.g., question & query) or even one (e.g., question) input.…”

Section: Introductionmentioning

confidence: 99%

VOGUE: Answer Verbalization through Multi-Task Learning

Kacupaj¹,

Premnadh²,

Singh³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer verbalization. However, in real-world scenarios (e.g., voice assistants such as Alexa, Siri, etc.), users prefer verbalized answers instead of a generated response. This paper addresses the task of answer verbalization for (complex) question answering over knowledge graphs. In this context, we propose a multi-task-based answer verbalization framework: VOGUE (Verbalization thrOuGh mUlti-task lEarning). The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multitask learning paradigm. Our framework can generate results based on using questions and queries as inputs concurrently. VOGUE comprises four modules that are trained simultaneously through multi-task learning. We evaluate our framework on all existing datasets for answer verbalization, and it outperforms all current baselines on both BLEU and ME-TEOR scores as evaluation metric.

show abstract

“…State-of-the-art works on ConvQA make use of single information sources: either curated knowledge bases (KB) [8,10,18,20,22,26,29,41,44], or unstructured text collections [5,13,31,33,34], or Web tables [14,27], but only one of these. Questions 𝑞 0 and 𝑞 2 can be answered more conveniently using KBs like Wikidata [53], YAGO [46], or DBpedia [1], that store factual world knowledge in compact RDF triples.…”

mentioning

confidence: 99%

Conversational Question Answering on Heterogeneous Sources

Christmann¹,

Roy²,

Weikum³

2022

Preprint

View full text Add to dashboard Cite

Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text corpus, or a collection of tables. This paper addresses the novel issue of jointly tapping into all of these together, this way boosting answer coverage and confidence. We present Convinse, an end-to-end pipeline for ConvQA over heterogeneous sources, operating in three stages: i) learning an explicit structured representation of an incoming question and its conversational context, ii) harnessing this framelike representation to uniformly capture relevant evidences from KB, text, and tables, and iii) running a fusion-in-decoder model to generate the answer. We construct and release the first benchmark, ConvMix, for ConvQA over heterogeneous sources, comprising 3000 real-user conversations with 16000 questions, along with entity annotations, completed question utterances, and question paraphrases. Experiments demonstrate the viability and advantages of our method, compared to state-of-the-art baselines. CCS CONCEPTS• Information systems → Question answering.

show abstract

Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

Cited by 29 publications

References 25 publications

Conversational Information Seeking

Conversational Information Seeking

VOGUE: Answer Verbalization through Multi-Task Learning

Conversational Question Answering on Heterogeneous Sources

Contact Info

Product

Resources

About