Learning Knowledge Graphs for Question Answering through Conversational Dialog

By Ben Hixon, Peter Clark, Hannaneh Hajishirzi. 2015

135 citations recorded by the source corpus.

We describe how a question-answering system can learn about its domain from conversational dialogs. Our system learns to relate concepts in science questions to propositions in a fact corpus, stores new concepts and relations in a knowledge graph (KG), and uses the graph to solve questions. We are the first to acquire knowledge for question-answering from open, natural language dialogs without a fixed ontology or domain model that predetermines what users can say. Our relation-based strategies complete more successful dialogs than a query expansion baseline, our taskdriven relations are more effective for solving science questions than relations from general knowledge sources, and our method is practical enough to generalize to other domains.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, background): “There are other, somewhat less related, ways to use feedback during dialogue for learning, notably for collecting knowledge to answer questions (Mazumder et al., 2018; Hixon et al., 2015; Pappu and Rudnicky, 2013), and more commonly in re-”
Dialog-based Language Learning (2016, background): “There is work on the the use of feedback and dialog for learning, notably for collecting knowledge to answer questions [8, 17], the use of natural language instruction for learning symbolic rules [10, 5] and the use of binary feedback (rewards) for learning parsers [3].”
Memory-assisted prompt editing to improve GPT-3 after deployment (2022, background): “While system debugging through dialogue has been explored in many contexts (Hixon et al., 2015; Wang et al., 2016; Davis, 1977), our novel contribution is a dialogue about the model’s understanding of the user’s intent.”
Parsing Algebraic Word Problems into Equations (2015, background): “More closely related is work on language grounding, whose goal is the interpretation of a sentence in the context of a world representation (Branavan et al., 2009; Liang et al., 2009; Chen et al., 2010; Bordes et al., 2010; Feng and Lapata, 2010; Hajishirzi et al., 2011; Matuszek et al., 2012; Hajis”
Learning End-to-End Goal-Oriented Dialog (2016, methodology): “The data for all tasks is available from http://fb.ai/babi .”
Conversational Neuro-Symbolic Commonsense Reasoning (2020, background): “, [14] on relation extraction through conversation for question answering.”
Solving Geometry Problems: Combining Text and Diagram Interpretation (2015, background): “…Hajishirzi et al., 2011; Liang et al., 2009; Koncel-Kedziorski et al., 2014; Bordes et al., 2010; Kim and Mooney, 2013; Angeli and Manning, 2014; Hixon et al., 2015; Koncel-Kedziorski et al., 2014; Artzi and Zettlemoyer, 2013) that involves mapping text to a restricted formalism (instead of a…”
Knowledge Acquisition for Visual Question Answering via Iterative Querying (2017, background): “Several works have investigated a variety of strategies to acquire knowledge from external sources [4, 14, 19, 29, 30, 34].”
Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks (2017, background): “Another related line of work is Hixon et al. (2015) who acquire knowledge in the form of knowledge graphs for question answering from natural language dialogs and (Goldwasser and Roth, 2014) who propose a technique called learning from natural instructions .”
Continuous and Interactive Factual Knowledge Learning in Veriﬁcation Dialogues (2020, methodology): “For example, we can directly extract knowledge from user utterances using information extraction methods [27, 18].”
Combining Natural Logic and Shallow Reasoning for Question Answering (2016, methodology): “This is the corpus used by Hixon et al. (2015) for their conversational dialog engine Knowbot, and therefore constitutes a more fair comparison against their results.”
VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases (2015, background): “Towards Answering Elementary-level Science Questions: Apart from answering generic questions, our approach can be useful for answering more specific questions such as those related to elementary-level general science [7, 21, 33, 20].”
Relational Memory-Augmented Language Models (2022, background): “, 2019), question answering (Zhang et al., 2018; Huang et al., 2019; Hixon et al., 2015), dialogue systems (Zhou et al.”
Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects (2016, background): “Qualitative Results: Size information is an important attribute for referring expressions and commonsense question answering (Mitchell, van Deemter, and Reiter 2011; Hixon, Clark, and Hajishirzi 2015) and can lead to inferences about size abnormalities in images.”
Lifelong Knowledge Learning in Rule-based Dialogue Systems (2020, background): “they directly use structured triples. Our KAD is a dialogue system and it does not have the restriction of requiring a user query that the system cannot answer. KAD aims to learn from any utterances. Hixon et al. (2015) proposed a system that starts with a multiple-choice science question and based ”