Learning Knowledge Graphs for Question Answering through Conversational Dialog

@inproceedings{Hixon2015LearningKG,
  title={Learning Knowledge Graphs for Question Answering through Conversational Dialog},
  author={Ben Hixon and Peter Clark and Hannaneh Hajishirzi},
  booktitle={NAACL},
  year={2015}
}
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… Expand
Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion
TLDR
ConVEX is an unsupervised method that can answer incomplete questions over a knowledge graph by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. Expand
Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues
TLDR
Two modifications to the KGC training are presented, creating pseudo entities having substrings of the names of the entities in the graph so that the entities whose names share substrings are connected and limiting the range of negative sampling, suggesting that the model trained with the modifications is capable of avoiding questions with incorrect content. Expand
Combining Natural Logic and Shallow Reasoning for Question Answering
TLDR
This work extends the breadth of inferences afforded by natural logic to include relational entailment and meronymy and trains an evaluation function – akin to gameplaying – to evaluate the expected truth of candidate premises on the fly. Expand
Discovering Knowledge Graph Schema from Short Natural Language Text via Dialog
TLDR
This work proposes a dialog strategy that looks to elicit the schema over as short a dialog as possible, and shows that this significantly reduces dialog complexity while engaging the expert in meaningful dialog. Expand
Question Answering When Knowledge Bases are Incomplete
TLDR
A typology of missing information in knowledge bases is formalized, and a dataset based on the Spider KB question answering dataset is presented, where it is shown that simple baselines fail to detect most of the unanswerable questions. Expand
Open Information Extraction from Question-Answer Pairs
TLDR
NeurON is described, a system for extracting tuples from question-answer pairs that combines distributed representations of a question and an answer to generate knowledge facts and is described on two real-world datasets that demonstrate that NeurON can find a significant number of new and interesting facts to extend a knowledge base compared to state-of-the-art OpenIE methods. Expand
TION METHOD FOR USE IN NATURAL DIALOGUE
  • 2019
The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic andExpand
Augmenting Topic Aware Knowledge-Grounded Conversations with Dynamic Built Knowledge Graphs
  • Junjie Wu, Hao Zhou
  • Computer Science
  • DEELIO
  • 2021
TLDR
This is the first attempt to dynamically form knowledge graphs between chatting topics to assist dialog topic management during a conversation and results manifest that the model can properly schedule conversational topics and pick suitable knowledge to generate informative responses comparing to several strong baselines. Expand
Dialog-based Language Learning
TLDR
This work studies dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation, and shows that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. Expand
Interactive Factual Knowledge Learning in Dialogues
  • 2020
Knowledge bases (KBs) used in applications need to be continuously expanded in 1 order to serve the users well. This process is known as knowledge base completion 2 (KBC). A piece of knowledge or aExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 37 REFERENCES
Learning situated knowledge bases through dialog
TLDR
This work builds a system that solicits situational information from its users in a domain that provides information on events (seminar talks) to augment its knowledge base (covering an academic field) and finds that this knowledge is consistent and useful and that it provides reliable information to users. Expand
Probabilistic enrichment of knowledge graph entities for relation detection in conversational understanding
TLDR
This paper proposes new methods to assign weights to semantic graphs that reflect common usage types of the entities and their relations and shows that all weighting methods result in better performance in comparison to using the unweighted version of the semantic knowledge graph. Expand
Modeling Biological Processes for Reading Comprehension
TLDR
This paper focuses on a new reading comprehension task that requires complex reasoning over a single document, and demonstrates that answering questions via predicted structures substantially improves accuracy over baselines that use shallower representations. Expand
Bootstrapping Semantic Parsers from Conversations
TLDR
This paper introduces a loss function to measure how well potential meanings match the conversation, and induces a weighted CCG grammar that could be used to automatically bootstrap the semantic analysis component in a complete dialog system. Expand
Knowledge Acquisition Strategies for Goal-Oriented Dialog Systems
TLDR
This paper proposes knowledge acquisition strategies for a dialog agent and shows their effectiveness, and the acquired knowledge can be shown to subsequently contribute to task completion. Expand
Open Dialogue Management for Relational Databases
TLDR
Evaluation of the system with simulated users shows that users with realistically limited domain knowledge have dialogues nearly as efficient as those of users with complete domain knowledge. Expand
An Interactive Dialogue System for Knowledge Acquisition in Cyc
TLDR
Cycorp has developed a knowledge acquisition system that can engage a user in a natural-language mixed-initiative dialogue that employs explicit topic and user-modeling, a system of prioritized interactions, and a transparent agenda to which either the user or the system can add interactions at any time. Expand
Commonsense Reasoning in and Over Natural Language
TLDR
It is concluded that the flexibility of natural language makes it a highly suitable representation for achieving practical inferences over text, such as context finding, inference chaining, and conceptual analogy. Expand
Generating Recommendation Dialogs by Extracting Information from User Reviews
TLDR
This work presents a framework for generating and ranking fine-grained, highly relevant questions from user-generated reviews, and releases a new sentiment lexicon with 1329 adjectives for the restaurant domain. Expand
Understanding natural language
TLDR
A computer system for understanding English that contains a parser, a recognition grammar of English, programs for semantic analysis, and a general problem solving system based on the belief that in modeling language understanding, it must deal in an integrated way with all of the aspects of language—syntax, semantics, and inference. Expand
...
1
2
3
4
...