Challenge: Existing approaches for question answering over dialogue did not consider dialogue structure and background knowledge (e.g., relationships between speakers).
Approach: They propose a method which organizes a dialogue as a "relational graph" and uses edges to represent relationships between entities to encode multi-relations knowledge for reasoning.
Outcome: The proposed method is better at tackling complex questions requiring relational reasoning and defending adversarial attacks with distracting sentences.

Similar Papers

Question Answering by Reasoning Across Documents with Graph Convolutional Networks (N19-1)

Copied to clipboard

Challenge: Recent research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs.
Approach: They propose a neural model which integrates and reasons relying on information spread within documents and across multiple documents.
Outcome: The proposed model achieves state-of-the-art on a multi-document question answering dataset, WikiHop.
GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems (2020.emnlp-main)

Copied to clipboard

Challenge: End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs.
Approach: They propose a recurrent cell architecture which exploits the structural information in dialogue history . they propose recursive cell architecture to allow representation learning on graphs .
Outcome: The proposed model improves on two different datasets on task-oriented dialogues.
Leveraging Argumentation Knowledge Graph for Interactive Argument Pair Identification (2021.findings-acl)

Copied to clipboard

Challenge: Existing researches focus on sentence matching but the interaction of opinions requires reasoning of knowledge, which is beyond textual information.
Approach: They propose to leverage external knowledge to enhance the identification of interactive argument pairs by analyzing the discussion thread of the target topic in an online forum.
Outcome: The proposed model achieves state-of-the-art in the benchmark dataset.
Graph Based Network with Contextualized Representations of Turns in Dialogue (2021.emnlp-main)

Copied to clipboard

Challenge: Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue.
Approach: They propose a dialogue-based relation extraction model which is based on emotion recognition in conversations.
Outcome: The proposed model outperforms the state-of-the-art models on most of the benchmark datasets.
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation (2022.findings-naacl)

Copied to clipboard

Challenge: Recent research focused on knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured.
Approach: They propose a novel task-oriented dialogue system that effectively incorporates knowledge into a language model by using structural information of a knowledge graph.
Outcome: The proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a Knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation.
Towards Knowledge-Augmented Visual Question Answering (2020.coling-main)

Copied to clipboard

Challenge: Visual Question Answering (VQA) is a challenging task for humans, but it is effortless for visual-based approaches.
Approach: They propose a visual-based approach that captures interactions between visual scenes and external knowledge sources and exploits ConceptNet as the source of general knowledge.
Outcome: The proposed model learns a question-adaptive graph representation of related knowledge instances.
Reading Comprehension with Graph-based Temporal-Casual Reasoning (C18-1)

Copied to clipboard

Challenge: Existing methods for reading comprehension tasks ignore semantic relations between sentences or use sliding window scanning over the words of the passage without sentence breaks.
Approach: They propose a method to integrate information from multiple sentences to answer complex questions.
Outcome: Experiments on RACE and MCTest show that the proposed approach improves state-of-the-art methods on simple factoid questions.
Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks (2020.lrec-1)

Copied to clipboard

Challenge: Existing question-answering models do not require reasoning across sentences in the given context (passage).
Approach: They propose a graph neural network that propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation.
Outcome: The proposed approach obtains the best performance compared to the widely used answer-selection models that do not consider the intersentential relationship.
Aligned Dual Channel Graph Convolutional Network for Visual Question Answering (2020.acl-main)

Copied to clipboard

Challenge: Existing graph-based methods focus only on relations between objects in an image and neglect the importance of syntactic dependency relations between words.
Approach: They propose a dual channel graph convolutional network to capture relations between objects in an image and syntactic dependency relations between words in a question.
Outcome: The proposed model achieves comparable performance with the state-of-the-art approaches.
Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation (2023.acl-long)

Copied to clipboard

Challenge: Existing graph neural networks (GNNs) teach message passing on a graph from text, resulting in a semantic gap between graph knowledge and text.
Approach: They propose a framework to integrate external graph knowledge into chatbots by coagulating representations of both text and graph knowledge.
Outcome: The proposed framework outperforms state-of-the-art (SOTA) baselines on dialogue generation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations