Single Sequence Prediction over Reasoning Graphs for Multi-hop QA
- URL: http://arxiv.org/abs/2307.00335v1
- Date: Sat, 1 Jul 2023 13:15:09 GMT
- Title: Single Sequence Prediction over Reasoning Graphs for Multi-hop QA
- Authors: Gowtham Ramesh and Makesh Sreedhar and Junjie Hu
- Abstract summary: We propose a single-sequence prediction method over a local reasoning graph (model)footnoteCode/Models.
We use a graph neural network to encode this graph structure and fuse the resulting representations into the entity representations of the model.
Our experiments show significant improvements in answer exact-match/F1 scores and faithfulness of grounding in the reasoning path.
- Score: 8.442412179333205
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent generative approaches for multi-hop question answering (QA) utilize
the fusion-in-decoder method~\cite{izacard-grave-2021-leveraging} to generate a
single sequence output which includes both a final answer and a reasoning path
taken to arrive at that answer, such as passage titles and key facts from those
passages. While such models can lead to better interpretability and high
quantitative scores, they often have difficulty accurately identifying the
passages corresponding to key entities in the context, resulting in incorrect
passage hops and a lack of faithfulness in the reasoning path. To address this,
we propose a single-sequence prediction method over a local reasoning graph
(\model)\footnote{Code/Models will be released at
\url{https://github.com/gowtham1997/SeqGraph}} that integrates a graph
structure connecting key entities in each context passage to relevant
subsequent passages for each question. We use a graph neural network to encode
this graph structure and fuse the resulting representations into the entity
representations of the model. Our experiments show significant improvements in
answer exact-match/F1 scores and faithfulness of grounding in the reasoning
path on the HotpotQA dataset and achieve state-of-the-art numbers on the
Musique dataset with only up to a 4\% increase in model parameters.
Related papers
- Graph Attention with Hierarchies for Multi-hop Question Answering [19.398300844233837]
We present two extensions to the SOTA Graph Neural Network (GNN) based model for HotpotQA.
Experiments on HotpotQA demonstrate the efficiency of the proposed modifications.
arXiv Detail & Related papers (2023-01-27T15:49:50Z) - Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph
Matching [68.35685422301613]
We propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs.
It couples the target graph with other counterpart instances and identifies the most crucial joint substructure by minimizing the node corresponding-based distance.
Experiments on synthetic and real-world datasets show the effectiveness of our MatchExplainer by outperforming all state-of-the-art parametric baselines with significant margins.
arXiv Detail & Related papers (2023-01-07T05:14:45Z) - Modeling Multi-hop Question Answering as Single Sequence Prediction [88.72621430714985]
We propose a simple generative approach (PathFid) that extends the task beyond just answer generation.
PathFid explicitly models the reasoning process to resolve the answer for multi-hop questions.
Our experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets.
arXiv Detail & Related papers (2022-05-18T21:57:59Z) - Question-Answer Sentence Graph for Joint Modeling Answer Selection [122.29142965960138]
We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs.
Online inference is then performed to solve the AS2 task on unseen queries.
arXiv Detail & Related papers (2022-02-16T05:59:53Z) - Question Answering Infused Pre-training of General-Purpose
Contextualized Representations [70.62967781515127]
We propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations.
We accomplish this goal by training a bi-encoder QA model, which independently encodes passages and questions, to match the predictions of a more accurate cross-encoder model.
We show large improvements over both RoBERTa-large and previous state-of-the-art results on zero-shot and few-shot paraphrase detection.
arXiv Detail & Related papers (2021-06-15T14:45:15Z) - Line Graph Neural Networks for Link Prediction [71.00689542259052]
We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications.
In this formalism, a link prediction problem is converted to a graph classification task.
We propose to seek a radically different and novel path by making use of the line graphs in graph theory.
In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
arXiv Detail & Related papers (2020-10-20T05:54:31Z) - Semantic Graphs for Generating Deep Questions [98.5161888878238]
We propose a novel framework which first constructs a semantic-level graph for the input document and then encodes the semantic graph by introducing an attention-based GGNN (Att-GGNN)
On the HotpotQA deep-question centric dataset, our model greatly improves performance over questions requiring reasoning over multiple facts, leading to state-of-the-art performance.
arXiv Detail & Related papers (2020-04-27T10:52:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.