Coarse-grained decomposition and fine-grained interaction for multi-hop question answering
Recent advances regarding question answering and reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text, requiring only single-hop reasoning. However, in actual scenarios, lots of complex queries require multi-hop reasoning. The key to the Question Answering task is semantic feature interaction between documents and questions, which is widely processed by Bi-directional Attention Flow (Bi-DAF), but Bi-DAF generally captures only the surface semantics of words in complex questions and fails to capture implied semantic feature of intermediate answers. As a result, Bi-DAF partially ignores part of the contexts related to the question and cannot extract the most important parts of multiple documents. In this paper we propose a new model architecture for multi-hop question answering, by applying two completion strategies: (1) Coarse-Grain complex question Decomposition (CGDe) strategy are introduced to decompose complex question into simple ones under the condition of without any additional annotations (2) Fine-Grained Interaction (FGIn) strategy are introduced to better represent each word in the document and extract more comprehensive and accurate sentences related to the inference path. The above two strategies are combined and tested on the SQuAD and HotpotQA datasets, and the experimental results show that our method outperforms state-of-the-art baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-hop Question AnsweringQuestion AnsweringReading ComprehensionSimilar Papers 제목 키워드 기반
Hyperspectral Image Recovery Constrained by Multi-Granularity Non-Local Self-Similarity Priors
Hyperspectral image (HSI) recovery, as an upstream image processing task, holds significant importance for downstream tasks such as classification, segmentation, and detection. In recent years, HSI recovery methods based…
CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors
Unsupervised conditional image generation (UCGen) aims to control generation without relying on manually annotated labels, yet remains challenging due to unstructured semantic representations across granularities. To add…
Conditional Image GenerationMulti-grained Attention Network for Aspect-Level Sentiment Classification
We propose a novel multi-grained attention network (MGAN) model for aspect level sentiment classification. Existing approaches mostly adopt coarse-grained attention mechanism, which may bring information loss if the aspe…
Aspect-Based Sentiment Analysis (ABSA)ClassificationGeneral ClassificationSentiment Analysis+1Enhancing Low-resource Fine-grained Named Entity Recognition by Leveraging Coarse-grained Datasets
Named Entity Recognition (NER) frequently suffers from the problem of insufficient labeled data, particularly in fine-grained NER scenarios. Although $K$-shot learning techniques can be applied, their performance tends t…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+1ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition
In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these me…
DisentanglementIntrinsic Image Decomposition