Multi-Hop Paragraph Retrieval for Open-Domain Question Answering

By Yair Feldman, Ran El-Yaniv. 2019

105 citations recorded by the source corpus.

This paper is concerned with the task of multi-hop open-domain Question Answering (QA). This task is particularly challenging since it requires the simultaneous performance of textual reasoning and efficient searching. We present a method for retrieving multiple supporting paragraphs, nested amidst a large knowledge base, which contain the necessary evidence to answer a given question. Our method iteratively retrieves supporting paragraphs by forming a joint vector representation of both a question and a paragraph. The retrieval is performed by considering contextualized sentence-level representations of the paragraphs in the knowledge source. Our method achieves state-of-the-art performance over two well-known datasets, SQuAD-Open and HotpotQA, which serve as our single- and multi-hop open-domain QA benchmarks, respectively.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, 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 Computer Vision and Pattern Recognition

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering (2019, methodology): “(Hu et al., 2019) 50.2 41.9 MUPPET (Feldman & El-Yaniv, 2019) 46.2 39.3 BERTserini (Yang et al., 2019) 46.1 38.6 DENSPI-hybrid (Seo et al., 2019) 44.4 36.2 MINIMAL (Min et al., 2018) 42.5 34.7 Multi-step Reasoner (Das et al., 2019) Re-rank2hop to Entity-centric IR demonstrates that exploring entity ”
Differentiable Reasoning over a Virtual Knowledge Base (2020, methodology): “The same limitation is shared by methods which perform multi-step retrieval interleaved with a reading comprehension model (Das et al., 2019a; Feldman & El-Yaniv, 2019; Lee et al., 2019).”
Hierarchical Graph Network for Multi-hop Question Answering (2019, neutral): “For the Fullwiki setting, the published baselines include SemanticRetrievalMRS (Yixin Nie, 2019), Entity-centric BERT (Godbole et al., 2019), GoldEn Retriever (Qi et al., 2019), Cognitive Graph (Ding et al., 2019), MUPPET (Feldman and El-Yaniv, 2019), QFE (Nishida et al., 2019), and the official bas”
Retrieve, Rerank, Read, then Iterate: Answering Open-Domain Questions of Arbitrary Complexity from Text (2020, methodology): “…various techniques to extend these retrieve-and-read systems, including making use of hyper-links between Wikipedia articles (Nie et al., 2019; Feldman and El-Yaniv, 2019; Zhao et al., 2019; Asai et al., 2020; Dhingra et al., 2020; Zhao et al., 2019) and iterative retrieval (Talmor and…”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “…the state-of-the-art dialogue systems such as Feng et al. (2019); Wu et al. (2016); Tao et al. (2019); Wang et al. (2019b); Chauhan et al. (2019); Feldman and El-Yaniv (2019); Chen et al. (2019c); Lu et al. (2019) and Coope et al. (2020) chose to use CNNs as a hierarchical feature extractor…”
Multi-Step Inference for Reasoning over Paragraphs (2020, unknown): “HOTPOTQA (Yang et al., 2018; Jiang et al., 2019; Jiang and Bansal, 2019; Min et al., 2019; Feldman and El-Yaniv, 2019), QANGAROO (Welbl et al.”
Delaying Interaction Layers in Transformer-based Encoders for Efficient Open Domain Question Answering (2020, background): “Since then, a few proposals (Lee, Chang, and Toutanova 2019; Feldman and El-Yaniv 2019; Wang et al. 2019; Ren, Cheng, and Su 2020) have been focusing on better selection of passages and a better pooling of answers from them.”
Answering Complex Open-domain Questions Through Iterative Query Generation (2019, unknown): “84 MUPPET (Feldman and El-Yaniv, 2019) 30.”
Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval (2021, methodology): “Instead, they use an iterative retrieval paradigm—akin to that introduced by Das et al. [6] and Feldman and El-Yaniv [9]—that retrieves passages relevant to the question, reads these passages, and then formulates a new query for another hop if necessary.”
HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions (2020, background): “Most of the recent works view multi-hop evidence collection as an iterative document retrieval problem (Asai et al. 2020; Feldman and El-Yaniv 2019; Das et al. 2019a), which can be decomposed to several single-step document retrieval.”
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention (2020, methodology): “We include other approaches on the FullWiki setting: Ofﬁcial Baseline (Yang et al., 2018), MUPPET (Feldman & El-Yaniv, 2019), QFE (Nishida et al., 2019), and DecompRC (Min et al., 2019a), Implementation Details.”
Distant Supervision for Multi-Stage Fine-Tuning in Retrieval-Based Question Answering (2020, methodology): “Furthermore, our techniques should be applicable to other neural models as well, including improvements to the basic BERTserini model architecture proposed by other researchers [1, 7, 8, 13, 20, 26].”
Differentiable Open-Ended Commonsense Reasoning (2020, unknown): “Multi-Hop Reasoning Many recent models for open-domain QA tackle multi-hop reasoning through iterative retrieval, e.g., GRAFT-Net (Sun et al., 2018), MUPPET (Feldman and El-Yaniv, 2019), PullNet (Sun et al., 2019), and GoldEn (Qi et al., 2019).”
Answering Any-hop Open-domain Questions with Iterative Document Reranking (2020, methodology): “Multi-step Reasoner [4] andMUPPET [11] read retrieved documents to reformulate the query in latent space for iterative retrieval.”
DDRQA: Dynamic Document Reranking for Open-domain Multi-hop Question Answering (2020, unknown): “Multi-step Reasoner (Das et al., 2019a) and MUPPET (Feldman and El-Yaniv, 2019) read retrieved documents to reformulate the query in latent space for iterative retrieval.”