Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

By Ameya Godbole, Dilip Chakravarthy Kavarthapu, Rajarshi Das, Z. Gong, Abhishek Singhal, Hamed Zamani, Mo Yu, Tian Gao, Xiaoxiao Guo, Manzil Zaheer and 1 more. 2019

54 citations recorded by the source corpus.

Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to ‘hop’ to other relevant evidence. In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by 10.59 F1.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

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): “The effectiveness of arbitrary-step retrieval The existing iterative retrieval methods ﬁx the number of reasoning steps (Qi et al., 2019; Das et al., 2019; Godbole et al., 2019; Feldman & El-Yaniv, 2019), while our approach accommodates arbitrary steps of reasoning.”
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering (2019, methodology): “Other graph retrieval methods have been developed, either using entity name matching (Ding et al., 2019; Xiong et al., 2019b; Godbole et al., 2019) or hyperlinks (Asai et al.”
Adaptive Information Seeking for Open-Domain Question Answering (2021, methodology): “…47.3 10.9 (Wang et al., 2019b) 53.0 60.9 100 DPR (Karpukhin et al., 2020) 29.8 - 100 BM25+DPR (Karpukhin et al., 2020) 36.7 - 100 Multi-step Reasoner (Das et al., 2019a) 31.9 39.2 5 MUPPET (Feldman and El-Yaniv, 2019) 39.3 46.2 45 GRR † (Asai et al., 2020) 56.5 63.8 ≥ 500 SPARTA † (Zhao et al.,…”
Differentiable Reasoning over a Virtual Knowledge Base (2020, background): “† : Baselines obtained from Das et al. (2019b).”
Hierarchical Graph Network for Multi-hop Question Answering (2019, neutral): “13 Entity-centric BERT (Godbole et al., 2019) 41.”
Multi-hop Question Answering via Reasoning Chains (2019, background): “A recent line of works on open-domain multi-hop QA (Feldman and El-Yaniv, 2019; Das et al., 2019; Asai et al., 2019; Qi et al., 2019; Godbole et al., 2019) also adopt the idea of forming query in a iterative way to select the most relevant documents regarding the question.”
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning (2020, background): “Finally, recently some works propose the entity-centric paragraph retrieval approaches (Ding et al., 2019; Godbole et al., 2019; Min et al., 2019b; Asai et al., 2019), where paragraphs are connected if they share the same-named entities.”
DDRQA: Dynamic Document Reranking for Open-domain Multi-hop Question Answering (2020, methodology): “BERT reranker (Das et al., 2019b) trains a BERT model to rerank the retrieved documents.”
Retrieval-Enhanced Machine Learning (2022, methodology): “[10] performed iterative retrieval for expanding and rewriting multi-hop questions.”
Answering Any-hop Open-domain Questions with Iterative Document Reranking (2020, methodology): “BERT Reranker [5], DrKIT [8] and Transformer-XH [43] employ the entities in the question and the retrieved documents to link additional documents, which expands the one-shot retrieval results and improves the evidence coverage.”
Answer Complex Questions: Path Ranker Is All You Need (2021, unknown): “Therefore, recent studies attempt to use the pretrained language models (PLM [13]) as the “re-ranker” to select the top1 candidate for extracting answer, which is the state-of-the-art approach in the open-domain QA [5].”