Joint Passage Ranking for Diverse Multi-Answer Retrieval

04/17/2021
by   Sewon Min, et al.
0

We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a given question. This task requires joint modeling of retrieved passages, as models should not repeatedly retrieve passages containing the same answer at the cost of missing a different valid answer. Prior work focusing on single-answer retrieval is limited as it cannot reason about the set of passages jointly. In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. To model the joint probability of the retrieved passages, JPR makes use of an autoregressive reranker that selects a sequence of passages, equipped with novel training and decoding algorithms. Compared to prior approaches, JPR achieves significantly better answer coverage on three multi-answer datasets. When combined with downstream question answering, the improved retrieval enables larger answer generation models since they need to consider fewer passages, establishing a new state-of-the-art.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/29/2022

Diverse Multi-Answer Retrieval with Determinantal Point Processes

Often questions provided to open-domain question answering systems are a...
research
09/22/2021

Eliciting Thinking Hierarchy without Prior

A key challenge in crowdsourcing is that majority may make systematic mi...
research
07/09/2021

Joint Models for Answer Verification in Question Answering Systems

This paper studies joint models for selecting correct answer sentences a...
research
10/07/2022

Retrieval Augmented Visual Question Answering with Outside Knowledge

Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQ...
research
01/16/2022

Double Retrieval and Ranking for Accurate Question Answering

Recent work has shown that an answer verification step introduced in Tra...
research
04/22/2022

Autoregressive Search Engines: Generating Substrings as Document Identifiers

Knowledge-intensive language tasks require NLP systems to both provide t...
research
03/22/2021

Mitigating False-Negative Contexts in Multi-document QuestionAnswering with Retrieval Marginalization

Question Answering (QA) tasks requiring information from multiple docume...

Please sign up or login with your details

Forgot password? Click here to reset