21 |
Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
22 |
Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
25 |
Relation-Guided Pre-Training for Open-Domain Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
English Machine Reading Comprehension Datasets: A Survey ...
|
|
|
|
BASE
|
|
Show details
|
|
28 |
End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs ...
|
|
|
|
BASE
|
|
Show details
|
|
29 |
FinQA: A Dataset of Numerical Reasoning over Financial Data ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection ...
|
|
|
|
BASE
|
|
Show details
|
|
32 |
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
33 |
Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation ...
|
|
|
|
BASE
|
|
Show details
|
|
34 |
Joint Passage Ranking for Diverse Multi-Answer Retrieval ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.560/ Abstract: 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. In this paper, we introduce JPR, the first joint passage retrieval model for multi-answer retrieval. JPR makes use of an autoregressive reranker that selects a sequence of passages, each conditioned on previously selected passages. JPR is trained to select passages that cover new answers at each timestep and uses a tree-decoding algorithm to enable flexibility in the degree of diversity. 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 ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing; Question-Answering Systems
|
|
URL: https://underline.io/lecture/37264-joint-passage-ranking-for-diverse-multi-answer-retrieval https://dx.doi.org/10.48448/6z1n-4s37
|
|
BASE
|
|
Hide details
|
|
35 |
SituatedQA: Incorporating Extra-Linguistic Contexts into QA ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
What's in a Name? Answer Equivalence For Open-Domain Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
38 |
Numerical reasoning in machine reading comprehension tasks: are we there yet? ...
|
|
|
|
BASE
|
|
Show details
|
|
39 |
Do We Know What We Don't Know? Studying Unanswerable Questions beyond SQuAD 2.0 ...
|
|
|
|
BASE
|
|
Show details
|
|
40 |
Relation-aware Bidirectional Path Reasoning for Commonsense Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|