Challenge: Popular QA benchmarks like SQuAD have driven progress on identifying answer spans within a specific passage . retrieving relevant answers from a huge corpus of documents is still a challenging problem .
Approach: They propose a benchmark for evaluating large-scale sentence-level answer retrieval models . they establish baselines using both neural encoding models and classical retrieval techniques .
Outcome: The proposed model outperforms human models on identifying answer spans within a specific passage . the proposed model is scalable and can bypass the typical document retrieval step .

Similar Papers

RankQA: Neural Question Answering with Answer Re-Ranking (P19-1)

Copied to clipboard

Challenge: RankQA extends the conventional two-stage process in neural question answering . RankQ achieves state-of-the-art performance on 3 out of 4 benchmark datasets .
Approach: They propose to extend the conventional two-stage process in neural QA with a third stage that performs an additional answer re-ranking.
Outcome: RankQA outperforms more complex question answering systems by a significant margin on 3 out of 4 benchmark datasets.
NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets (2020.emnlp-demos)

Copied to clipboard

Challenge: Existing tools for Question Answering (QA) have challenges that limit their use in practice.
Approach: They propose a library that integrates with existing infrastructure and offers helpful defaults for QA subtasks.
Outcome: NeuralQA integrates well with existing infrastructure and offers helpful defaults for QA subtasks.
End-to-End Training of Neural Retrievers for Open-Domain Question Answering (2021.acl-long)

Copied to clipboard

Challenge: Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised methods.
Approach: They propose an approach of unsupervised pre-training with the Inverse Cloze Task and masked salient spans followed by supervised finetuning using question-context pairs.
Outcome: The proposed approach outperforms models like REALM and RAG in retrieval accuracy and answer extraction.
Answer Generation for Retrieval-based Question Answering Systems (2021.findings-acl)

Copied to clipboard

Challenge: Question Answering systems are a core component of many commercial applications . answer sentence selection (AS2) models are trained to select the best answer sentence .
Approach: They propose to train a sequence to sequence transformer model to generate an answer from a set of candidates.
Outcome: The proposed model improves accuracy by 32 points over the state-of-the-art model on English AS2 datasets.
Adaptive Document Retrieval for Deep Question Answering (D18-1)

Copied to clipboard

Challenge: Existing methods for deep question answering do not understand the exact interplay between document retrieval and machine comprehension.
Approach: They propose an adaptive document retrieval model that learns the optimal document number, conditional on the size of the corpus and the query.
Outcome: The proposed model outperforms state-of-the-art methods on multiple benchmark datasets and in the context of corpora with variable sizes.
Double Retrieval and Ranking for Accurate Question Answering (2023.findings-eacl)

Copied to clipboard

Challenge: Recent work shows that answer verification models can improve the state of the art in Question Answering . despite the fact that the supporting candidates are ranked only according to the relevancy with the question, the model still lacks the support needed for other answer candidates.
Approach: They propose a double reranking model that selects the best support for each target answer . they propose 'second neural retrieval stage' to encode question and answer pair as query .
Outcome: The proposed approach improves the state of the art in Question Answering . the proposed model ranked candidates according to relevancy and not the answer . but the proposed approach fails to provide the best support .
Retrieving Support to Rank Answers in Open-Domain Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: a novel question answering architecture retrieves content relevant to the combined pair . previous work on automatic claim verification has shown hallucinations .
Approach: They propose a question-answer architecture that prioritizes supporting evidence . it retrieves paragraphs that directly substantiate the correctness of a with respect to q .
Outcome: The proposed approach can be used by large language models to retrieve explanatory paragraphs that ground their reasoning.
RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering (2025.findings-naacl)

Copied to clipboard

Challenge: Existing ranking methods rely on small encoder-based ranking models, which are incompatible with modern decoder--based generative large language models (LLMs) Existing methods based on small LLaVA rankers are incompatible with advanced LLMs.
Approach: They propose a framework that combines learning-to-rank methods with generative permutation-enhanced ranking techniques.
Outcome: The proposed framework improves on two benchmarks, WebQA and MultiModalQA, showing significant improvements over baselines.
UQA: Corpus for Urdu Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Urdu is a low-resource language with over 70 million native speakers . expanding the reach of NLP to languages other than English is crucial for advancing multilingual AI systems.
Approach: They introduce a novel dataset for question answering and text comprehension in Urdu . they use a technique called EATS which preserves the answer spans in translated context paragraphs .
Outcome: The proposed dataset preserves answer spans in translated context paragraphs.
CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to answer open domain questions rely on unlabeled text or synthetically generated question-answer pairs.
Approach: They propose a large-scale open-domain question-answering dataset based on the Common Crawl project that can be used to in-domain pre-train popular language models.
Outcome: The proposed dataset achieves promising results in zero-shot, low resource and fine-tuned settings across multiple tasks, models and benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations