Challenge: lexical approaches to find passages have outperformed lexicals due to their superior performance . however, for some languages, such as Polish, few models are available . a recent study shows that neural retrievers are more efficient and efficient than lexica.
Approach: They present a neural retriever for Polish trained on a diverse collection of manual and weakly labeled datasets.
Outcome: The proposed model outperforms lexical retrieval models in Polish on three retrieval tasks.

Similar Papers

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.
Efficient Passage Retrieval with Hashing for Open-domain Question Answering (2021.acl-short)

Copied to clipboard

Challenge: Open-domain question answering systems often require large memory to run because of the massive size of their passage index.
Approach: They propose a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever to represent the passage index using compact binary codes.
Outcome: The proposed model significantly reduces memory cost from 65GB to 2GB without loss of accuracy on two open-domain question answering benchmarks.
SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval (2021.naacl-main)

Copied to clipboard

Challenge: SPARTA is a novel neural retrieval method for open-domain question answering . it learns a sparse representation that can be efficiently implemented as an Inverted Index .
Approach: They propose a method that learns a sparse representation that can be implemented as an Inverted Index.
Outcome: The proposed method achieves state-of-the-art results on 4 open-domain question answering tasks and 11 retrieval question answering (ReQA) tasks.
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering (N19-1)

Copied to clipboard

Challenge: Existing approaches to open-domain question answering struggle to retrieve indirectly related evidence when no direct evidence is provided.
Approach: They propose a retriever-reader model that learns to attend on essential terms during the question answering process.
Outcome: The proposed model achieves the state-of-the-art on multiple open-domain QA datasets and achieves a 'reader-reader' level.
Retrieval-based Question Answering with Passage Expansion Using a Knowledge Graph (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in dense neural retrievers and language models have hindered performance, especially for less common entities and facts.
Approach: They propose a multi-modal passage retrieval model that combines entity features and textual data to improve retrieval precision for less common entities.
Outcome: The proposed model improves retrieval precision on less common entities and facts on common benchmarks.
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.
Neural Retriever and Go Beyond: A Thesis Proposal (2022.naacl-srw)

Copied to clipboard

Challenge: Existing neural retrievers are developed for pure-text queries, which prevents them from handling multi-modality queries.
Approach: They propose methods to address issues of existing neural retrievers from three angles . they propose new model architectures, IR-oriented pretraining tasks and generating large scale training data .
Outcome: The proposed methods address the abovementioned issues of neural retrievers from three angles and generate large scale training data.
You Only Need One Model for Open-domain Question Answering (2022.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to Open-domain Question Answering use external knowledge bases, but have separate parameters and are weakly-coupled during training.
Approach: They propose to use a single question answering model trained end-to-end to retrieve external knowledge and rerank passages with a separate reranked model.
Outcome: The proposed model outperforms the previous state-of-the-art model by 1.0 and 0.7 exact match scores on the Natural Questions and TriviaQA open datasets.
PolQA: Polish Question Answering Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Recent proposed systems for open-domain question answering (OpenQA) require large amounts of training data to achieve state-of-the-art performance.
Approach: They propose an efficient annotation strategy that increases passage retrieval accuracy@10 by 10.55 p.p. while reducing the annotation cost by 82%.
Outcome: The proposed approach increases passage retrieval accuracy @10 by 10.55 p.p. while reducing the annotation cost by 82%.
Answering Complex Open-domain Questions Through Iterative Query Generation (D19-1)

Copied to clipboard

Challenge: Currently, one-step retrieve-and-read question answering systems cannot answer such questions because they rarely contain retrievable clues about the missing entity.
Approach: They propose a multi-step approach to retrieve relevant content with the question, then reading the paragraphs returned by the information retrieval component to arrive at the final answer.
Outcome: The proposed model outperforms the best previously published model despite not using pretrained language models such as BERT.

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