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.

Similar Papers

XQA: A Cross-lingual Open-domain Question Answering Dataset (P19-1)

Copied to clipboard

Challenge: Open-domain question answering aims to answer questions through text retrieval and reading comprehension . but, the success of these models relies on a massive volume of training data, which is not available in other languages . a new dataset aims at investigating cross-lingual OpenQA .
Approach: They propose to use a dataset for cross-lingual OpenQA research to test models . they use XQA dataset to train models with large volumes of labeled data .
Outcome: The proposed model achieves best results in almost all target languages while the performance is lower than that of English.
PerCQA: Persian Community Question Answering Dataset (2022.lrec-1)

Copied to clipboard

Challenge: Community Question Answering (CQA) forums provide answers to many real-life questions.
Approach: They propose to make Persian dataset PerCQA public to encourage more research in Persian CQA.
Outcome: The proposed dataset contains 989 questions and 21,915 annotated answers from the most well-known Persian forum.
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.
Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision (2024.emnlp-main)

Copied to clipboard

Challenge: Cross-lingual open domain question answering requires multiple models, requiring substantial annotated datasets and auxiliary resources to bridge between languages.
Approach: They propose a selfsupervised method that exploits Wikipedia's cross-lingual link structure . they show that the method outperforms comparable methods on supervised and zero-shot settings .
Outcome: The proposed method outperforms comparable methods on supervised and zero-shot language adaptation settings.
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering (2021.tacl-1)

Copied to clipboard

Challenge: Existing multilingual QA datasets lack linguistic diversity and comparable evaluation between languages.
Approach: They propose a multilingual question-answer evaluation set with 10k English queries and human translations of them into 25 additional languages and dialects.
Outcome: The proposed model is based on a multilingual knowledge questions and answers evaluation set with 26 languages.
CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data (2020.lrec-1)

Copied to clipboard

Challenge: Pre-training text representations have led to significant improvements in many areas of natural language processing.
Approach: They propose a pipeline to extract monolingual datasets from Common Crawl . pipeline follows data processing introduced in fastText that deduplicates documents .
Outcome: The proposed pipeline performs standard document deduplication and language identification similar to the pipeline introduced in fastText and a filtering step to select documents close to high quality corpora like Wikipedia.
A Multi-Domain Framework for Textual Similarity. A Case Study on Question-to-Question and Question-Answering Similarity Tasks (L18-1)

Copied to clipboard

Challenge: Community Question Answering websites are becoming popular and useful source of information for users.
Approach: They propose to use community question answering forum to detect similar questions . they use question-answering similarity task to provide correct answers .
Outcome: The proposed framework provides the first framework on the evaluation of similar questions and question-answering detection on a multi-domain corpora.
A Flexible, Efficient and Accurate Framework for Community Question Answering Pipelines (P18-4)

Copied to clipboard

Challenge: Community Question Answering is a research area that benefits from deep linguistic analysis . previous cQA challenges have shown that neural approaches are not enough to deliver state-of-the-art results .
Approach: They propose a framework to distribute computation of cQA tasks over computer clusters . community question answering is a research area that benefits from deep linguistic analysis .
Outcome: The proposed framework scales to large datasets and delivers fast processing.
ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to code question answering use bi-modal and unimodal pretraining to align text and code representations.
Approach: They propose a modality-agnostic contrastive pre-training approach to improve alignment of text and code representations of current code language models.
Outcome: The proposed model exhibits significant performance improvements across a wide range of code retrieval benchmarks.
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Existing KBQA methods focus on the natural language but ignore textual information carried by the nodes and edges.
Approach: They propose to perform relation extraction, relation matching, and relation reasoning tasks to align the natural language expressions to the relations in the KB and reason over the missing connections.
Outcome: Experiments on WebQSP show that the proposed model outperforms baselines even when the KB is incomplete.

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