Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDense Hierarchical Retrieval for Open-domain Question Answering
استرجاع هرمي كثيف للنطاق المفتوح الإجابة
315
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
حققت استرجاع النص العصبي الكثيف نتائج واعدة حول السؤال المفتوح للنطاق الرد (QA)، حيث يتم استغلال تمثيلات كامنة للأسئلة والمراجيات للحصول على أقصى قدر من البحث الداخلي في عملية الاسترجاع. ومع ذلك، فإن المستردات الكثيفة الحالية تتطلب تقسيم المستندات إلى مقاطع قصيرة تحتوي عادة على سياق محلي جزئي ومحازي في بعض الأحيان، وتعتمد بشدة على عملية تقسيم. ونتيجة لذلك، قد تسفر عن تعويضات مخفية غير دقيقة ومضللة، مما تدهور نتيجة الاسترجاع النهائي. في هذا العمل، نقترح استرجاع هرمي هرمي كثيف (DHR)، وهو إطار هرمي يمكنه إنشاء تمثيلات كثيفة دقيقة من الممرات من خلال الاستفادة من كل من الدلالات الكبيرة في الوثيقة والدليل المجهري المحدد لكل مقطع. على وجه التحديد، يحدد المسترد على مستوى المستند أولا المستندات ذات الصلة، من بينها يتم استرداد المقاطع ذات الصلة من خلال المسترد لمستوى المقاطع. سيتم معايرة ترتيب الممرات المستردة من خلال دراسة أهمية مستوى الوثيقة. بالإضافة إلى ذلك، يتم التحقيق في هيكل العنوان الهرمي واستراتيجيات أخذ العينات السلبية (I.E.، في السلبيات في السلبيات) في السلبيات). نطبق DHR إلى مجموعات بيانات QA مفتوحة على نطاق واسع. تتفوق DHR بشكل كبير على استرداد المقطع الكثيف الأصلي، ويساعد نظام ضمان الجودة في نهاية إلى نهاية يتفوق على الأساس القوي على معايير QA متعددة النطاق.
Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However, current dense retrievers require splitting documents into short passages that usually contain local, partial and sometimes biased context, and highly depend on the splitting process. As a consequence, it may yield inaccurate and misleading hidden representations, thus deteriorating the final retrieval result. In this work, we propose Dense Hierarchical Retrieval (DHR), a hierarchical framework which can generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage. Specifically, a document-level retriever first identifies relevant documents, among which relevant passages are then retrieved by a passage-level retriever. The ranking of the retrieved passages will be further calibrated by examining the document-level relevance. In addition, hierarchical title structure and two negative sampling strategies (i.e., In-Doc and In-Sec negatives) are investigated. We apply DHR to large-scale open-domain QA datasets. DHR significantly outperforms the original dense passage retriever, and helps an end-to-end QA system outperform the strong baselines on multiple open-domain QA benchmarks.
References used
https://aclanthology.org/
rate research
Read More
In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and passages for s
emantic matching. However, it is difficult to effectively train a dual-encoder due to the challenges including the discrepancy between training and inference, the existence of unlabeled positives and limited training data. To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. We make three major technical contributions in RocketQA, namely cross-batch negatives, denoised hard negatives and data augmentation. The experiment results show that RocketQA significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions. We also conduct extensive experiments to examine the effectiveness of the three strategies in RocketQA. Besides, we demonstrate that the performance of end-to-end QA can be improved based on our RocketQA retriever.
Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages. In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a
retriever designed to handle tabular context. We present an effective pre-training procedure for our retriever and improve retrieval quality with mined hard negatives. As relevant datasets are missing, we extract a subset of Natural Questions (Kwiatkowski et al., 2019) into a Table QA dataset. We find that our retriever improves retrieval results from 72.0 to 81.1 recall@10 and end-to-end QA results from 33.8 to 37.7 exact match, over a BERT based retriever.
We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. Unlike many neural ranking methods that use dense vector nearest neighbor search, S
PARTA learns a sparse representation that can be efficiently implemented as an Inverted Index. The resulting representation enables scalable neural retrieval that does not require expensive approximate vector search and leads to better performance than its dense counterpart. We validated our approaches on 4 open-domain question answering (OpenQA) tasks and 11 retrieval question answering (ReQA) tasks. SPARTA achieves new state-of-the-art results across a variety of open-domain question answering tasks in both English and Chinese datasets, including open SQuAD, CMRC and etc. Analysis also confirms that the proposed method creates human interpretable representation and allows flexible control over the trade-off between performance and efficiency.
Abstract Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open- domain question answering evaluation set comprising 10k question-an
swer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). Answers are based on heavily curated, language- independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evaluating question answering. We benchmark a variety of state- of-the-art methods and baselines for generative and extractive question answering, trained on Natural Questions, in zero shot and translation settings. Results indicate this dataset is challenging even in English, but especially in low-resource languages.1
Open-domain question answering aims at locating the answers to user-generated questions in massive collections of documents. Retriever-readers and knowledge graph approaches are two big families of solutions to this task. A retriever-reader first app
lies information retrieval techniques to locate a few passages that are likely to be relevant, and then feeds the retrieved text to a neural network reader to extract the answer. Alternatively, knowledge graphs can be constructed and queried to answer users' questions. We propose an algorithm with a novel reader-retriever design that differs from both families. Our reader-retriever first uses an offline reader to read the corpus and generate collections of all answerable questions associated with their answers, and then uses an online retriever to respond to user queries by searching the pre-constructed question spaces for answers that are most likely to be asked in the given way. We further combine one retriever-reader and two reader-retrievers into a hybrid model called R6 for the best performance. Experiments with two large-scale public datasets show that R6 achieves state-of-the-art accuracy.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
