Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
Rocketqa: نهج تدريب محسن لاسترجاع الممر الكثيف للنطاق المفتوح الإجابة
200
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في الإجابة على الأسئلة المفتوحة للنطاق، أصبح استرجاع المقطع الكثيف نموذجا جديدا لاسترداد الممرات ذات الصلة لإيجاد الإجابات. عادة ما يتم اعتماد بنية التشفير المزدوجة لتعلم تمثيلات كثيفة من الأسئلة والممرات للمطابقة الدلالية. ومع ذلك، من الصعب تدريب تشفير مزدوج بشكل فعال بسبب التحديات بما في ذلك التناقض بين التدريب والاستدلال، ووجود إيجابيات غير محدودة وبيانات تدريب محدودة. لمعالجة هذه التحديات، نقترح نهج تدريبي محسن، يسمى Rocketqa، لتحسين استرجاع الممر الكثيف. نجعل ثلاث مساهمات تقنية رئيسية في Rocketqa، وهي السلبيات عبر الدفعة، السلبيات الصلبة الشاقة وزعم البيانات. تظهر نتائج التجربة أن Rocketqa تتفوق بشكل كبير على النماذج السابقة من بين الفنادق السابقة على كل من MSMARCO والأسئلة الطبيعية. نقوم أيضا بإجراء تجارب مكثفة لفحص فعالية الاستراتيجيات الثلاث في Rocketqa. علاوة على ذلك، نوضح أن أداء ضمان الجودة المناسبة يمكن تحسينه بناء على مسترد Rocketqa لدينا.
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 semantic 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.
References used
https://aclanthology.org/
rate research
Read More
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.
In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly o
ptimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage reranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dynamic distillation, the retriever and the re-ranker can be adaptively improved according to each other's relevance information. We also propose a hybrid data augmentation strategy to construct diverse training instances for listwise training approach. Extensive experiments show the effectiveness of our approach on both MSMARCO and Natural Questions datasets. Our code is available at https://github.com/PaddlePaddle/RocketQA.
Dense retrieval has shown great success for passage ranking in English. However, its effectiveness for non-English languages remains unexplored due to limitation in training resources. In this work, we explore different transfer techniques for docume
nt ranking from English annotations to non-English languages. Our experiments reveal that zero-shot model-based transfer using mBERT improves search quality. We find that weakly-supervised target language transfer is competitive compared to generation-based target language transfer, which requires translation models.
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.
In the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of the retrieval system and ho
w they complement each other. We propose a multi-stage framework comprising of pre-training with synthetic data, fine-tuning with labeled data, and negative sampling at both stages. We study six negative sampling strategies and apply them to the fine-tuning stage and, as a noteworthy novelty, to the synthetic data that we use for pre-training. Also, we explore fusion methods that combine negatives from different strategies. We evaluate our system using two passage retrieval tasks for open-domain QA and using MS MARCO. Our experiments show that augmenting the negative contrast in both stages is effective to improve passage retrieval accuracy and, importantly, they also show that synthetic data generation and negative sampling have additive benefits. Moreover, using the fusion of different kinds allows us to reach performance that establishes a new state-of-the-art level in two of the tasks we evaluated.
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
