Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDealing with Typos for BERT-based Passage Retrieval and Ranking
التعامل مع الأخطاء المطبعية لاسترجاع المقطع المستند إلى بيرت
571
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
استرجاع المرور والترتيب هو مهمة رئيسية في الإجابة على الأسئلة المفتوحة واسترجاع المعلومات. تعتمد الأساليب الفعالة الحالية في الغالب على المستردين المعتمدين على النموذج العميق المدربين مسبقا. تم عرض هذه الأساليب نموذجا بفعالية المطابقة الدلالية بين الاستعلامات والمرورات، أيضا في وجود عدم تطابق الكلمات الرئيسية، أي الممرات ذات الصلة بالاستعلام ولكن لا تحتوي على كلمات رئيسية مهمة. في هذه الورقة، نعتبر المسترد الكثيف (DR) وطريقة استرجاع الممر، و Re-Ranker Reveer، وهي طريقة إعادة ترتيب الشعبية. في هذا السياق، نحقق رسميا كيفية استجابة هذه النماذج والتكيف مع نوع معين من عدم تطابق الكلمة الرئيسية - التي تحدث عن طريق الكلمة الأساسية التي تحدث في استفسارات. من خلال التحقيق التجريبي، نجد أن الأخطاء المطبعية يمكن أن تؤدي إلى انخفاض كبير في فعالية الاسترجاع والترتيب. بعد ذلك اقترحنا إطارا بسيطا للتدريب في الطباعة المطبعية عن DR و Bert Re-Ranker لمعالجة هذه المسألة. نظرا لنتائجنا التجريبية على مجموعة بيانات مرتبة مرور MS MARCO، بإظهار مجموعة بيانات MS MARCO، من خلال التدريب على الأخطاء المطبعية المقترحة، يمكن أن يصبح تدريب DR و Bert Re-Ranker قويا للمخططات المطبعية في الاستفسارات، مما يؤدي إلى تحسين فعالية محسنة بشكل كبير مقارنة بالنماذج المدربة دون محاسبة بشكل مناسب عن الأخطاء المطبعية.
Passage retrieval and ranking is a key task in open-domain question answering and information retrieval. Current effective approaches mostly rely on pre-trained deep language model-based retrievers and rankers. These methods have been shown to effectively model the semantic matching between queries and passages, also in presence of keyword mismatch, i.e. passages that are relevant to a query but do not contain important query keywords. In this paper we consider the Dense Retriever (DR), a passage retrieval method, and the BERT re-ranker, a popular passage re-ranking method. In this context, we formally investigate how these models respond and adapt to a specific type of keyword mismatch -- that caused by keyword typos occurring in queries. Through empirical investigation, we find that typos can lead to a significant drop in retrieval and ranking effectiveness. We then propose a simple typos-aware training framework for DR and BERT re-ranker to address this issue. Our experimental results on the MS MARCO passage ranking dataset show that, with our proposed typos-aware training, DR and BERT re-ranker can become robust to typos in queries, resulting in significantly improved effectiveness compared to models trained without appropriately accounting for typos.
References used
https://aclanthology.org/
rate research
Read More
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.
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a given question. This task requires joint modeling of retrieved passages, as models should not repeatedly retrieve pa
ssages containing the same answer at the cost of missing a different valid answer. Prior work focusing on single-answer retrieval is limited as it cannot reason about the set of passages jointly. In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. To model the joint probability of the retrieved passages, JPR makes use of an autoregressive reranker that selects a sequence of passages, equipped with novel training and decoding algorithms. Compared to prior approaches, JPR achieves significantly better answer coverage on three multi-answer datasets. When combined with downstream question answering, the improved retrieval enables larger answer generation models since they need to consider fewer passages, establishing a new state-of-the-art.
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.
One of the challenges in information retrieval (IR) is the vocabulary mismatch problem, which happens when the terms between queries and documents are lexically different but semantically similar. While recent work has proposed to expand the queries
or documents by enriching their representations with additional relevant terms to address this challenge, they usually require a large volume of query-document pairs to train an expansion model. In this paper, we propose an Unsupervised Document Expansion with Generation (UDEG) framework with a pre-trained language model, which generates diverse supplementary sentences for the original document without using labels on query-document pairs for training. For generating sentences, we further stochastically perturb their embeddings to generate more diverse sentences for document expansion. We validate our framework on two standard IR benchmark datasets. The results show that our framework significantly outperforms relevant expansion baselines for IR.
In quality estimation (QE), the quality of translation can be predicted by referencing the source sentence and the machine translation (MT) output without access to the reference sentence. However, there exists a paradox in that constructing a datase
t for creating a QE model requires non-trivial human labor and time, and it may even requires additional effort compared to the cost of constructing a parallel corpus. In this study, to address this paradox and utilize the various applications of QE, even in low-resource languages (LRLs), we propose a method for automatically constructing a pseudo-QE dataset without using human labor. We perform a comparative analysis on the pseudo-QE dataset using multilingual pre-trained language models. As we generate the pseudo dataset, we conduct experiments using various external machine translators as test sets to verify the accuracy of the results objectively. Also, the experimental results show that multilingual BART demonstrates the best performance, and we confirm the applicability of QE in LRLs using pseudo-QE dataset construction methods.
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
