Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSparse, Dense, and Attentional Representations for Text Retrieval
تمثيلات متناثرة، كثيفة، ويهما عن استرجاع النص
381
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقوم المشفر المزدح المجرقة بإجراء استرجاع من خلال ترميز المستندات والاستعلامات في متجهات كثيفة منخفضة الأبعاد، حيث سجل كل وثيقة عن طريق المنتج الداخلي مع الاستعلام.نحن نبحث في قدرة هذه الهندسة المعمارية بالنسبة إلى نماذج كيس من الكلمات المتفرقة والشبكات العصبية الاهتمام.باستخدام كل من التحليلات النظرية والتجريبية، نقوم بإنشاء اتصالات بين بعد ترميز، الهامش بين الذهب والوثائق ذات المرتبة الأدنى، وطول الوثيقة، مما يشير إلى حد قيود في سعة الترميزات ذات الطول الثابت لدعم استرجاع الدقة الدقيقة للوثائق الطويلة.بناء على هذه الأفكار، نقترح نموذجا عصبا بسيطا يجمع بين كفاءة الترميز المزدوج مع بعض التعبير عن هياكل التعبير الأكثر تكلفة، واستكشاف الهجينة الكثيفة المتنارية للاستفادة من دقة الاسترجاع المتناقضة.تتفوق هذه النماذج بدائل قوية في استرجاع واسع النطاق.
Abstract Dual encoders perform retrieval by encoding documents and queries into dense low-dimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insights, we propose a simple neural model that combines the efficiency of dual encoders with some of the expressiveness of more costly attentional architectures, and explore sparse-dense hybrids to capitalize on the precision of sparse retrieval. These models outperform strong alternatives in large-scale retrieval.
References used
https://aclanthology.org/
rate research
Read More
The semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches. However, neural models' dense representations are more suitable for re-ranking, due to their inefficiency. Sparse
representations, either in symbolic or latent form, are more efficient with an inverted index. Taking the merits of the sparse and dense representations, we propose an ultra-high dimensional (UHD) representation scheme equipped with directly controllable sparsity. UHD's large capacity and minimal noise and interference among the dimensions allow for binarized representations, which are highly efficient for storage and search. Also proposed is a bucketing method, where the embeddings from multiple layers of BERT are selected/merged to represent diverse linguistic aspects. We test our models with MS MARCO and TREC CAR, showing that our models outperforms other sparse models.
Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Build
ing on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.
In Arabic Language, diacritics are used to specify meanings as well as pronunciations. However, diacritics are often omitted from written texts, which increases the number of possible meanings and pronunciations. This leads to an ambiguous text and m
akes the computational process on undiacritized text more difficult. In this paper, we propose a Linguistic Attentional Model for Arabic text Diacritization (LAMAD). In LAMAD, a new linguistic feature representation is presented, which utilizes both word and character contextual features. Then, a linguistic attention mechanism is proposed to capture the important linguistic features. In addition, we explore the impact of the linguistic features extracted from the text on Arabic text diacritization (ATD) by introducing them to the linguistic attention mechanism. The extensive experimental results on three datasets with different sizes illustrate that LAMAD outperforms the existing state-of-the-art models.
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.
A text retrieval system for language learning returns reading materials at the appropriate difficulty level for the user. The system typically maintains a learner model on the user's vocabulary knowledge, and identifies texts that best fit the model.
As the user's language proficiency increases, model updates are necessary to retrieve texts with the corresponding lexical complexity. We investigate an open learner model that allows user modification of its content, and evaluate its effectiveness with respect to the amount of user update effort. We compare this model with the graded approach, in which the system returns texts at the optimal grade. When the user makes at least half of the expected updates to the open learner model, simulation results show that it outperforms the graded approach in retrieving texts that fit user preference for new-word density.
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
