Dual Encoder
Related Papers
Large-Scale Representation Learning from Visually Grounded Untranscribed Speech
AbstractSystems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for …...
Learning Dense Representations for Entity Retrieval
AbstractWe show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate …...
Entity Linking in 100 Languages
AbstractWe propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior …...
Cross-lingual Sentence Embedding using Multi-Task Learning
AbstractMultilingual sentence embeddings capture rich semantic information not only for measuring similarity between texts but also for catering to a broad range of downstream cross-lingual NLP tasks. State-of-the-art multilingual sentence …...
Multi-Vector Attention Models for Deep Re-ranking
AbstractLarge-scale document retrieval systems often utilize two styles of neural network models which live at two different ends of the joint computation vs. accuracy spectrum. The first style is dual …...
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations
AbstractEntity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing. Recent progress in entity retrieval shows that the …...
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
AbstractIn 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 …...
Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model
AbstractAspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources …...
Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization
AbstractEfficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or L2-distance, there already exist many …...
IIT Bombay’s WMT22 Automatic Post-Editing Shared Task Submission
AbstractThis paper describes IIT Bombay’s submission to the WMT22 Automatic Post-Editing (APE) shared task for the English-Marathi (En-Mr) language pair. We follow the curriculum training strategy to train our APE …...
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval
AbstractCurrent text-image approaches (e.g., CLIP) typically adopt dual-encoder architecture using pre-trained vision-language representation. However, these models still pose non-trivial memory requirements and substantial incremental indexing time, which makes them less …...
HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification
AbstractHierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure. Existing dual-encoder methods in HTC achieve weak performance gains with huge …...