Search Results for author:
Found 10 papers, 3 papers with code
Multi-Scenario Ranking with Adaptive Feature Learning
Recently, Multi-Scenario Learning (MSL) is widely used in recommendation and retrieval systems in the industry because it facilitates transfer learning from different scenarios, mitigating data sparsity and reducing maintenance cost.
CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation
Micro-video recommender systems suffer from the ubiquitous noises in users' behaviors, which might render the learned user representation indiscriminating, and lead to trivial recommendations (e. g., popular items) or even weird ones that are far beyond users' interests.
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.
Subcharacter Information in Japanese Embeddings: When Is It Worth It?
Languages with logographic writing systems present a difficulty for traditional character-level models.
Subword-level Composition Functions for Learning Word Embeddings
Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries.
Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings
The number of word embedding models is growing every year.
Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics
The existing word representation methods mostly limit their information source to word co-occurrence statistics.
The (too Many) Problems of Analogical Reasoning with Word Vectors
This paper explores the possibilities of analogical reasoning with vector space models.
Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification
We train n-gram embeddings and use NB weighting to guide the neural models to focus on important words.
Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews
Many document embeddings methods have been proposed to capture semantics, but they still can't outperform bag-of-ngram based methods on this task.
