On the Hidden Negative Transfer in Sequential Transfer Learning for Domain Adaptation from News to Tweets
Transfer Learning has been shown to be a powerful tool for Natural Language Processing (NLP) and has outperformed the standard supervised learning paradigm, as it takes benefit from the pre-learned knowledge. Nevertheless, when transfer is performed between less related domains, it brings a negative transfer, i.e. hurts the transfer performance. In this research, we shed light on the hidden negative transfer occurring when transferring from the News domain to the Tweets domain, through quantitative and qualitative analysis. Our experiments on three NLP taks: Part-Of-Speech tagging, Chunking and Named Entity recognition, reveal interesting insights.
Code (0)
등록된 구현이 없습니다.
Tasks
ChunkingDomain Adaptationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech TaggingTransfer LearningSimilar Papers 제목 키워드 기반
Cracking the Code of Negative Transfer: A Cooperative Game Theoretic Approach for Cross-Domain Sequential Recommendation
This paper investigates Cross-Domain Sequential Recommendation (CDSR), a promising method that uses information from multiple domains (more than three) to generate accurate and diverse recommendations, and takes into acc…
Contrastive LearningSequential RecommendationPacer and Runner: Cooperative Learning Framework between Single- and Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) improves recommendation performance by utilizing information from multiple domains, which contrasts with Single-Domain Sequential Recommendation (SDSR) that relies on a histo…
Sequential RecommendationBeyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across domains to enhance recommendation quality. However, naive aggregation of sequential signals can introduce conflicting domain-specific preferen…
Sequential RecommendationCollaborative FilteringGRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning
Multi-source transfer learning faces a fundamental scalability bottleneck: existing approaches require either loading all K source models into memory simultaneously during parameter fusion, requiring O(K) memory, or depl…
Continual LearningTransfer LearningLearning Vector-Quantized Item Representation for Transferable Sequential Recommenders
Recently, the generality of natural language text has been leveraged to develop transferable recommender systems. The basic idea is to employ pre-trained language models~(PLM) to encode item text into item representation…
Language ModellingRecommendation Systemstext similarity