12 citations · 37 across the 13 of their papers we have counts for
12 papers · 1 filter
Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs
Shenglai Zeng, Tianqi Zheng, Chuan Tian +10
Personalizing large language models (LLMs) to individual users requires incorporating extensive interaction histories and profiles, but input token constraints make this impractica…
PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification
Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang +1
We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural…
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
Ruohong Zhang, Yau-Shian Wang, Yiming Yang
The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention. However, employing LLMs for large-scale inference…
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
Yau-Shian Wang, Ashley Wu, Graham Neubig
Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requi…
Toxicity Detection with Generative Prompt-based Inference
Yau-Shian Wang, Yingshan Chang
Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a lon…
Exploiting Local and Global Features in Transformer-based Extreme Multi-label Text Classification
Ruohong Zhang, Yau-Shian Wang, Yiming Yang +2
Extreme multi-label text classification (XMTC) is the task of tagging each document with the relevant labels from a very large space of predefined categories. Recently, large pre-t…
Are you doing what I say? On modalities alignment in ALFRED
Ting-Rui Chiang, Yi-Ting Yeh, Ta-Chung Chi +1
ALFRED is a recently proposed benchmark that requires a model to complete tasks in simulated house environments specified by instructions in natural language. We hypothesize that k…
Investigation of Sentiment Controllable Chatbot
Hung-yi Lee, Cheng-Hao Ho, Chien-Fu Lin +5
Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the outpu…
Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification
Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen
Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret…
Tree Transformer: Integrating Tree Structures into Self-Attention
Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen
Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the…
Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks
Yau-Shian Wang, Hung-Yi Lee
Auto-encoders compress input data into a latent-space representation and reconstruct the original data from the representation. This latent representation is not easily interpreted…
Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu +3
Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the outpu…