Search Results for author:
Found 13 papers, 4 papers with code
PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification
We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification.
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
To overcome these limitations, we introduce a novel method, namely GenCo, which leverages the strong generative power of LLMs to assist in training a smaller and more adaptable language model.
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
The performance can be further enhanced when cross-lingual NLI data is available.
Toxicity Detection with Generative Prompt-based Inference
It is a long-known risk that language models (LMs), once trained on corpus containing undesirable content, have the power to manifest biases and toxicity.
Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptions
Extreme Multi-label Text Classification (XMTC) has been a tough challenge in machine learning research and applications due to the sheer sizes of the label spaces and the severe data scarce problem associated with the long tail of rare labels in highly skewed distributions.
Multi Label Text Classification
Multi-Label Text Classification
+3
Exploiting Local and Global Features in Transformer-based Extreme Multi-label Text Classification
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.
Multi Label Text Classification
Multi-Label Text Classification
+1
Are you doing what I say? On modalities alignment in ALFRED
ALFRED is a recently proposed benchmark that requires a model to complete tasks in simulated house environments specified by instructions in natural language.
Investigation of Sentiment Controllable Chatbot
Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences.
Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification
Also, the performance is on par with a recently proposed weakly-supervised text classification method.
Tree Transformer: Integrating Tree Structures into Self-Attention
This paper proposes Tree Transformer, which adds an extra constraint to attention heads of the bidirectional Transformer encoder in order to encourage the attention heads to follow tree structures.
Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks
The generator encodes the input text into a shorter word sequence, and the reconstructor recovers the generator input from the generator output.
TopicGAN: Unsupervised Text Generation from Explainable Latent Topics
Learning discrete representations of data and then generating data from the discovered representations have been increasingly studied because the obtained discrete representations can benefit unsupervised learning.
Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis
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 output sentences.
