984 citations · 1.3k across the 27 of their papers we have counts for
27 papers
Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge Distillation
Huachuan Qiu, Shuai Zhang, Hongliang He +2
NSFW (Not Safe for Work) content, in the context of a dialogue, can have severe side effects on users in open-domain dialogue systems. However, research on detecting NSFW language,…
Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models
Huachuan Qiu, Shuai Zhang, Anqi Li +2
Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensiti…
A Benchmark for Understanding Dialogue Safety in Mental Health Support
Huachuan Qiu, Tong Zhao, Anqi Li +3
Dialogue safety remains a pervasive challenge in open-domain human-machine interaction. Existing approaches propose distinctive dialogue safety taxonomies and datasets for detectin…
SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark
Liang Xu, Anqi Li, Lei Zhu +7
Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' perform…
Understanding Client Reactions in Online Mental Health Counseling
Anqi Li, Lizhi Ma, Yaling Mei +4
Communication success relies heavily on reading participants' reactions. Such feedback is especially important for mental health counselors, who must carefully consider the client'…
Enhancing Grammatical Error Correction Systems with Explanations
Yuejiao Fei, Leyang Cui, Sen Yang +3
Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system mak…
Instance Smoothed Contrastive Learning for Unsupervised Sentence Embedding
Hongliang He, Junlei Zhang, Zhenzhong Lan +1
Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous stud…
Contrastive Learning of Sentence Embeddings from Scratch
Junlei Zhang, Zhenzhong Lan, Junxian He
Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the us…
SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support
Huachuan Qiu, Hongliang He, Shuai Zhang +2
Developing specialized dialogue systems for mental health support requires multi-turn conversation data, which has recently garnered increasing attention. However, gathering and re…
Towards Automated Real-time Evaluation in Text-based Counseling
Anqi Li, Jingsong Ma, Lizhi Ma +3
Automated real-time evaluation of counselor-client interaction is important for ensuring quality counseling but the rules are difficult to articulate. Recent advancements in machin…
Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems
Chiyu Song, Hongliang He, Haofei Yu +3
Sample-and-rank is a key decoding strategy for modern generation-based dialogue systems. It helps achieve diverse and high-quality responses by selecting an answer from a small poo…
Memformer: A Memory-Augmented Transformer for Sequence Modeling
Qingyang Wu, Zhenzhong Lan, Kun Qian +3
Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as…
Attention that does not Explain Away
Nan Ding, Xinjie Fan, Zhenzhong Lan +2
Models based on the Transformer architecture have achieved better accuracy than the ones based on competing architectures for a large set of tasks. A unique feature of the Transfor…
Multi-stage Pretraining for Abstractive Summarization
Sebastian Goodman, Zhenzhong Lan, Radu Soricut
Neural models for abstractive summarization tend to achieve the best performance in the presence of highly specialized, summarization specific modeling add-ons such as pointer-gene…
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Zhenzhong Lan, Mingda Chen, Sebastian Goodman +3
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases be…
Video Representation Learning and Latent Concept Mining for Large-scale Multi-label Video Classification
Po-Yao Huang, Ye Yuan, Zhenzhong Lan +2
We report on CMU Informedia Lab's system used in Google's YouTube 8 Million Video Understanding Challenge. In this multi-label video classification task, our pipeline achieved 84.6…
Hidden Two-Stream Convolutional Networks for Action Recognition
Yi Zhu, Zhenzhong Lan, Shawn Newsam +1
Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical f…
Guided Optical Flow Learning
Yi Zhu, Zhenzhong Lan, Shawn Newsam +1
We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior p…
Deep Local Video Feature for Action Recognition
Zhenzhong Lan, Yi Zhu, Alexander G. Hauptmann
We investigate the problem of representing an entire video using CNN features for human action recognition. Currently, limited by GPU memory, we have not been able to feed a whole…
Improving Human Activity Recognition Through Ranking and Re-ranking
Zhenzhong Lan, Shoou-I Yu, Alexander G. Hauptmann
We propose two well-motivated ranking-based methods to enhance the performance of current state-of-the-art human activity recognition systems. First, as an improvement over the cla…
Handcrafted Local Features are Convolutional Neural Networks
Zhenzhong Lan, Shoou-I Yu, Ming Lin +2
Image and video classification research has made great progress through the development of handcrafted local features and learning based features. These two architectures were prop…
Beyond Spatial Pyramid Matching: Space-time Extended Descriptor for Action Recognition
Zhenzhong Lan, Alexander G. Hauptmann
We address the problem of generating video features for action recognition. The spatial pyramid and its variants have been very popular feature models due to their success in balan…
The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition
Zhenzhong Lan, Dezhong Yao, Ming Lin +2
Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents…
Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation
Zhiyong Cheng, Daniel Soudry, Zexi Mao +1
Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demon…