58 citations · 114 across the 15 of their papers we have counts for
15 papers
C-PMI: Conditional Pointwise Mutual Information for Turn-level Dialogue Evaluation
Liliang Ren, Mankeerat Sidhu, Qi Zeng +3
Existing reference-free turn-level evaluation metrics for chatbots inadequately capture the interaction between the user and the system. Consequently, they often correlate poorly w…
Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization
Hou Pong Chan, Qi Zeng, Heng Ji
Existing factual consistency evaluation approaches for text summarization provide binary predictions and limited insights into the weakness of summarization systems. Therefore, we…
Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation
Qi Zeng, Mankeerat Sidhu, Ansel Blume +3
Opinions in scientific research papers can be divergent, leading to controversies among reviewers. However, most existing datasets for opinion summarization are centered around pro…
EAE: Improving Consistency with Event Awareness for Document-Level Argument Extraction
Qi Zeng, Qiusi Zhan, Heng Ji
Events are inter-related in documents. Motivated by the one-sense-per-discourse theory, we hypothesize that a participant tends to play consistent roles across multiple events in t…
Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
Yinglun Xu, Qi Zeng, Gagandeep Singh
We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the e…
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Yifan Chen, Qi Zeng, Dilek Hakkani-Tur +3
Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules. To address this limitation, Li…
Skyformer: Remodel Self-Attention with Gaussian Kernel and Nyström Method
Yifan Chen, Qi Zeng, Heng Ji +1
Transformers are expensive to train due to the quadratic time and space complexity in the self-attention mechanism. On the other hand, although kernel machines suffer from the same…
ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
Qingyun Wang, Qi Zeng, Lifu Huang +3
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful compar…
Cross-media Structured Common Space for Multimedia Event Extraction
Manling Li, Alireza Zareian, Qi Zeng +4
We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents. We develop the first benchmark and collect…
Text Assisted Insight Ranking Using Context-Aware Memory Network
Qi Zeng, Liangchen Luo, Wenhao Huang +1
Extracting valuable facts or informative summaries from multi-dimensional tables, i.e. insight mining, is an important task in data analysis and business intelligence. However, ran…
Learning Personalized End-to-End Goal-Oriented Dialog
Liangchen Luo, Wenhao Huang, Qi Zeng +2
Most existing works on dialog systems only consider conversation content while neglecting the personality of the user the bot is interacting with, which begets several unsolved iss…
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
Liangchen Luo, Jingjing Xu, Junyang Lin +2
Generating semantically coherent responses is still a major challenge in dialogue generation. Different from conventional text generation tasks, the mapping between inputs and resp…
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
Jingjing Xu, Xuancheng Ren, Yi Zhang +3
Narrative story generation is a challenging problem because it demands the generated sentences with tight semantic connections, which has not been well studied by most existing gen…
Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations
Guangxiang Zhao, Jingjing Xu, Qi Zeng +1
This paper explores a new natural language processing task, review-driven multi-label music style classification. This task requires the system to identify multiple styles of music…
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
Jingjing Xu, Xu Sun, Qi Zeng +4
The goal of sentiment-to-sentiment "translation" is to change the underlying sentiment of a sentence while keeping its content. The main challenge is the lack of parallel data. To…