17 citations · 105 across the 32 of their papers we have counts for
21 papers · 1 filter
Low-Rank Prune-And-Factorize for Language Model Compression
Siyu Ren, Kenny Q. Zhu
The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy. Matrix factorization, a well-established technique from matrix theory, has…
Pruning Pre-trained Language Models with Principled Importance and Self-regularization
Siyu Ren, Kenny Q. Zhu
Iterative pruning is one of the most effective compression methods for pre-trained language models. We discovered that finding the optimal pruning decision is an equality-constrain…
Reducing Sensitivity on Speaker Names for Text Generation from Dialogues
Qi Jia, Haifeng Tang, Kenny Q. Zhu
Changing speaker names consistently throughout a dialogue should not affect its meaning and corresponding outputs for text generation from dialogues. However, pre-trained language…
In-sample Curriculum Learning by Sequence Completion for Natural Language Generation
Qi Jia, Yizhu Liu, Haifeng Tang +1
Curriculum learning has shown promising improvements in multiple domains by training machine learning models from easy samples to hard ones. Previous works which either design rule…
Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions
Qi Jia, Yizhu Liu, Siyu Ren +1
Abstractive dialogue summarization is to generate a concise and fluent summary covering the salient information in a dialogue among two or more interlocutors. It has attracted grea…
Few-Shot Natural Language Inference Generation with PDD: Prompt and Dynamic Demonstration
Kaijian Li, Shansan Gong, Kenny Q. Zhu
Natural Language Inference Generation task is to generate a text hypothesis given a text premise and a logical relation between the two. This task can be used in data augmentation…
Post-Training Dialogue Summarization using Pseudo-Paraphrasing
Qi Jia, Yizhu Liu, Haifeng Tang +1
Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models. These features eith…
Modeling Multi-level Context for Informational Bias Detection by Contrastive Learning and Sentential Graph Network
Shijia Guo, Kenny Q. Zhu
Informational bias is widely present in news articles. It refers to providing one-sided, selective or suggestive information of specific aspects of certain entity to guide a specif…
Diverse and Specific Clarification Question Generation with Keywords
Zhiling Zhang, Kenny Q. Zhu
Product descriptions on e-commerce websites often suffer from missing important aspects. Clarification question generation (CQGen) can be a promising approach to help alleviate the…
Statistically Profiling Biases in Natural Language Reasoning Datasets and Models
Shanshan Huang, Kenny Q. Zhu
Recent work has indicated that many natural language understanding and reasoning datasets contain statistical cues that may be taken advantaged of by NLP models whose capability ma…
DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialogues
Qi Jia, Hongru Huang, Kenny Q. Zhu
Interpersonal language style shifting in dialogues is an interesting and almost instinctive ability of human. Understanding interpersonal relationship from language content is also…
Multi-turn Response Selection using Dialogue Dependency Relations
Qi Jia, Yizhu Liu, Siyu Ren +2
Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models. However…
Matching Questions and Answers in Dialogues from Online Forums
Qi Jia, Mengxue Zhang, Shengyao Zhang +1
Matching question-answer relations between two turns in conversations is not only the first step in analyzing dialogue structures, but also valuable for training dialogue systems.…
ST: Small-data Text Style Transfer via Multi-task Meta-Learning
Xiwen Chen, Kenny Q. Zhu
Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsuperv…
MICK: A Meta-Learning Framework for Few-shot Relation Classification with Small Training Data
Xiaoqing Geng, Xiwen Chen, Kenny Q. Zhu +2
Few-shot relation classification seeks to classify incoming query instances after meeting only few support instances. This ability is gained by training with large amount of in-dom…
Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions
Siyu Ren, Kenny Q. Zhu
In this paper, we propose a novel configurable framework to automatically generate distractive choices for open-domain cloze-style multiple-choice questions, which incorporates a g…
Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
Zuyi Bao, Rui Huang, Chen Li +1
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching. Such requirements and assumptions ar…
Representing Verbs as Argument Concepts
Yu Gong, Kaiqi Zhao, Kenny Q. Zhu
Verbs play an important role in the understanding of natural language text. This paper studies the problem of abstracting the subject and object arguments of a verb into a set of n…
Automatic Generation of Chinese Short Product Titles for Mobile Display
Yu Gong, Xusheng Luo, Kenny Q. Zhu +3
This paper studies the problem of automatically extracting a short title from a manually written longer description of E-commerce products for display on mobile devices. It is a ne…
Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant
Yu Gong, Xusheng Luo, Yu Zhu +6
Slot filling is a critical task in natural language understanding (NLU) for dialog systems. State-of-the-art approaches treat it as a sequence labeling problem and adopt such model…
Automatic Extraction of Commonsense LocatedNear Knowledge
Frank F. Xu, Bill Yuchen Lin, Kenny Q. Zhu
LocatedNear relation is a kind of commonsense knowledge describing two physical objects that are typically found near each other in real life. In this paper, we study how to automa…