Search Results for author: Kenny Q. Zhu

Found 36 papers, 18 papers with code

Low-Rank Prune-And-Factorize for Language Model Compression

no code implementations25 Jun 2023 Siyu Ren, Kenny Q. Zhu

The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy.

Language Modelling Model Compression +2

LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation

no code implementations23 May 2023 Siyuan Chen, Mengyue Wu, Kenny Q. Zhu, Kunyao Lan, Zhiling Zhang, Lyuchun Cui

Empowering chatbots in the field of mental health is receiving increasing amount of attention, while there still lacks exploration in developing and evaluating chatbots in psychiatric outpatient scenarios.


Reducing Sensitivity on Speaker Names for Text Generation from Dialogues

no code implementations23 May 2023 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.

Text Generation

Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation

1 code implementation4 May 2023 Zhiling Zhang, Mengyue Wu, Kenny Q. Zhu

Controlling chatbot utterance generation with multiple attributes such as personalities, emotions and dialogue acts is a practically useful but under-studied problem.

Dialogue Generation

In-sample Curriculum Learning by Sequence Completion for Natural Language Generation

1 code implementation21 Nov 2022 Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Q. Zhu

Curriculum learning has shown promising improvements in multiple domains by training machine learning models from easy samples to hard ones.

Text Generation

Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions

no code implementations18 Oct 2022 Qi Jia, Yizhu Liu, Siyu Ren, Kenny Q. Zhu

Abstractive dialogue summarization is to generate a concise and fluent summary covering the salient information in a dialogue among two or more interlocutors.

Abstractive Dialogue Summarization Document Summarization

Symptom Identification for Interpretable Detection of Multiple Mental Disorders

no code implementations23 May 2022 Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Q. Zhu

Mental disease detection (MDD) from social media has suffered from poor generalizability and interpretability, due to lack of symptom modeling.

Few-Shot Natural Language Inference Generation with PDD: Prompt and Dynamic Demonstration

no code implementations21 May 2022 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.

Data Augmentation Natural Language Inference +1

Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression

1 code implementation19 May 2022 Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Q. Zhu

Depression is a prominent health challenge to the world, and early risk detection (ERD) of depression from online posts can be a promising technique for combating the threat.

Depression Detection

Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation

1 code implementation12 May 2022 Shansan Gong, Kenny Q. Zhu

News recommendation for anonymous readers is a useful but challenging task for many news portals, where interactions between readers and articles are limited within a temporary login session.

News Recommendation Session-Based Recommendations

Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval

1 code implementation NAACL 2022 Siyu Ren, Kenny Q. Zhu

Current text-image approaches (e. g., CLIP) typically adopt dual-encoder architecture us- ing pre-trained vision-language representation.

Image Retrieval Model Compression +1

Post-Training Dialogue Summarization using Pseudo-Paraphrasing

1 code implementation Findings (NAACL) 2022 Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Q. Zhu

Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models.

Diverse and Specific Clarification Question Generation with Keywords

1 code implementation21 Apr 2021 Zhiling Zhang, Kenny Q. Zhu

Due to the variety of possible user backgrounds and use cases, the information need can be quite diverse but also specific to a detailed topic, while previous works assume generating one CQ per context and the results tend to be generic.

Question Generation Question-Generation +1

Statistically Profiling Biases in Natural Language Reasoning Datasets and Models

no code implementations9 Feb 2021 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 may thus be grossly overestimated.

Multiple-choice Natural Language Understanding

Multi-turn Response Selection using Dialogue Dependency Relations

1 code implementation EMNLP 2020 Qi Jia, Yizhu Liu, Siyu Ren, Kenny Q. Zhu, Haifeng Tang

In this paper, we propose a dialogue extraction algorithm to transform a dialogue history into threads based on their dependency relations.

Matching Questions and Answers in Dialogues from Online Forums

1 code implementation19 May 2020 Qi Jia, Mengxue Zhang, Shengyao Zhang, Kenny Q. Zhu

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.

MICK: A Meta-Learning Framework for Few-shot Relation Classification with Small Training Data

no code implementations26 Apr 2020 Xiaoqing Geng, Xiwen Chen, Kenny Q. Zhu, Libin Shen, Yinggong Zhao

In this framework, models not only strive to classify query instances, but also seek underlying knowledge about the support instances to obtain better instance representations.

Classification Few-Shot Relation Classification +1

ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning

no code implementations24 Apr 2020 Xiwen Chen, Kenny Q. Zhu

Text style transfer aims to paraphrase a sentence in one style into another style while preserving content.

Meta-Learning Small Data Image Classification +2

Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions

no code implementations21 Apr 2020 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 general-purpose knowledge base to effectively create a small distractor candidate set, and a feature-rich learning-to-rank model to select distractors that are both plausible and reliable.

Distractor Generation Learning-To-Rank +1

Unpack Local Model Interpretation for GBDT

no code implementations3 Apr 2020 Wenjing Fang, Jun Zhou, Xiaolong Li, Kenny Q. Zhu

Besides the commonly used feature importance as a global interpretation, feature contribution is a local measure that reveals the relationship between a specific instance and the related output.

Feature Importance

AliCoCo: Alibaba E-commerce Cognitive Concept Net

no code implementations30 Mar 2020 Xusheng Luo, Luxin Liu, Yonghua Yang, Le Bo, Yuanpeng Cao, Jinhang Wu, Qiang Li, Keping Yang, Kenny Q. Zhu

However, user needs in e-commerce are still not well defined, and none of the existing ontologies has the enough depth and breadth for universal user needs understanding.

Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations

1 code implementation IJCNLP 2019 Zuyi Bao, Rui Huang, Chen Li, Kenny Q. Zhu

Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching.

Language Modelling NER +1

Conceptualize and Infer User Needs in E-commerce

1 code implementation8 Oct 2019 Xusheng Luo, Yonghua Yang, Kenny Q. Zhu, Yu Gong, Keping Yang

Understanding latent user needs beneath shopping behaviors is critical to e-commercial applications.

Automatic Generation of Text Descriptive Comments for Code Blocks

no code implementations21 Aug 2018 Yuding Liang, Kenny Q. Zhu

We propose a framework to automatically generate descriptive comments for source code blocks.


Automatic Generation of Chinese Short Product Titles for Mobile Display

1 code implementation30 Mar 2018 Yu Gong, Xusheng Luo, Kenny Q. Zhu, Wenwu Ou, Zhao Li, Lu Duan

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.

Extractive Summarization

Representing Verbs as Argument Concepts

no code implementations2 Mar 2018 Yu Gong, Kaiqi Zhao, Kenny Q. Zhu

Verbs play an important role in the understanding of natural language text.

Automatic Extraction of Commonsense LocatedNear Knowledge

1 code implementation ACL 2018 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.

Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation

no code implementations COLING 2016 Shi Feng, Shujie Liu, Nan Yang, Mu Li, Ming Zhou, Kenny Q. Zhu

In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence.

Machine Translation Translation

Data-Driven Metaphor Recognition and Explanation

no code implementations TACL 2013 Hongsong Li, Kenny Q. Zhu, Haixun Wang

Recognizing metaphors and identifying the source-target mappings is an important task as metaphorical text poses a big challenge for machine reading.

Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.