AIConfPaper
← Search

Kenny Zhu

15 accepted papers

2024

Mapping Long-term Causalities in Psychiatric Symptomatology and Life Events from Social Media

Siyuan Chen, Meilin Wang, Minghao Lv, Zhiling Zhang, Juqianqian Juqianqian, Dejiyangla Dejiyangla +3
NAACL 2024long

Social media is a valuable data source for exploring mental health issues. However, previous studies have predominantly focused on the semantic content of these posts, overlooking the importance of their temporal attributes, as well as the evolving nature of mental disorders and symptoms.In this pap…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

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

Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Zhu
ACL 2023long

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 rules or train models for scoring the difficulty highly rely on task-specific expertise, and cannot generalize. Inspired by…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

Incomplete Utterance Rewriting by A Two-Phase Locate-and-Fill Regime

Zitong Li, Jiawei Li, Haifeng Tang, Kenny Zhu, Ruolan Yang
ACL 2023findings

Rewriting incomplete and ambiguous utterances can improve dialogue models’ understanding of the context and help them generate better results. However, the existing end-to-end models will have the problem of too large search space, resulting in poor quality of rewriting results. We propose a 2-phase…

Cited by 4Source ↗PDF ↗Scholar ↗
2023

Pruning Pre-trained Language Models with Principled Importance and Self-regularization

Siyu Ren, Kenny Zhu
ACL 2023findings

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-constrained 0-1 Integer Linear Programming problem. The solution to this optimization problem leads to a principled importance cr…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Reducing Sensitivity on Speaker Names for Text Generation from Dialogues

Qi Jia, Haifeng Tang, Kenny Zhu
ACL 2023findings

Changing speaker names consistently throughout a dialogue should not affect its meaning and corresponding outputs for text generation from dialogues. However, pre-trained language models, serving as the backbone for dialogue-processing tasks, have shown to be sensitive to nuances. This may result in…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Transcribing Vocal Communications of Domestic Shiba lnu Dogs

Jieyi Huang, Chunhao Zhang, Mengyue Wu, Kenny Zhu
ACL 2023findings

How animals communicate and whether they have languages is a persistent curiosity of human beings. However, the study of animal communications has been largely restricted to data from field recordings or in a controlled environment, which is expensive and limited in scale and variety. In this paper,…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Transferable and Efficient: Unifying Dynamic Multi-Domain Product Categorization

Shansan Gong, Zelin Zhou, Shuo Wang, Fengjiao Chen, Xiujie Song, Xuezhi Cao +2
ACL 2023industry

As e-commerce platforms develop different business lines, a special but challenging product categorization scenario emerges, where there are multiple domain-specific category taxonomies and each of them evolves dynamically over time. In order to unify the categorization process and ensure efficiency…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2022

ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments

Ruolan Yang, Zitong Li, Haifeng Tang, Kenny Zhu
ACL 2022long

Existing automatic evaluation systems of chatbots mostly rely on static chat scripts as ground truth, which is hard to obtain, and requires access to the models of the bots as a form of “white-box testing”. Interactive evaluation mitigates this problem but requires human involvement. In our work, we…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2022

Length Control in Abstractive Summarization by Pretraining Information Selection

Yizhu Liu, Qi Jia, Kenny Zhu
ACL 2022long

Previous length-controllable summarization models mostly control lengths at the decoding stage, whereas the encoding or the selection of information from the source document is not sensitive to the designed length. They also tend to generate summaries as long as those in the training data. In this p…

Cited by 37Source ↗PDF ↗code ↗Scholar ↗
2022

Post-Training Dialogue Summarization using Pseudo-Paraphrasing

Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Zhu
NAACL 2022findings

Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models. These features either require additional knowledge to recognize or make the resulting models harder to tune. To bridge the format gap betwe…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Reference-free Summarization Evaluation via Semantic Correlation and Compression Ratio

Yizhu Liu, Qi Jia, Kenny Zhu
NAACL 2022long

A document can be summarized in a number of ways. Reference-based evaluation of summarization has been criticized for its inflexibility. The more sufficient the number of abstracts, the more accurate the evaluation results. However, it is difficult to collect sufficient reference summaries. In this…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2022

Specializing Pre-trained Language Models for Better Relational Reasoning via Network Pruning

Siyu Ren, Kenny Zhu
NAACL 2022findings

Pretrained masked language models (PLMs) were shown to be inheriting a considerable amount of relational knowledge from the source corpora. In this paper, we present an in-depth and comprehensive study concerning specializing PLMs into relational models from the perspective of network pruning. We sh…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2022

Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media

Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Zhu
EMNLP 2022main

Mental disease detection (MDD) from social media has suffered from poor generalizability and interpretability, due to lack of symptom modeling. This paper introduces PsySym, the first annotated symptom identification corpus of multiple psychiatric disorders, to facilitate further research progress.…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗