no code implementations • 29 Jan 2025 • Duy A. Nguyen, Rishi Kesav Mohan, Van Yang, Pritom Saha Akash, Kevin Chen-Chuan Chang
Query rewriting (QR) is a critical technique in e-commerce search, addressing the lexical gap between user queries and product descriptions to enhance search performance.
no code implementations • 12 Nov 2024 • Youan Cong, Cheng Wang, Pritom Saha Akash, Kevin Chen-Chuan Chang
We introduce the Extract-Refine-Retrieve-Read (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the specific knowledge requirements of Large Language Models (LLMs).
no code implementations • 20 Oct 2024 • Kashob Kumar Roy, Pritom Saha Akash, Kevin Chen-Chuan Chang, Lucian Popa
Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth.
no code implementations • 4 Oct 2024 • Pritom Saha Akash, Kevin Chen-Chuan Chang
Topic modeling is a powerful technique for uncovering hidden themes within a collection of documents.
1 code implementation • 18 Dec 2023 • Ziyi Chen, Xiaocong Yang, Jiacheng Lin, Chenkai Sun, Kevin Chen-Chuan Chang, Jie Huang
Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft.
no code implementations • 15 Nov 2023 • Pritom Saha Akash, Kashob Kumar Roy, Lucian Popa, Kevin Chen-Chuan Chang
From an extensive experiment on both an open domain and a technical domain QA dataset, we find that our model outperforms the state-of-the-art models on various textual and factual metrics for the LFQA task.
no code implementations • 24 Oct 2023 • Pritom Saha Akash, Jie Huang, Kevin Chen-Chuan Chang
Besides, we provide a simple solution extending a neural topic model to reduce the effect of noisy out-of-topics text generation from PLMs.
1 code implementation • 23 Oct 2023 • Nishant Balepur, Jie Huang, Kevin Chen-Chuan Chang
Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content.
1 code implementation • 21 Oct 2023 • Yuxiang Liu, Jie Huang, Kevin Chen-Chuan Chang
We introduce a new task called *entity-centric question generation* (ECQG), motivated by real-world applications such as topic-specific learning, assisted reading, and fact-checking.
no code implementations • 18 Oct 2023 • Kerui Zhu, Jie Huang, Kevin Chen-Chuan Chang
We present a novel system that automatically extracts and generates informative and descriptive sentences from the biomedical corpus and facilitates the efficient search for relational knowledge.
no code implementations • 8 Oct 2023 • Pritom Saha Akash, Trisha Das, Kevin Chen-Chuan Chang
Topic models are popular statistical tools for detecting latent semantic topics in a text corpus.
1 code implementation • 28 Sep 2023 • Shen Zheng, Yuyu Zhang, Yijie Zhu, Chenguang Xi, Pengyang Gao, Xun Zhou, Kevin Chen-Chuan Chang
With the rapid advancement of large language models (LLMs), there is a pressing need for a comprehensive evaluation suite to assess their capabilities and limitations.
1 code implementation • 15 Aug 2023 • Jie Huang, Wei Ping, Peng Xu, Mohammad Shoeybi, Kevin Chen-Chuan Chang, Bryan Catanzaro
In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models.
no code implementations • 5 Jul 2023 • Jie Huang, Kevin Chen-Chuan Chang
Despite the complexity of implementing such a citation mechanism, along with the potential pitfalls, we advocate for its development.
no code implementations • 19 Jun 2023 • Lam Thanh Do, Pritom Saha Akash, Kevin Chen-Chuan Chang
To solve this problem, we propose a seq2seq model that consists of two modules, namely \textit{phraseness} and \textit{informativeness} module, both of which can be built in an unsupervised and open-domain fashion.
no code implementations • 24 May 2023 • Nishant Balepur, Jie Huang, Samraj Moorjani, Hari Sundaram, Kevin Chen-Chuan Chang
When answering complex questions, large language models (LLMs) may produce answers that do not satisfy all criteria of the question.
1 code implementation • 22 May 2023 • Hanyin Shao, Jie Huang, Shen Zheng, Kevin Chen-Chuan Chang
The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure.
no code implementations • 19 May 2023 • Jie Huang, Yifan Gao, Zheng Li, Jingfeng Yang, Yangqiu Song, Chao Zhang, Zining Zhu, Haoming Jiang, Kevin Chen-Chuan Chang, Bing Yin
We propose and study Complementary Concept Generation (CCGen): given a concept of interest, e. g., "Digital Cameras", generating a list of complementary concepts, e. g., 1) Camera Lenses 2) Batteries 3) Camera Cases 4) Memory Cards 5) Battery Chargers.
1 code implementation • 5 May 2023 • Nishant Balepur, Jie Huang, Kevin Chen-Chuan Chang
Expository documents are vital resources for conveying complex information to readers.
no code implementations • 20 Apr 2023 • Shen Zheng, Jie Huang, Kevin Chen-Chuan Chang
To better understand the model's particular weaknesses in providing truthful answers, we embark an in-depth exploration of open-domain question answering.
1 code implementation • 20 Dec 2022 • Jie Huang, Kevin Chen-Chuan Chang
Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking.
1 code implementation • 20 Dec 2022 • Chenzhengyi Liu, Jie Huang, Kerui Zhu, Kevin Chen-Chuan Chang
MoREE consists of a mixture of retrievers model that retrieves diverse context sentences related to the given concepts, and a mixture of generators model that generates diverse sentences based on the retrieved contexts.
1 code implementation • 20 Nov 2022 • Jie Huang, Kevin Chen-Chuan Chang
To know the relationship between two entities, humans tend to create a sentence to connect them.
no code implementations • 15 Nov 2022 • Kevin Pei, Ishan Jindal, Kevin Chen-Chuan Chang, ChengXiang Zhai, Yunyao Li
Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks.
no code implementations • 16 Oct 2022 • Pritom Saha Akash, Jie Huang, Kevin Chen-Chuan Chang
It then uses the axes to model a corpus for easily understandable representation.
1 code implementation • 11 Oct 2022 • Jie Huang, Kevin Chen-Chuan Chang, JinJun Xiong, Wen-mei Hwu
We hope this work can bring to awareness the notion of specificity of language models and encourage the research community to further explore this important but understudied problem.
1 code implementation • 25 May 2022 • Jie Huang, Hanyin Shao, Kevin Chen-Chuan Chang
Are Large Pre-Trained Language Models Leaking Your Personal Information?
1 code implementation • 21 May 2022 • Jie Huang, Kerui Zhu, Kevin Chen-Chuan Chang, JinJun Xiong, Wen-mei Hwu
Experiments demonstrate that our system can extract and generate high-quality relation descriptions for explaining entity relationships.
1 code implementation • Findings (ACL) 2022 • Pritom Saha Akash, Jie Huang, Kevin Chen-Chuan Chang, Yunyao Li, Lucian Popa, ChengXiang Zhai
We propose a probabilistic approach to select a subset of a \textit{target domain representative keywords} from a candidate set, contrasting with a context domain.
no code implementations • 16 Mar 2022 • Pritom Saha Akash, Kevin Chen-Chuan Chang
Then, the variational graph auto-encoder is used to learn a vector representation for each method.
1 code implementation • 14 Nov 2021 • Jie Huang, Hanyin Shao, Kevin Chen-Chuan Chang, JinJun Xiong, Wen-mei Hwu
From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin stands for without additional knowledge.
1 code implementation • ECNLP (ACL) 2022 • Anurendra Kumar, Keval Morabia, Jingjin Wang, Kevin Chen-Chuan Chang, Alexander Schwing
To address this challenge we propose to reformulate WIE as a context-aware Webpage Object Detection task.
Ranked #1 on
Webpage Object Detection
on CoVA
(using extra training data)
1 code implementation • Findings (ACL) 2022 • Jie Huang, Kevin Chen-Chuan Chang, JinJun Xiong, Wen-mei Hwu
Relations between entities can be represented by different instances, e. g., a sentence containing both entities or a fact in a Knowledge Graph (KG).
1 code implementation • ACL 2021 • Jie Huang, Kevin Chen-Chuan Chang, JinJun Xiong, Wen-mei Hwu
To support a fine-grained domain without relying on a matching corpus for supervision, we develop hierarchical core-fringe learning, which learns core and fringe terms jointly in a semi-supervised manner contextualized in the hierarchy of the domain.
no code implementations • NeurIPS 2020 • Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Chunxu Zhang, Bo Yang
Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space.
1 code implementation • EMNLP 2020 • Jie Huang, Zilong Wang, Kevin Chen-Chuan Chang, Wen-mei Hwu, JinJun Xiong
We introduce and study semantic capacity of terms.
4 code implementations • ICLR 2020 • Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang
From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses.
Node Classification on Non-Homophilic (Heterophilic) Graphs
Representation Learning
+1
no code implementations • 11 May 2019 • Suhansanu Kumar, Heting Gao, Changyu Wang, Hari Sundaram, Kevin Chen-Chuan Chang
When the property of the target entities is not directly queryable via the API, we refer to the property as `hidden' and the population as a hidden population.
1 code implementation • 28 Nov 2017 • Jia Wang, Vincent W. Zheng, Zemin Liu, Kevin Chen-Chuan Chang
As a result, we introduce a new data model, namely diffusion topologies, to fully describe the cascade structure.
1 code implementation • 15 Nov 2017 • Aravind Sankar, Xinyang Zhang, Kevin Chen-Chuan Chang
This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas.
no code implementations • 22 Sep 2017 • Hongyun Cai, Vincent W. Zheng, Kevin Chen-Chuan Chang
Graph is an important data representation which appears in a wide diversity of real-world scenarios.
no code implementations • 5 Sep 2017 • Carl Yang, Hanqing Lu, Kevin Chen-Chuan Chang
It is usually modeled as an unsupervised clustering problem on graphs, based on heuristic assumptions about community characteristics, such as edge density and node homogeneity.
Social and Information Networks Physics and Society
1 code implementation • 15 May 2017 • Hongyun Cai, Vincent W. Zheng, Kevin Chen-Chuan Chang
Graph embedding provides an efficient solution for graph analysis by converting the graph into a low-dimensional space which preserves the structure information.
no code implementations • 17 Jan 2017 • Hongyun Cai, Vincent W. Zheng, Fanwei Zhu, Kevin Chen-Chuan Chang, Zi Huang
Most existing community-related studies focus on detection, which aim to find the community membership for each user from user friendship links.
2 code implementations • 31 Oct 2016 • Vincent W. Zheng, Sandro Cavallari, Hongyun Cai, Kevin Chen-Chuan Chang, Erik Cambria
Most of the existing graph embedding methods focus on nodes, which aim to output a vector representation for each node in the graph such that two nodes being "close" on the graph are close too in the low-dimensional space.