no code implementations • Findings (EMNLP) 2021 • Feifan Yang, Tao Yang, Xiaojun Quan, Qinliang Su
We argue that the posts created by a user contain critical contents that could help answer the questions in a questionnaire, resulting in an assessment of his personality by linking the texts and the questionnaire.
1 code implementation • 20 Mar 2024 • Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Xing Gao, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang, Jingren Zhou
In this paper, we introduce RoleInteract, the first benchmark designed to systematically evaluate the sociality of role-playing conversational agents at both individual and group levels of social interactions.
1 code implementation • 25 Feb 2024 • Fanqi Wan, ZiYi Yang, Longguang Zhong, Xiaojun Quan, Xinting Huang, Wei Bi
Recently, FuseLLM introduced the concept of knowledge fusion to transfer the collective knowledge of multiple structurally varied LLMs into a target LLM through lightweight continual training.
no code implementations • 7 Feb 2024 • Haihui Yang, Xiaojun Quan
Then, we combine the source sentence with the initial correction and feed it through an alignment model for another round of correction, aiming to enforce the alignment model to focus on potential overcorrection.
1 code implementation • 19 Jan 2024 • Fanqi Wan, Xinting Huang, Deng Cai, Xiaojun Quan, Wei Bi, Shuming Shi
In this paper, we introduce the notion of knowledge fusion for LLMs, aimed at combining the capabilities of existing LLMs and transferring them into a single LLM.
1 code implementation • 19 Jan 2024 • Fanqi Wan, Xinting Huang, Leyang Cui, Xiaojun Quan, Wei Bi, Shuming Shi
While large language models (LLMs) have demonstrated exceptional performance across various tasks following human alignment, they may still generate responses that sound plausible but contradict factual knowledge, a phenomenon known as \emph{hallucination}.
1 code implementation • 14 Jan 2024 • Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, Fei Huang
Each component is implemented by a single LLM that focuses on a specific capability and collaborates with others to accomplish the task.
no code implementations • 13 Jan 2024 • Hongzhan Chen, Xiaojun Quan, Hehong Chen, Ming Yan, Ji Zhang
The prior estimation aims to derive a prior distribution by utilizing the corpus generated by closed-source language models, while the posterior estimation employs a proxy model to update the prior distribution and derive a posterior distribution.
1 code implementation • 31 Oct 2023 • Tao Yang, Tianyuan Shi, Fanqi Wan, Xiaojun Quan, Qifan Wang, Bingzhe Wu, Jiaxiang Wu
Drawing inspiration from Psychological Questionnaires, which are carefully designed by psychologists to evaluate individual personality traits through a series of targeted items, we argue that these items can be regarded as a collection of well-structured chain-of-thought (CoT) processes.
no code implementations • 23 Oct 2023 • Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang
Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests.
1 code implementation • 23 Oct 2023 • Hongzhan Chen, Siyue Wu, Xiaojun Quan, Rui Wang, Ming Yan, Ji Zhang
Large language models (LLMs) have showcased remarkable capabilities in complex reasoning through chain of thought (CoT) prompting.
1 code implementation • 13 Oct 2023 • Fanqi Wan, Xinting Huang, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi
Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks.
1 code implementation • 13 Oct 2023 • Weizhou Shen, Yingqi Gao, Canbin Huang, Fanqi Wan, Xiaojun Quan, Wei Bi
The results demonstrate that when combined with meta knowledge, the response generator can effectively leverage high-quality knowledge records from the retriever and enhance the quality of generated responses.
1 code implementation • 24 May 2023 • Zihong Liang, Xiaojun Quan, Qifan Wang
Chinese Spelling Correction (CSC) aims to detect and correct erroneous characters in Chinese texts.
1 code implementation • 17 May 2023 • Siyue Wu, Hongzhan Chen, Xiaojun Quan, Qifan Wang, Rui Wang
To enhance the knowledge transfer of model reasoning and generalization, we further explore multi-view attribution distillation on all potential decisions of the teacher.
1 code implementation • 17 May 2023 • Fanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan, Wei Bi
Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses.
1 code implementation • 17 May 2023 • Jinghao Deng, Fanqi Wan, Tao Yang, Xiaojun Quan, Rui Wang
Contrastive learning has been widely studied in sentence representation learning.
1 code implementation • 21 Feb 2023 • Weizhou Shen, Xiaojun Quan, Ke Yang
To model the dependencies between utterances in multi-party conversations, we propose a simple and generic framework based on the dependency parsing results of utterances.
1 code implementation • 3 Dec 2022 • Tao Yang, Jinghao Deng, Xiaojun Quan, Qifan Wang
Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis.
1 code implementation • 12 Oct 2022 • Tao Yang, Jinghao Deng, Xiaojun Quan, Qifan Wang, Shaoliang Nie
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available.
no code implementations • 10 Oct 2022 • Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan, Dawei Song
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner.
no code implementations • COLING 2022 • Guanhuan Huang, Xiaojun Quan, Qifan Wang
In either approach, the systems may generate a response with conflicting entity information.
1 code implementation • 15 Sep 2022 • Yunyi Yang, Hong Ding, Qingyi Liu, Xiaojun Quan
This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error propagation and damaging the robustness of the TOD system.
2 code implementations • 28 Jun 2022 • Weizhou Shen, Yeyun Gong, Yelong Shen, Song Wang, Xiaojun Quan, Nan Duan, Weizhu Chen
Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates.
1 code implementation • 22 May 2022 • Liqi Yan, Qifan Wang, Yiming Cui, Fuli Feng, Xiaojun Quan, Xiangyu Zhang, Dongfang Liu
Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description.
no code implementations • 5 Mar 2022 • Qifan Wang, Yi Fang, Anirudh Ravula, Ruining He, Bin Shen, Jingang Wang, Xiaojun Quan, Dongfang Liu
Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks.
no code implementations • 1 Feb 2022 • Qifan Wang, Yi Fang, Anirudh Ravula, Fuli Feng, Xiaojun Quan, Dongfang Liu
Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product title, description, brand and price.
no code implementations • ACL 2021 • Tao Yang, Feifan Yang, Haolan Ouyang, Xiaojun Quan
In this paper, we propose a psycholinguistic knowledge-based tripartite graph network, TrigNet, which consists of a tripartite graph network and a BERT-based graph initializer.
1 code implementation • Findings (ACL) 2021 • Yunhao Li, Yunyi Yang, Xiaojun Quan, Jianxing Yu
In this paper, we propose a retrieve-and-memorize framework to enhance the learning of system actions.
no code implementations • Findings (ACL) 2021 • Ruikun Luo, Guanhuan Huang, Xiaojun Quan
The major paradigm of applying a pre-trained language model to downstream tasks is to fine-tune it on labeled task data, which often suffers instability and low performance when the labeled examples are scarce.~One way to alleviate this problem is to apply post-training on unlabeled task data before fine-tuning, adapting the pre-trained model to target domains by contrastive learning that considers either token-level or sequence-level similarity.
1 code implementation • ACL 2021 • Weizhou Shen, Siyue Wu, Yunyi Yang, Xiaojun Quan
In this paper, we put forward a novel idea of encoding the utterances with a directed acyclic graph (DAG) to better model the intrinsic structure within a conversation, and design a directed acyclic neural network, namely DAG-ERC, to implement this idea.
Ranked #10 on Emotion Recognition in Conversation on DailyDialog
1 code implementation • ACL 2021 • Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Nan Duan, Daxin Jiang
We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa.
4 code implementations • 16 Dec 2020 • Weizhou Shen, Junqing Chen, Xiaojun Quan, Zhixian Xie
Specifically, we first modify the recurrence mechanism of XLNet from segment-level to utterance-level in order to better model the conversational data.
Ranked #2 on Emotion Recognition in Conversation on CPED
1 code implementation • 7 Dec 2020 • Yunyi Yang, Yunhao Li, Xiaojun Quan
This paper presents our task-oriented dialog system UBAR which models task-oriented dialogs on a dialog session level.
no code implementations • COLING 2020 • Wuya Chen, Xiaojun Quan, Chunyu Kit, Zhengcheng Min, Jiahai Wang
We propose a multi-choice relational reasoning (McR$^2$) model with an aim to enable relational reasoning on candidates based on fusion representations of document, query and candidates.
1 code implementation • COLING 2020 • Yunyi Yang, Kun Li, Xiaojun Quan, Weizhou Shen, Qinliang Su
One of the remaining challenges for aspect term extraction in sentiment analysis resides in the extraction of phrase-level aspect terms, which is non-trivial to determine the boundaries of such terms.
Aspect Term Extraction and Sentiment Classification Sentence +1
1 code implementation • ACL 2020 • Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, Yonggang Wang
Chinese word segmentation (CWS) and part-of-speech (POS) tagging are important fundamental tasks for Chinese language processing, where joint learning of them is an effective one-step solution for both tasks.
no code implementations • ACL 2020 • Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin
Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.
no code implementations • ACL 2020 • Kun Li, Chengbo Chen, Xiaojun Quan, Qing Ling, Yan Song
In this paper, we formulate the data augmentation as a conditional generation task: generating a new sentence while preserving the original opinion targets and labels.
1 code implementation • ACL 2020 • Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang
Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • ACL 2020 • Kai Wang, Junfeng Tian, Rui Wang, Xiaojun Quan, Jianxing Yu
Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed.
no code implementations • IJCNLP 2019 • Zenan Xu, Qinliang Su, Xiaojun Quan, Weijia Zhang
Textual network embeddings aim to learn a low-dimensional representation for every node in the network so that both the structural and textual information from the networks can be well preserved in the representations.
1 code implementation • ACL 2019 • Kai Wang, Xiaojun Quan, Rui Wang
The success of neural summarization models stems from the meticulous encodings of source articles.
Ranked #14 on Text Summarization on GigaWord