Author name cluster

Zhoujun Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

31 papers

1 author row

NeurIPS Conference 2025 Conference Paper

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Jiajun Shi
Jian Yang
Jiaheng Liu
Xingyuan Bu
Jiangjie Chen
Junting Zhou
Kaijing Ma
Zhoufutu Wen

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchmarks are often domain-specific and thus cannot fully capture an LLM’s general reasoning potential. To address this limitation, we introduce the Knowledge Orthogonal Reasoning Gymnasium (KORGym), a dynamic evaluation platform inspired by KOR-Bench and Gymnasium. KORGym offers over fifty games in either textual or visual formats and supports interactive, multi-turn assessments with reinforcement learning scenarios. Using KORGym, we conduct extensive experiments on 19 LLMs and 8 VLMs, revealing consistent reasoning patterns within model families and demonstrating the superior performance of closed-source models. Further analysis examines the effects of modality, reasoning strategies, reinforcement learning techniques, and response length on model performance. We expect KORGym to become a valuable resource for advancing LLM reasoning research and developing evaluation methodologies suited to complex, interactive environments.

AAAI Conference 2025 Conference Paper

Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow

Jiaqi Bai
Hongcheng Guo
Zhongyuan Peng
Jian Yang
Zhoujun Li
Mohan Li
Zhihong Tian

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do not exist in the image. In this paper, we reveal that object hallucination can be attributed to overconfidence in irrelevant visual features when soft visual tokens map to the LLM's word embedding space. Specifically, by figuring out the semantic similarity between visual tokens and LLM's word embedding, we observe that the smoothness of similarity distribution strongly correlates with the emergence of object hallucinations. To mitigate hallucinations, we propose using the Variational Information Bottleneck (VIB) to alleviate overconfidence by introducing stochastic noise, facilitating the constraining of irrelevant information. Furthermore, we propose an entropy-based noise-controlling strategy to enable the injected noise to be adaptively constrained regarding the smoothness of the similarity distribution. We adapt the proposed AdaVIB across distinct model architectures. Experimental results demonstrate that the proposed AdaVIB mitigates object hallucinations by effectively alleviating the overconfidence in irrelevant visual features, with consistent improvements on two object hallucination benchmarks.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Xeron Du
Yifan Yao
Kaijing Ma
Bingli Wang
Tianyu Zheng
Minghao Liu
Yiming Liang
Xiaolong Jin

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e. g. , the reasoning-focused model Gemini-2. 5-Pro achieved the highest accuracy of 63. 56% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

AAAI Conference 2025 Conference Paper

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

Xianjie Wu
Jian Yang
Linzheng Chai
Ge Zhang
Jiaheng Liu
Xeron Du
Di Liang
Daixin Shu

Recent advancements in Large Language Models (LLMs) have markedly enhanced the interpretation and processing of tabular data, introducing previously unimaginable capabilities. Despite these achievements, LLMs still encounter significant challenges when applied in industrial scenarios, particularly due to the increased complexity of reasoning required with real-world tabular data, underscoring a notable disparity between academic benchmarks and practical applications. To address this discrepancy, we conduct a detailed investigation into the application of tabular data in industrial scenarios and propose a comprehensive and complex benchmark TableBench, including 18 fields within four major categories of table question answering (TableQA) capabilities. Furthermore, we introduce TableLLM, trained on our meticulously constructed training set TableInstruct, achieving comparable performance with GPT-3.5. Massive experiments conducted on TableBench indicate that both open-source and proprietary LLMs still have significant room for improvement to meet real-world demands, where the most advanced model, GPT-4, achieves only a modest score compared to humans.

PDF Details DOI

AAAI Conference 2025 Conference Paper

XCOT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

Linzheng Chai
Jian Yang
Tao Sun
Hongcheng Guo
Jiaheng Liu
Bing Wang
Xinnian Liang
Jiaqi Bai

Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent performance in English, but its usage in low-resource languages is constrained due to poor language generalization. To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCoT) to transfer knowledge from high-resource languages to low-resource languages. Specifically, the multilingual instruction training data (xCoT-Instruct) is created to encourage the semantic alignment of multiple languages. We introduce cross-lingual in-context few-shot learning (xICL) to accelerate multilingual agreement in instruction tuning, where some fragments of source languages in examples are randomly substituted by their counterpart translations of target languages. During multilingual instruction tuning, we adopt the randomly online CoT strategy to enhance the multilingual reasoning ability of the large language model by first translating the query to another language and then answering in English. To further facilitate the language transfer, we leverage the high-resource CoT to supervise the training of low-resource languages with cross-lingual distillation. Experimental results demonstrate the superior performance of xCoT in reducing the gap among different languages, highlighting its potential to reduce the cross-lingual gap.

PDF Details DOI

AAAI Conference 2024 Conference Paper

LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection

Hongcheng Guo
Jian Yang
Jiaheng Liu
Jiaqi Bai
Boyang Wang
Zhoujun Li
Tieqiao Zheng
Bo Zhang

Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios. However, previous deep models merely focused on extracting the semantics of log sequences in the same domain, leading to poor generalization on multi-domain logs. To alleviate this issue, we propose a unified Transformer-based framework for Log anomaly detection (LogFormer) to improve the generalization ability across different domains, where we establish a two-stage process including the pre-training and adapter-based tuning stage. Specifically, our model is first pre-trained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer such knowledge to the target domain via shared parameters. Besides, the Log-Attention module is proposed to supplement the information ignored by the log-paring. The proposed method is evaluated on three public datasets and one real-world dataset. Experimental results on multiple benchmarks demonstrate the effectiveness of our LogFormer with fewer trainable parameters and lower training costs.

PDF Details DOI

AAAI Conference 2024 Conference Paper

MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning

Ying Mo
Jian Yang
Jiahao Liu
Qifan Wang
Ruoyu Chen
Jingang Wang
Zhoujun Li

Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora, especially for non-English data. While prior efforts mainly focus on data-driven transfer methods, a significant aspect that has not been fully explored is aligning both semantic and token-level representations across diverse languages. In this paper, we propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (MCL-NER). Specifically, we reframe the CrossNER task into a problem of recognizing relationships between pairs of tokens. This approach taps into the inherent contextual nuances of token-to-token connections within entities, allowing us to align representations across different languages. A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations. By enforcing agreement within both semantic and relational spaces, we minimize the gap between source sentences and their counterparts of both codeswitched and target sentences. This alignment extends to the relationships between diverse tokens, enhancing the projection of entities across languages. We further augment CrossNER by combining self-training with labeled source data and unlabeled target data. Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of MCL-NER over prior data-driven and model-based approaches. It achieves a substantial increase of nearly +2.0 F1 scores across a broad spectrum and establishes itself as the new state-of-the-art performer.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Low Resource Quantitative Information Extraction via Structure Searching and Prefix-Based Text Generation

Tongliang Li
Zixiang Wang
Zhoujun Li

Quantitative information plays an important part in the financial and data analysis areas. Prior work relied on pattern-matching methods and complex hand-crafted rules to extract quantitative information due to the lack of labeled data. Such methods can be unstable and difficult to scale to the open domain. In this paper, we study quantitative information extraction in the low-resource setting. We propose a search-based approach by searching from the syntactic structures to acquire basic training data. The search process is simple yet effective. Then, a prefix-based text-to-text generation method is employed to extract the quantitative information. The prefix design can fully leverage pre-trained language models for text generation to serve the information extraction purpose. Experimental results show that our approaches achieves high performance with a limited amount of labeled data. The extraction result could further boost the performance of other tasks such as quantitative reasoning.

PDF Details DOI

AAAI Conference 2023 Conference Paper

TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models

Minghao Li
Tengchao Lv
Jingye Chen
Lei Cui
Yijuan Lu
Dinei Florencio
Cha Zhang
Zhoujun Li

Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is usually needed to improve the overall accuracy as a post-processing step. In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. The TrOCR model is simple but effective, and can be pre-trained with large-scale synthetic data and fine-tuned with human-labeled datasets. Experiments show that the TrOCR model outperforms the current state-of-the-art models on the printed, handwritten and scene text recognition tasks. The TrOCR models and code are publicly available at https://aka.ms/trocr.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

High-resource Language-specific Training for Multilingual Neural Machine Translation

Jian Yang
Yuwei Yin
Shuming Ma
Dongdong Zhang
Zhoujun Li
Furu Wei

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages. In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference, which adopts the two-stage training with the language-specific selection mechanism. Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder to enhance the translation quality of high-resource directions. Next, the model is further trained on all available corpora to transfer knowledge from high-resource languages (HRLs) to low-resource languages (LRLs). Experimental results show that HLT-MT outperforms various strong baselines on WMT-10 and OPUS-100 benchmarks. Furthermore, the analytic experiments validate the effectiveness of our method in mitigating the negative interference in multilingual training.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation

Jian Yang
Yuwei Yin
Shuming Ma
Dongdong Zhang
ShuangZhi Wu
Hongcheng Guo
Zhoujun Li
Furu Wei

Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enables one-pass translation using shared semantic space for all languages compared to the two-pass pivot translation but often underperforms the pivot-based method. In this paper, we propose a novel method, named as Unified Multilingual Multiple teacher-student Model for NMT (UM4). Our method unifies source-teacher, target-teacher, and pivot-teacher models to guide the student model for the zero-resource translation. The source teacher and target teacher force the student to learn the direct source-target translation by the distilled knowledge on both source and target sides. The monolingual corpus is further leveraged by the pivot-teacher model to enhance the student model. Experimental results demonstrate that our model of 72 directions significantly outperforms previous methods on the WMT benchmark.

PDF Details DOI

AAAI Conference 2021 Conference Paper

A Unified Multi-Task Learning Framework for Joint Extraction of Entities and Relations

Tianyang Zhao
Zhao Yan
Yunbo Cao
Zhoujun Li

Joint extraction of entities and relations has achieved great success in recent year by task decomposition and multi-task learning. Previous works effectively perform the task through different extraction order, such as relation-last, relation-first and relation-middle manner. However, these methods still suffer from the template-dependency, non-entity detection and non-predefined relation prediction problem. To overcome these challenges, in this paper, we propose a unified multitask learning framework, which decomposes the task into three interacted sub-tasks. Specifically, we first introduce the type-attentional method for subject extraction to provide prior type information explicitly. Then, the subject-aware relation prediction is presented to select useful relations based on the combination of global and local semantics. Third, we propose a question generation based QA method for object extraction to obtain diverse queries automatically. Notably, our method detects subjects or objects without relying on NER models and thus it is capable of dealing with the non-entity scenario. Finally, three sub-tasks are integrated into a unified model through parameter sharing. Extensive experiments demonstrate that the proposed framework outperforms all the baseline methods on four benchmark datasets, and further achieves excellent performance for non-predefined relations.

AAAI Conference 2021 Conference Paper

Learning to Copy Coherent Knowledge for Response Generation

Jiaqi Bai
Ze Yang
Xinnian Liang
Wei Wang
Zhoujun Li

Knowledge-driven dialog has shown remarkable performance to alleviate the problem of generating uninformative responses in the dialog system. However, incorporating knowledge coherently and accurately into response generation is still far from being solved. Previous works dropped into the paradigm of non-goal-oriented knowledge-driven dialog, they are prone to ignore the effect of dialog goal, which has potential impacts on knowledge exploitation and response generation. To address this problem, this paper proposes a Goal-Oriented Knowledge Copy network, GOKC. Specifically, a goal-oriented knowledge discernment mechanism is designed to help the model discern the knowledge facts that are highly correlated to the dialog goal and the dialog context. Besides, a context manager is devised to copy facts not only from the discerned knowledge but also from the dialog goal and the dialog context, which allows the model to accurately restate the facts in the generated response. The empirical studies are conducted on two benchmarks of goal-oriented knowledge-driven dialog generation. The results show that our model can significantly outperform several state-of-theart models in terms of both automatic evaluation and human judgments.

AAAI Conference 2021 Conference Paper

Open Domain Dialogue Generation with Latent Images

Ze Yang
Wei Wu
Huang Hu
Can Xu
Wei Wang
Zhoujun Li

We consider grounding open domain dialogues with images. Existing work assumes that both an image and a textual context are available, but image-grounded dialogues by nature are more difficult to obtain than textual dialogues. Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques. The likelihood of the two types of dialogues is then formulated by a response generator and an image reconstructor that are learned within a conditional variational auto-encoding framework. Empirical studies are conducted in both image-grounded conversation and text-based conversation. In the first scenario, image-grounded dialogues, especially under a low-resource setting, can be effectively augmented by textual dialogues with latent images; while in the second scenario, latent images can enrich the content of responses and at the same time keep them relevant to contexts.

AAAI Conference 2020 Conference Paper

Alternating Language Modeling for Cross-Lingual Pre-Training

Jian Yang
Shuming Ma
Dongdong Zhang
ShuangZhi Wu
Zhoujun Li
Ming Zhou

Language model pre-training has achieved success in many natural language processing tasks. Existing methods for cross-lingual pre-training adopt Translation Language Model to predict masked words with the concatenation of the source sentence and its target equivalent. In this work, we introduce a novel cross-lingual pre-training method, called Alternating Language Modeling (ALM). It code-switches sentences of different languages rather than simple concatenation, hoping to capture the rich cross-lingual context of words and phrases. More speciﬁcally, we randomly substitute source phrases with target translations to create code-switched sentences. Then, we use these code-switched data to train ALM model to learn to predict words of different languages. We evaluate our pre-training ALM on the downstream tasks of machine translation and cross-lingual classiﬁcation. Experiments show that ALM can outperform the previous pretraining methods on three benchmarks. 1

IJCAI Conference 2020 Conference Paper

Asking Effective and Diverse Questions: A Machine Reading Comprehension based Framework for Joint Entity-Relation Extraction

Tianyang Zhao
Zhao Yan
Yunbo Cao
Zhoujun Li

Recent advances cast the entity-relation extraction to a multi-turn question answering (QA) task and provide an effective solution based on the machine reading comprehension (MRC) models. However, they use a single question to characterize the meaning of entities and relations, which is intuitively not enough because of the variety of context semantics. Meanwhile, existing models enumerate all relation types to generate questions, which is inefficient and easily leads to confusing questions. In this paper, we improve the existing MRC-based entity-relation extraction model through diverse question answering. First, a diversity question answering mechanism is introduced to detect entity spans and two answering selection strategies are designed to integrate different answers. Then, we propose to predict a subset of potential relations and filter out irrelevant ones to generate questions effectively. Finally, entity and relation extractions are integrated in an end-to-end way and optimized through joint learning. Experiment results show that the proposed method significantly outperforms baseline models, which improves the relation F1 to 62. 1% (+1. 9%) on ACE05 and 71. 9% (+3. 0%) on CoNLL04. Our implementation is available at https: //github. com/TanyaZhao/MRC4ERE.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Adversarial Learning for Weakly-Supervised Social Network Alignment

Chaozhuo Li
Senzhang Wang
Yukun Wang
Philip Yu
Yanbo Liang
Yun Liu
Zhoujun Li

Nowadays, it is common for one natural person to join multiple social networks to enjoy different kinds of services. Linking identical users across multiple social networks, also known as social network alignment, is an important problem of great research challenges. Existing methods usually link social identities on the pairwise sample level, which may lead to undesirable performance when the number of available annotations is limited. Motivated by the isomorphism information, in this paper we consider all the identities in a social network as a whole and perform social network alignment from the distribution level. The insight is that we aim to learn a projection function to not only minimize the distance between the distributions of user identities in two social networks, but also incorporate the available annotations as the learning guidance. We propose three models SNNAu, SNNAb and SNNAo to learn the projection function under the weakly-supervised adversarial learning framework. Empirically, we evaluate the proposed models over multiple datasets, and the results demonstrate the superiority of our proposals.

AAAI Conference 2019 Conference Paper

Leveraging Web Semantic Knowledge in Word Representation Learning

Haoyan Liu
Lei Fang
Jian-Guang Lou
Zhoujun Li

Much recent work focuses on leveraging semantic lexicons like WordNet to enhance word representation learning (WRL) and achieves promising performance on many NLP tasks. However, most existing methods might have limitations because they require high-quality, manually created, semantic lexicons or linguistic structures. In this paper, we propose to leverage semantic knowledge automatically mined from web structured data to enhance WRL. We first construct a semantic similarity graph, which is referred as semantic knowledge, based on a large collection of semantic lists extracted from the web using several pre-defined HTML tag patterns. Then we introduce an efficient joint word representation learning model to capture semantics from both semantic knowledge and text corpora. Compared with recent work on improving WRL with semantic resources, our approach is more general, and can be easily scaled with no additional effort. Extensive experimental results show that our approach outperforms the state-of-the-art methods on word similarity, word sense disambiguation, text classification and textual similarity tasks.

AAAI Conference 2019 Conference Paper

Response Generation by Context-Aware Prototype Editing

Yu Wu
Furu Wei
Shaohan Huang
Yunli Wang
Zhoujun Li
Ming Zhou

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm, prototypethen-edit for response generation, that first retrieves a prototype response from a pre-defined index and then edits the prototype response according to the differences between the prototype context and current context. Our motivation is that the retrieved prototype provides a good start-point for generation because it is grammatical and informative, and the post-editing process further improves the relevance and coherence of the prototype. In practice, we design a contextaware editing model that is built upon an encoder-decoder framework augmented with an editing vector. We first generate an edit vector by considering lexical differences between a prototype context and current context. After that, the edit vector and the prototype response representation are fed to a decoder to generate a new response. Experiment results on a large scale dataset demonstrate that our new paradigm significantly increases the relevance, diversity and originality of generation results, compared to traditional generative models. Furthermore, our model outperforms retrieval-based methods in terms of relevance and originality.

AAAI Conference 2018 Conference Paper

Assertion-Based QA With Question-Aware Open Information Extraction

Zhao Yan
Duyu Tang
Nan Duan
Shujie Liu
Wendi Wang
Daxin Jiang
Ming Zhou
Zhoujun Li

We present assertion based question answering (ABQA), an open domain question answering task that takes a question and a passage as inputs, and outputs a semi-structured assertion consisting of a subject, a predicate and a list of arguments. An assertion conveys more evidences than a short answer span in reading comprehension, and it is more concise than a tedious passage in passage-based QA. These advantages make ABQA more suitable for human-computer interaction scenarios such as voice-controlled speakers. Further progress towards improving ABQA requires richer supervised dataset and powerful models of text understanding. To remedy this, we introduce a new dataset called WebAssertions, which includes hand-annotated QA labels for 358, 427 assertions in 55, 960 web passages. To address ABQA, we develop both generative and extractive approaches. The backbone of our generative approach is sequence to sequence learning. In order to capture the structure of the output assertion, we introduce a hierarchical decoder that ﬁrst generates the structure of the assertion and then generates the words of each ﬁeld. The extractive approach is based on learning to rank. Features at different levels of granularity are designed to measure the semantic relevance between a question and an assertion. Experimental results show that our approaches have the ability to infer question-aware assertions from a passage. We further evaluate our approaches by incorporating the ABQA results as additional features in passage-based QA. Results on two datasets show that ABQA features signiﬁcantly improve the accuracy on passage-based QA.

IJCAI Conference 2018 Conference Paper

Ensemble Neural Relation Extraction with Adaptive Boosting

Dongdong Yang
Senzhang Wang
Zhoujun Li

Relation extraction has been widely studied to extract new relational facts from open corpus. Previous relation extraction methods are faced with the problem of wrong labels and noisy data, which substantially decrease the performance of the model. In this paper, we propose an ensemble neural network model - Adaptive Boosting LSTMs with Attention, to more effectively perform relation extraction. Specifically, our model first employs the recursive neural network LSTMs to embed each sentence. Then we import attention into LSTMs by considering that the words in a sentence do not contribute equally to the semantic meaning of the sentence. Next via adaptive boosting, we build strategically several such neural classifiers. By ensembling multiple such LSTM classifiers with adaptive boosting, we could build a more effective and robust joint ensemble neural networks based relation extractor. Experiment results on real dataset demonstrate the superior performance of the proposed model, improving F1-score by about 8% compared to the state-of-the-art models.

AAAI Conference 2018 Conference Paper

Knowledge Enhanced Hybrid Neural Network for Text Matching

Yu Wu
Wei Wu
Can Xu
Zhoujun Li

Long text brings a big challenge to neural network based text matching approaches due to their complicated structures. To tackle the challenge, we propose a knowledge enhanced hybrid neural network (KEHNN) that leverages prior knowledge to identify useful information and ﬁlter out noise in long text and performs matching from multiple perspectives. The model fuses prior knowledge into word representations by knowledge gates and establishes three matching channels with words, sequential structures of text given by Gated Recurrent Units (GRUs), and knowledge enhanced representations. The three channels are processed by a convolutional neural network to generate high level features for matching, and the features are synthesized as a matching score by a multilayer perceptron. In this paper, we focus on exploring the use of taxonomy knowledge for text matching. Evaluation results from extensive experiments on public data sets of question answering and conversation show that KEHNN can signiﬁcantly outperform state-of-the-art matching models and particularly improve matching accuracy on pairs with long text.

AAAI Conference 2018 Conference Paper

Neural Response Generation With Dynamic Vocabularies

Yu Wu
Wei Wu
Dejian Yang
Can Xu
Zhoujun Li

We study response generation for open domain conversation in chatbots. Existing methods assume that words in responses are generated from an identical vocabulary regardless of their inputs, which not only makes them vulnerable to generic patterns and irrelevant noise, but also causes a high cost in decoding. We propose a dynamic vocabulary sequence-tosequence (DVS2S) model which allows each input to possess their own vocabulary in decoding. In training, vocabulary construction and response generation are jointly learned by maximizing a lower bound of the true objective with a Monte Carlo sampling method. In inference, the model dynamically allocates a small vocabulary for an input with the word prediction model, and conducts decoding only with the small vocabulary. Because of the dynamic vocabulary mechanism, DVS2S eludes many generic patterns and irrelevant words in generation, and enjoys efﬁcient decoding at the same time. Experimental results on both automatic metrics and human annotations show that DVS2S can signiﬁcantly outperform state-of-the-art methods in terms of response quality, but only requires 60% decoding time compared to the most efﬁcient baseline.

AAAI Conference 2017 Conference Paper

Building Task-Oriented Dialogue Systems for Online Shopping

Zhao Yan
Nan Duan
Peng Chen
Ming Zhou
Jianshe Zhou
Zhoujun Li

We present a general solution towards building task-oriented dialogue systems for online shopping, aiming to assist online customers in completing various purchase-related tasks, such as searching products and answering questions, in a natural language conversation manner. As a pioneering work, we show what & how existing natural language processing techniques, data resources, and crowdsourcing can be leveraged to build such task-oriented dialogue systems for E-commerce usage. To demonstrate its effectiveness, we integrate our system into a mobile online shopping application. To the best of our knowledge, this is the ﬁrst time that an dialogue system in Chinese is practically used in online shopping scenario with millions of real consumers. Interesting and insightful observations are shown in the experimental part, based on the analysis of human-bot conversation log. Several current challenges are also pointed out as our future directions.

AAAI Conference 2016 Conference Paper

Aggregating Inter-Sentence Information to Enhance Relation Extraction

Hao Zheng
Zhoujun Li
Senzhang Wang
Zhao Yan
Jianshe Zhou

Previous work for relation extraction from free text is mainly based on intra-sentence information. As relations might be mentioned across sentences, inter-sentence information can be leveraged to improve distantly supervised relation extraction. To effectively exploit inter-sentence information, we propose a ranking-based approach, which ﬁrst learns a scoring function based on a listwise learning-to-rank model and then uses it for multi-label relation extraction. Experimental results verify the effectiveness of our method for aggregating information across sentences. Additionally, to further improve the ranking of high-quality extractions, we propose an effective method to rank relations from different entity pairs. This method can be easily integrated into our overall relation extraction framework, and boosts the precision signiﬁcantly.

TIST Journal 2016 Journal Article

Coranking the Future Influence of Multiobjects in Bibliographic Network Through Mutual Reinforcement

Senzhang Wang
Sihong Xie
Xiaoming Zhang
Zhoujun Li
Philip S. Yu
Yueying He

Scientific literature ranking is essential to help researchers find valuable publications from a large literature collection. Recently, with the prevalence of webpage ranking algorithms such as PageRank and HITS, graph-based algorithms have been widely used to iteratively rank papers and researchers through the networks formed by citation and coauthor relationships. However, existing graph-based ranking algorithms mostly focus on ranking the current importance of literature. For researchers who enter an emerging research area, they might be more interested in new papers and young researchers that are likely to become influential in the future, since such papers and researchers are more helpful in letting them quickly catch up on the most recent advances and find valuable research directions. Meanwhile, although some works have been proposed to rank the prestige of a certain type of objects with the help of multiple networks formed of multiobjects, there still lacks a unified framework to rank multiple types of objects in the bibliographic network simultaneously. In this article, we propose a unified ranking framework MRCoRank to corank the future popularity of four types of objects: papers, authors, terms, and venues through mutual reinforcement. Specifically, because the citation data of new publications are sparse and not efficient to characterize their innovativeness, we make the first attempt to extract the text features to help characterize innovative papers and authors. With the observation that the current trend is more indicative of the future trend of citation and coauthor relationships, we then construct time-aware weighted graphs to quantify the importance of links established at different times on both citation and coauthor graphs. By leveraging both the constructed text features and time-aware graphs, we finally fuse the rich information in a mutual reinforcement ranking framework to rank the future importance of multiobjects simultaneously. We evaluate the proposed model through extensive experiments on the ArnetMiner dataset containing more than 1,500,000 papers. Experimental results verify the effectiveness of MRCoRank in coranking the future influence of multiobjects in a bibliographic network.

AAAI Conference 2016 Conference Paper

Improving Recommendation of Tail Tags for Questions in Community Question Answering

Yu Wu
Wei Wu
Zhoujun Li
Ming Zhou

We study tag recommendation for questions in community question answering (CQA). Tags represent the semantic summarization of questions are useful for navigation and expert ﬁnding in CQA and can facilitate content consumption such as searching and mining in these web sites. The task is challenging, as both questions and tags are short and a large fraction of tags are tail tags which occur very infrequently. To solve these problems, we propose matching questions and tags not only by themselves, but also by similar questions and similar tags. The idea is then formalized as a model in which we calculate question-tag similarity using a linear combination of similarity with similar questions and tags weighted by tag importance. Question similarity, tag similarity, and tag importance are learned in a supervised random walk framework by fusing multiple features. Our model thus can not only accurately identify question-tag similarity for head tags, but also improve the accuracy of recommendation of tail tags. Experimental results show that the proposed method significantly outperforms state-of-the-art methods on tag recommendation for questions. Particularly, it improves tail tag recommendation accuracy by a large margin.

AAAI Conference 2015 Conference Paper

Burst Time Prediction in Cascades

Senzhang Wang
Zhao Yan
Xia Hu
Philip S. Yu
Zhoujun Li

Studying the bursty nature of cascades in social media is practically important in many applications such as product sales prediction, disaster relief, and stock market prediction. Although the cascade volume prediction has been extensively studied, how to predict when a burst will come remains an open problem. It is challenging to predict the time of the burst due to the “quick rise and fall” pattern and the diverse time spans of the cascades. To this end, this paper proposes a classification based approach for burst time prediction by utilizing and modeling rich knowledge in information diffusion. Particularly, we first propose a time window based approach to predict in which time window the burst will appear. This paves the way to transform the time prediction task to a classification problem. To address the challenge that the original time series data of the cascade popularity only are not sufficient for predicting cascades with diverse magnitudes and time spans, we explore rich information diffusion related knowledge and model them in a scale-independent manner. Extensive experiments on a Sina Weibo reposting dataset demonstrate the superior performance of the proposed approach in accurately predicting the burst time of posts.

IJCAI Conference 2015 Conference Paper

Learning Geographical Hierarchy Features for Social Image Location Prediction

Xiaoming Zhang
Xia Hu
Zhoujun Li

Image location prediction is to estimate the geolocation where an image is taken. Social image contains heterogeneous contents, which makes image location prediction nontrivial. Moreover, it is observed that image content patterns and location preferences correlate hierarchically. Traditional image location prediction methods mainly adopt a single-level architecture, which is not directly adaptable to the hierarchical correlation. In this paper, we propose a geographically hierarchical bi-modal deep belief network model (GH- BDBN), which is a compositional learning architecture that integrates multi-modal deep learning model with non-parametric hierarchical prior model. GH-BDBN learns a joint representation capturing the correlations among different types of image content using a bi-modal DBN, with a geographically hierarchical prior over the joint representation to model the hierarchical correlation between image content and location. Experimental results demonstrate the superiority of our model for image location prediction.

AAAI Conference 2015 Conference Paper

Mining Query Subtopics from Questions in Community Question Answering

Yu Wu
Wei Wu
Zhoujun Li
Ming Zhou

This paper proposes mining query subtopics from questions in community question answering (CQA). The subtopics are represented as a number of clusters of questions with keywords summarizing the clusters. The task is unique in that the subtopics from questions can not only facilitate user browsing in CQA search, but also describe aspects of queries from a question-answering perspective. The challenges of the task include how to group semantically similar questions and how to find keywords capable of summarizing the clusters. We formulate the subtopic mining task as a non-negative matrix factorization (NMF) problem and further extend the model of NMF to incorporate question similarity estimated from metadata of CQA into learning. Compared with existing methods, our method can jointly optimize question clustering and keyword extraction and encourage the former task to enhance the latter. Experimental results on large scale real world CQA datasets show that the proposed method significantly outperforms the existing methods in terms of keyword extraction, while achieving a comparable performance to the state-ofthe-art methods for question clustering.

AAAI Conference 2013 Conference Paper

From Interest to Function: Location Estimation in Social Media

Yan Chen
Jichang Zhao
Xia Hu
Xiaoming Zhang
Zhoujun Li
Tat-Seng Chua

Recent years have witnessed the tremendous development of social media, which attracts a vast number of Internet users. The high-dimension content generated by these users provides an unique opportunity to understand their behavior deeply. As one of the most fundamental topics, location estimation attracts more and more research efforts. Different from the previous literature, we find that user’s location is strongly related to user interest. Based on this, we first build a detection model to mine user interest from short text. We then establish the mapping between location function and user interest before presenting an efficient framework to predict the user’s location with convincing fidelity. Thorough evaluations and comparisons on an authentic data set show that our proposed model significantly outperforms the state-of-the-arts approaches. Moreover, the high efficiency of our model also guarantees its applicability in real-world scenarios.