Ting Wang


2024

pdf
Recommending Missed Citations Identified by Reviewers: A New Task, Dataset and Baselines
Kehan Long | Shasha Li | Pancheng Wang | Chenlong Bao | Jintao Tang | Ting Wang
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Citing comprehensively and appropriately has become a challenging task with the explosive growth of scientific publications. Current citation recommendation systems aim to recommend a list of scientific papers for a given text context or a draft paper. However, none of the existing work focuses on already included citations of full papers, which are imperfect and still have much room for improvement. In the scenario of peer reviewing, it is a common phenomenon that submissions are identified as missing vital citations by reviewers. This may lead to a negative impact on the credibility and validity of the research presented. To help improve citations of full papers, we first define a novel task of Recommending Missed Citations Identified by Reviewers (RMC) and construct a corresponding expert-labeled dataset called CitationR. We conduct an extensive evaluation of several state-of-the-art methods on CitationR. Furthermore, we propose a new framework RMCNet with an Attentive Reference Encoder module mining the relevance between papers, already-made citations, and missed citations. Empirical results prove that RMC is challenging, with the proposed architecture outperforming previous methods in all metrics. We release our dataset and benchmark models to motivate future research on this challenging new task.

pdf
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
Tianrong Zhang | Zhaohan Xi | Ting Wang | Prasenjit Mitra | Jinghui Chen
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed to few-shot fine-tuning and prompting as the most popular training paradigms for natural language processing (NLP) models. Nevertheless, existing studies have shown that these NLP models can be backdoored such that model behavior is manipulated when trigger tokens are presented.In this paper, we propose PromptFix, a novel backdoor mitigation strategy for NLP models via adversarial prompt-tuning in few-shot settings.Unlike existing NLP backdoor removal methods, which rely on accurate trigger inversion and subsequent model fine-tuning, PromptFix keeps the model parameters intact and only utilizes two extra sets of soft tokens which approximate the trigger and counteract it respectively. The use of soft tokens and adversarial optimization eliminates the need to enumerate possible backdoor configurations and enables an adaptive balance between trigger finding and preservation of performance.Experiments with various backdoor attacks validate the effectiveness of the proposed method and the performances when domain shift is present further shows PromptFix’s applicability to models pretrained on unknown data source which is the common case in prompt tuning scenarios.

2023

pdf
Improving Image Captioning via Predicting Structured Concepts
Ting Wang | Weidong Chen | Yuanhe Tian | Yan Song | Zhendong Mao
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly. Although promising results on concept prediction were obtained, the aforementioned studies normally ignore the relationship among concepts, which relies on not only objects in the image, but also word dependencies in the text, so that offers a considerable potential for improving the process of generating good descriptions. In this paper, we propose a structured concept predictor (SCP) to predict concepts and their structures, then we integrate them into captioning, so that enhance the contribution of visual signals in this task via concepts and further use their relations to distinguish cross-modal semantics for better description generation. Particularly, we design weighted graph convolutional networks (W-GCN) to depict concept relations driven by word dependencies, and then learns differentiated contributions from these concepts for following decoding process. Therefore, our approach captures potential relations among concepts and discriminatively learns different concepts, so that effectively facilitates image captioning with inherited information across modalities. Extensive experiments and their results demonstrate the effectiveness of our approach as well as each proposed module in this work.

2022

pdf
Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction
Kunyuan Pang | Haoyu Zhang | Jie Zhou | Ting Wang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems. FCLC first train a coarse backbone model as a feature extractor and noise estimator. Loss correction is then applied to each feature cluster, learning directly from the noisy labels. Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems. Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias. We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance.

pdf
DUTNLP Machine Translation System for WMT22 General MT Task
Ting Wang | Huan Liu | Junpeng Liu | Degen Huang
Proceedings of the Seventh Conference on Machine Translation (WMT)

This paper describes DUTNLP Lab’s submission to the WMT22 General MT Task on four translation directions: English to/from Chinese and English to/from Japanese under the constrained condition. Our primary system are built on several Transformer variants which employ wider FFN layer or deeper encoder layer. The bilingual data are filtered by detailed data pre-processing strategies and four data augmentation methods are combined to enlarge the training data with the provided monolingual data. Several common methods are also employed to further improve the model performance, such as fine-tuning, model ensemble and post-editing. As a result, our constrained systems achieve 29.01, 63.87, 41.84, and 24.82 BLEU scores on Chinese-to-English, English-to-Chinese, English-to-Japanese, and Japanese-to-English, respectively.

pdf
Multi-Document Scientific Summarization from a Knowledge Graph-Centric View
Pancheng Wang | Shasha Li | Kunyuan Pang | Liangliang He | Dong Li | Jintao Tang | Ting Wang
Proceedings of the 29th International Conference on Computational Linguistics

Multi-Document Scientific Summarization (MDSS) aims to produce coherent and concise summaries for clusters of topic-relevant scientific papers. This task requires precise understanding of paper content and accurate modeling of cross-paper relationships. Knowledge graphs convey compact and interpretable structured information for documents, which makes them ideal for content modeling and relationship modeling. In this paper, we present KGSum, an MDSS model centred on knowledge graphs during both the encoding and decoding process. Specifically, in the encoding process, two graph-based modules are proposed to incorporate knowledge graph information into paper encoding, while in the decoding process, we propose a two-stage decoder by first generating knowledge graph information of summary in the form of descriptive sentences, followed by generating the final summary. Empirical results show that the proposed architecture brings substantial improvements over baselines on the Multi-Xscience dataset.

2021

pdf
Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting
Yi Feng | Ting Wang | Chuanyi Li | Vincent Ng | Jidong Ge | Bin Luo | Yucheng Hu | Xiaopeng Zhang
Findings of the Association for Computational Linguistics: EMNLP 2021

User targeting is an essential task in the modern advertising industry: given a package of ads for a particular category of products (e.g., green tea), identify the online users to whom the ad package should be targeted. A (ad package specific) user targeting model is typically trained using historical clickthrough data: positive instances correspond to users who have clicked on an ad in the package before, whereas negative instances correspond to users who have not clicked on any ads in the package that were displayed to them. Collecting a sufficient amount of positive training data for training an accurate user targeting model, however, is by no means trivial. This paper focuses on the development of a method for automatic augmentation of the set of positive training instances. Experimental results on two datasets, including a real-world company dataset, demonstrate the effectiveness of our proposed method.

2008

pdf
Story Link Detection based on Dynamic Information Extending
Xiaoyan Zhang | Ting Wang | Huowang Chen
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf
Semantic Role Labeling of Chinese Using Transductive SVM and Semantic Heuristics
Yaodong Chen | Ting Wang | Huowang Chen | Xishan Xu
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-II