Papers by Xiang Dai
On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Evidence-enhanced detectors are able to detect malicious social text, but they are prone to evidence pollution. |
| Approach: | They propose three defense strategies to mitigate evidence pollution by large language models by machine-generated text detection and a mixture of experts. |
| Outcome: | The proposed defense strategies could mitigate evidence pollution, but they faced limitations for practical employment. |
MultiFin: A Dataset for Multilingual Financial NLP (2023.findings-eacl)
Copied to clipboard
| Challenge: | Multilingual models are needed to process financial text, which is produced across the world and requires a large dataset. |
| Approach: | They propose to annotate a publicly available financial dataset using a hierarchical label structure and an annotation schema based on a real-world application. |
| Outcome: | The proposed model can be used in high-resource languages, but there is room for improvement in low-resourced languages. |
Revisiting Transformer-based Models for Long Document Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent literature in text classification is biased towards short text sequences . multi-page multi-paragraph documents cannot be efficiently encoded by vanilla transformers based on short text. |
| Approach: | They compare different Transformer-based Long Document Classification approaches to mitigate the computational overhead of vanilla transformers to encode much longer text. |
| Outcome: | The proposed models can process longer text and provide practical advice for long document classification tasks. |
NNE: A Dataset for Nested Named Entity Recognition in English Newswire (P19-1)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is widely used in downstream tasks but most tools focus on flat mention structure over coarse schemas. |
| Approach: | They describe a fine-grained, nested named entity dataset over the Wall Street Journal portion of the Penn Treebank. |
| Outcome: | The proposed dataset comprises 279,795 mentions of 114 entity types with up to 6 layers of nesting. |
An Analysis of Simple Data Augmentation for Named Entity Recognition (2020.coling-main)
Copied to clipboard
| Challenge: | Recent studies have focused on using data augmentation techniques on sentence-level and sentence-pair natural language processing tasks such as text classification. |
| Approach: | They propose to use data augmentation techniques for named entity recognition to increase model performance. |
| Outcome: | The proposed techniques boost performance for both recurrent and transformer-based models, especially for small training sets. |
Named Entity Recognition for Social Media Texts with Semantic Augmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts. |
| Approach: | They propose a neural-based approach to named entity recognition for social media texts . they obtain augmented semantic information from a large-scale corpus and encode it . |
| Outcome: | The proposed approach outperforms existing approaches on three social media datasets. |
Understanding Faithfulness and Reasoning of Large Language Models on Plain Biomedical Summaries (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Generating plain biomedical summaries with Large Language Models (LLMs) can enhance access to biomedically knowledge. |
| Approach: | They propose a benchmark dataset with expert-annotated Faithfulness and Reasoning on plain biomedical summaries. |
| Outcome: | The proposed dataset shows that LLMs perform poorly in generating faithful biomedical summaries and that abstractiveness and faithfulness are negatively correlated. |
Born Differently Makes a Difference: Counterfactual Study of Bias in Biography Generation from a Data-to-Text Perspective (2024.acl-short)
Copied to clipboard
| Challenge: | Current research shows that biographies reflect bias from society such as gender and religions. |
| Approach: | They propose a method that manipulates the personal attributes of interest while keeping the co-occurring attributes unchanged. |
| Outcome: | The proposed method expands the analysis of gender-centered bias in text generation. |
Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR). |
| Approach: | They propose a Multi-Attentive Neural Fusion model to fuse linguistic evidence and semantic connection for IDRR by using a Dual Attention Network and an Offset Matrix Network. |
| Outcome: | The proposed model achieves state-of-the-art on the PDTB 3.0 corpus. |
Using Similarity Measures to Select Pretraining Data for NER (N19-1)
Copied to clipboard
| Challenge: | Existing studies on how to select appropriate data to pretrain word vectors or LMs are lacking. |
| Approach: | They propose to quantify aspects of similarity between pretraining and target data. |
| Outcome: | The proposed measures are good predictors of the usefulness of pretrained models for Named Entity Recognition over 30 data pairs. |
Recognizing Complex Entity Mentions: A Review and Future Directions (P18-3)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a task of identifying and classifying named entities (NE) within text. |
| Approach: | They review existing methods for identifying and classifying named entities within text . they identify the research gap and propose a new approach to tackle these problems . |
| Outcome: | The proposed methods address the identified identified gaps in the literature and provide recommendations for future work. |
An Effective Transition-based Model for Discontinuous NER (2020.acl-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) data sets often contain mentions consisting of discontinuous spans. |
| Approach: | They propose a transition-based model with generic neural encoding for discontinuous NER that can recognize discontinuous mentions without sacrificing the accuracy on continuous mentions. |
| Outcome: | The proposed model can recognize discontinuous mentions without sacrificing accuracy on continuous mentions. |
How Do Social Bots Participate in Misinformation Spread? A Comprehensive Dataset and Analysis (2025.emnlp-main)
Copied to clipboard
| Challenge: | Social media platforms provide an ideal environment to spread misinformation, where social bots can accelerate the spread. |
| Approach: | They construct a large-scale dataset that includes annotations for misinformation and social bots on the Sina Weibo platform. |
| Outcome: | The proposed dataset contains 65,749 social bots and 345,886 genuine accounts, annotated using a weakly supervised annotator. |
mDAPT: Multilingual Domain Adaptive Pretraining in a Single Model (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain-specific multilingual pretraining data is difficult to obtain due to regulations, legislation, or simply a lack of language- and domain- specific text. |
| Approach: | They propose to continue pretraining a language model on domain-specific unlabelled text . this allows for better modelling of text for downstream tasks within the domain . |
| Outcome: | The proposed approach outperforms the general multilingual model and performs close to its monolingual counterpart. |
A Critical Look at Meta-evaluating Summarisation Evaluation Metrics (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Effective summarisation evaluation metrics enable researchers and practitioners to compare different summarization systems efficiently. |
| Approach: | They argue that evaluation metrics are primarily meta-evaluated on news summarisation datasets and that there has been a noticeable shift in research focus towards evaluating the faithfulness of generated summaries. |
| Outcome: | The evaluation metrics are primarily meta-evaluated on news summarisation datasets and there has been a noticeable shift in research focus towards evaluating the faithfulness of generated summaries. |
Can VLMs Actually See and Read? A Survey on Modality Collapse in Vision-Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Vision-language models integrate textual and visual information, enabling them to process visual inputs and generate predictions. |
| Approach: | They review work on modality collapse analysis to provide insights into the reason for this unintended behavior and review probing studies for fine-grained vision-language understanding. |
| Outcome: | The proposed models can achieve competitive performance in vision-language tasks despite relying heavily on textual information and ignoring visual information. |
Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that domain-specific BERT models can be improved when in-domain data is used for pretraining. |
| Approach: | They propose to use Twitter and forum text as pretraining sources for two BERT models and use similarity measures to nominate in-domain data for pretraining. |
| Outcome: | The proposed method can be used to improve performance on downstream tasks by using in-domain data. |
Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing prompt-tuning methods for event argument extraction lack entity information . eAE is a key step of event extraction, but it requires a pre-trained language model to extract event arguments. |
| Approach: | They propose a prompt-tuning method that takes advantage of entity information and pre-trained language models. |
| Outcome: | The proposed method outperforms the state-of-the-art prompt-tuning methods on an english dataset. |
ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition (2022.coling-1)
Copied to clipboard
| Challenge: | Existing paradigms for Implicit Discourse Relation Recognition (IDRR) do not exploit linguistic evidence embedded in the pre-training process. |
| Approach: | They propose a new paradigm to detect and classify relation sense between two text segments without an explicit connective. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art algorithms even with fewer training data. |
The More, The Better? A Critical Study of Multimodal Context in Radiology Report Summarization (2025.findings-emnlp)
Copied to clipboard
Mong Yuan Sim, Wei Emma Zhang, Xiang Dai, Biaoyan Fang, Sarbin Ranjitkar, Arjun Burlakoti, Jamie Taylor, Haojie Zhuang
| Challenge: | Current multimodal summarization models often fail to utilize radiology images in summarizing Findings section. |
| Approach: | They conduct a thorough analysis to determine whether current multimodal summarization models can utilize radiology images in summarizing Findings section. |
| Outcome: | The Impression section plays a crucial role in communication between radiologists and physicians. |