Papers by Bonan Min
Measure Country-Level Socio-Economic Indicators with Streaming News: An Empirical Study (D19-1)
Copied to clipboard
| Challenge: | a large number of indicators are difficult to measure, such as unemployment rate . a novel approach to measure socio-economic indicators with news events is proposed . |
| Approach: | They propose an event-centric indicator measure to extract news events from streaming news . they show strong correlations between ECIM values and representative indicators . |
| Outcome: | The proposed method is effective and correlated with several indicators . it is based on events reported in streaming news . |
Unsupervised Domain Adaptation for Joint Information Extraction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Current JIE methods focus on standard supervised learning setting where training and test data come from the same domain. |
| Approach: | They propose a method to induce domain-invariant representations for the tasks in JIE by a generalized version of domain-adversarial learning. |
| Outcome: | The proposed method improves out-of-domain performance for current pipeline approaches for all IE tasks. |
Modal Dependency Parsing via Language Model Priming (2022.naacl-main)
Copied to clipboard
| Challenge: | modal dependency parsing is a task of parse a text into its modal dependence structure . the root node of an MDS is always the author of a document, the ultimate source of information sources . |
| Approach: | They propose a modal dependency parser based on priming pre-trained language models and evaluate it on two data sets. |
| Outcome: | The proposed parser improves on two data sets. |
FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction (2022.naacl-demo)
Copied to clipboard
| Challenge: | Existing active learning frameworks require long time between annotation batches due to time-consuming nature of model training and data selection. |
| Approach: | They propose a small proxy network to synchronize the proxy network with the main large model to ensure appropriateness of the selected annotation examples for the main model. |
| Outcome: | The proposed framework can support multiple languages and is available on github and demo website. |
Weakly Supervised Subevent Knowledge Acquisition (2020.emnlp-main)
Copied to clipboard
| Challenge: | Subevents elaborate an event and exist in event descriptions. |
| Approach: | They propose a weakly supervised approach to extract subevent relation tuples from text . they then use the initial seed subeven pairs to train a contextual classifier . |
| Outcome: | The proposed method is high quality and covers a wide range of event types. |
ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations (2022.naacl-demo)
Copied to clipboard
| Challenge: | Information Extraction (IE) analysts use supervised machine learning to define the schema and build a training corpus with annotated examples. |
| Approach: | They propose a workflow where the analyst verbalizes the entities/relations, which are then used by a Textual Entailment model to perform zero-shot IE. |
| Outcome: | The proposed workflow performs very well on four IE tasks with a single user interface and a video demonstration is available on vimeo. |
Factuality Assessment as Modal Dependency Parsing (2021.acl-long)
Copied to clipboard
| Challenge: | a critical step towards factuality assessment is to determine the factuality of events in text. |
| Approach: | They propose a modal dependency parsing task that assesses the factuality of events in text . they crowdsource a large-scale data set annotated with modal dependence structures . |
| Outcome: | The proposed model outperforms the pipeline model in factuality assessment . the proposed model is based on a crowdsourced dataset . |
Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent work shows that Relation Extraction tasks can be recasted as Textual Entailment tasks using verbalizations. |
| Approach: | They propose to recasted RE tasks as Textual Entailment tasks using verbalizations . they show that entailment reduces the need for manual annotation to 50% and 20% . |
| Outcome: | The proposed method reduces the need for manual annotation to 50% and 20% in event argument extraction tasks while achieving the same performance as with full training. |
Document-Level Event Argument Extraction via Optimal Transport (2022.findings-acl)
Copied to clipboard
| Challenge: | Prior work on event-level EAE models ignore syntactic structures for documents . prior work on EE is restricted to sentence-level setting where event triggers and arguments are assumed to appear in the same sentences. |
| Approach: | They propose to employ Optimal Transport to induce structures of documents based on sentence-level syntactic structures and tailored to EAE task. |
| Outcome: | The proposed model is effective in document-level EAE, with a new constraint on unrelated context words. |
Open Domain Question Answering with Conflicting Contexts (2025.findings-naacl)
Copied to clipboard
Siyi Liu, Qiang Ning, Kishaloy Halder, Zheng Qi, Wei Xiao, Phu Mon Htut, Yi Zhang, Neha Anna John, Bonan Min, Yassine Benajiba, Dan Roth
| Challenge: | Open domain question answering systems often rely on information retrieved from large collections of text to answer questions. |
| Approach: | They evaluate and benchmark three powerful Large Language Models with a dataset . they find that 25% of unambiguous open domain questions can lead to conflicting contexts . |
| Outcome: | The proposed model can't be used to answer questions with conflicting contexts . it can be fine tuned to provide richer information into the model's training . |
Annotating Temporal Dependency Graphs via Crowdsourcing (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing temporal annotation schemes have been limited due to the complexity of temporal relations between events. |
| Approach: | They propose to build a corpus of Wikinews articles annotated with temporal dependency graphs . they also propose a crowdsourcing strategy to annotate TDGs based on the corpus . |
| Outcome: | The proposed method achieves a good trade-off between completeness and practicality in temporal annotation. |
Exploring Contextualized Neural Language Models for Temporal Dependency Parsing (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows that deep contextualized language models (LMs) can extract temporal relations between events and time expressions. |
| Approach: | They propose a temporal relation extraction technique which extracts temporal relations between events and time expressions. |
| Outcome: | The proposed method significantly improves temporal dependency parsing, the authors show . their work compares the proposed method to other methods and shows where they may fail . |
Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models that perform information extraction tasks manually assume heuristic dependency between the task instances and mean-field factorization for the joint distribution of instance labels. |
| Approach: | They propose to induce a dependency graph among task instances to boost representation learning by estimating their joint distribution via Conditional Random Fields. |
| Outcome: | The proposed model outperforms previous models on multiple IE tasks across 5 datasets and 2 languages. |
Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on IE tasks that use two types of dependencies is not optimal . emr, event trigger detection, event argument extraction, and relation extraction are challenging . |
| Approach: | They propose a model that learns cross-task dependencies from data . they treat each task instance as a node in a dependency graph . |
| Outcome: | The proposed model outperforms strong baselines over four datasets with different languages. |
ExcavatorCovid: Extracting Events and Relations from Text Corpora for Temporal and Causal Analysis for COVID-19 (2021.emnlp-demo)
Copied to clipboard
| Challenge: | a new machine reading system ingests open-source text documents to analyze COVID-19 events . the system extracts COVId-19 related events and relations between them . |
| Approach: | They propose a machine reading system that ingests open-source text documents and extracts COVID-19 related events and relations between them. |
| Outcome: | The proposed system extracts COVID-19 related events and relations from open-source text . it will help government agencies alleviate the information overload and respond to COVId-19 . |
Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning (2023.acl-long)
Copied to clipboard
Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, Jie Ma, Patrick Ng, Zhiguo Wang, Bonan Min, William Yang Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang
| Challenge: | Existing methods for data-to-text generation focus on specific types of structured data. |
| Approach: | They propose a method that provides a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. |
| Outcome: | The proposed method improves zero-shot and few-shot scenarios and can adapt to new structured data. |
Towards Machine Reading for Interventions from Humanitarian-Assistance Program Literature (D19-1)
Copied to clipboard
| Challenge: | a complex socio-political system is causing problems such as food insecurity . a first step is to extract past interventions and when and where they have been applied . |
| Approach: | They develop an automatic extraction system to extract past interventions from texts . they analyze a corpus annotated with interventions to foster research . |
| Outcome: | The proposed system extracts past interventions and when and where they have been applied from text . it shows early, encouraging results on extracting interventions . |
Aligning to Constraints for Data-Efficient Language Model Customization (2025.findings-naacl)
Copied to clipboard
Fei Wang, Chao Shang, Shuai Wang, Sarthak Jain, Qiang Ning, Bonan Min, Vittorio Castelli, Yassine Benajiba, Dan Roth
| Challenge: | General-purpose language models (LMs) are aligned to diverse user intents, but fall short when it comes to specific applications. |
| Approach: | They propose a framework that uses constraints to automatically produce supervision signals for user alignment with constraints. |
| Outcome: | The proposed framework can produce supervision signals for user alignment with constraints. |
A Multi-Modal Multilingual Benchmark for Document Image Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing document image classification datasets have several limitations and we present two new datasets that overcome these limitations. |
| Approach: | They propose to use two newly curated multilingual datasets that overcome these limitations and propose to develop multilingual Document AI models. |
| Outcome: | The proposed datasets overcome limitations in document image classification and open the door for future research into improving Document AI models. |
Benchmarking Query-Conditioned Natural Language Inference (2025.findings-acl)
Copied to clipboard
| Challenge: | Query-conditioned natural language inference (QC-NLI) is a new approach to detect inconsistencies in large language models. |
| Approach: | They propose a task of Query-Conditioned Natural Language Inference to determine the semantic relationship between two documents conditioned on a query. |
| Outcome: | The proposed task is based on a query-conditioned natural language inference (QC-NLI) it is used to determine the relationship between the premise and hypothesis given a given query. |
RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering (2024.emnlp-main)
Copied to clipboard
Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli
| Challenge: | Existing datasets for question answering based on retrieval augmented generation (RAG-QA) are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization. |
| Approach: | They propose a dataset that integrates short extractive answers from multiple documents into a single coherent narrative. |
| Outcome: | The proposed dataset integrates short extractive answers from multiple documents into a single coherent narrative, covering 26K queries and large corpora across seven different domains. |
Rapid Customization for Event Extraction (P19-3)
Copied to clipboard
| Challenge: | a novel system allows users to customize event extraction to find new event types and their arguments. |
| Approach: | They propose a system that allows a user to find, expand and filter event triggers by exploring an unannotated development corpus. |
| Outcome: | The proposed system can find, expand and filter event triggers from an unannotated development corpus . it trains a generic argument attachment model for extracting Actor, Place, and Time . |
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models (2024.emnlp-main)
Copied to clipboard
Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang
| Challenge: | Modern language models fail to follow human instructions while being faithful . a trade-off exists between instruction following and faithfulness when training LMs . |
| Approach: | They propose a method that relies on Reject-sampling by Self-instruct with Continued Fine-tuning to train LMs to follow human instructions while being faithful. |
| Outcome: | The proposed method outperforms vanilla MTL with high-quality data, but with significantly smaller data. |
Towards Few-Shot Event Mention Retrieval: An Evaluation Framework and A Siamese Network Approach (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for event extraction are "one size fits all" and are not adaptable to new event types or domains of interest. |
| Approach: | They propose a few-shot Event Mention Retrieval task to retrieve event mentions from text . they use existing event datasets such as ACE and a Siamese Network approach . |
| Outcome: | The proposed approach lowers the bar of specifying event-centric information needs. |
When ACE met KBP: End-to-End Evaluation of Knowledge Base Population with Component-level Annotation (L18-1)
Copied to clipboard
| Challenge: | Automating constructing a Knowledge Base from unstructured text is a goal of natural language processing. |
| Approach: | They propose a method to evaluate a Knowledge Base population from unstructured text . they propose bootstrap resampling to provide statistical significance to the results . |
| Outcome: | The proposed method uses component-level annotations to evaluate Cold Start KBP . it also uses bootstrap resampling to provide statistical significance to the results reported . |
Modeling Document-Level Context for Event Detection via Important Context Selection (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Event Detection (ED) do not encode long-range document-level context . e.g., BERT cannot encode long text-level contextual information . |
| Approach: | They propose a method to model document-level context for Event Detection using transformer-based language models. |
| Outcome: | The proposed model can predict event prediction of target sentence in document-level context . the proposed model is effective on multiple benchmark datasets . |
Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class Alignments (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to crosslingual Relation and Event Extraction (REE) suffer from monolingual bias due to training of models on source language data. |
| Approach: | They propose to use unlabeled data in target language to aid alignment of crosslingual representations by fooling a language discriminator. |
| Outcome: | The proposed method significantly advances the state-of-the-art in crosslingual REE tasks. |
CiteEval: Principle-Driven Citation Evaluation for Source Attribution (2025.acl-long)
Copied to clipboard
Yumo Xu, Peng Qi, Jifan Chen, Kunlun Liu, Rujun Han, Lan Liu, Bonan Min, Vittorio Castelli, Arshit Gupta, Zhiguo Wang
| Challenge: | Current evaluation frameworks rely on NLI to assess binary or ternary support from cited sources, which is suboptimal for citation evaluation. |
| Approach: | They propose a citation evaluation framework based on fine-grained citation ratings within a broad context and construct a multi-domain benchmark with high-quality human annotations. |
| Outcome: | The proposed framework provides a high-quality human annotation benchmark and a suite of model-based metrics that exhibit strong correlation with human judgments. |
Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 Training (2023.findings-acl)
Copied to clipboard
| Challenge: | Relation Extraction (RE) is the task of identifying semantic relation between entities mentioned in text. |
| Approach: | They propose a framework to automatically generate labeled data for Relation Extraction . they propose 'reward function' to update pre-trained language model for RE . |
| Outcome: | The proposed framework generates labeled data for relation extraction using a pre-trained language model and a meta learning approach to improve the generated samples. |
Efficient Table Retrieval and Understanding with Multimodal Large Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Tabular data is often captured in image form across a wide range of real-world scenarios. |
| Approach: | They propose a framework that enables MLLMs to answer queries over large tables. |
| Outcome: | The proposed framework outperforms existing methods by 7.0% in retrieval recall and 6.1% in answer accuracy on a newly constructed dataset with 48,504 unique tables. |