@article{liu2024open,title={Open domain question answering with conflicting contexts},author={Liu, Siyi and Ning, Qiang and Halder, Kishaloy and Xiao, Wei and Qi, Zheng and Htut, Phu Mon and Zhang, Yi and John, Neha Anna and Min, Bonan and Benajiba, Yassine and Roth, Dan},journal={Findings of NAACL},year={2025}}
LLM
Aligning to Constraints for Data-Efficient Language Model Customization
Fei Wang, Chao Shang, Shuai Wang, Sarthak Jain, Qiang Ning, Bonan Min, Vittorio Castelli, Yassine Benajiba, and Dan Roth
@article{wang-etal-2025-aligning,title={Aligning to Constraints for Data-Efficient Language Model Customization},author={Wang, Fei and Shang, Chao and Wang, Shuai and Jain, Sarthak and Ning, Qiang and Min, Bonan and Castelli, Vittorio and Benajiba, Yassine and Roth, Dan},journal={Findings of NAACL},year={2025}}
2022
NLP
PInKS: Preconditioned commonsense inference with minimal supervision
Ehsan Qasemi, Piyush Khanna, Qiang Ning, and Muhao Chen
@article{qasemi2022pinks,title={PInKS: Preconditioned commonsense inference with minimal supervision},author={Qasemi, Ehsan and Khanna, Piyush and Ning, Qiang and Chen, Muhao},journal={AACL},year={2022}}
NLP
Answer Consolidation: Formulation and Benchmarking
Wenxuan Zhou, Qiang Ning, Heba Elfardy, Kevin Small, and Muhao Chen
Current question answering (QA) systems primarily consider the single-answer scenario, where each question is assumed to be paired with one correct answer. However, in many real-world QA applications, multiple answer scenarios arise where consolidating answers into a comprehensive and non-redundant set of answers is a more efficient user interface. In this paper, we formulate the problem of answer consolidation, where answers are partitioned into multiple groups, each representing different aspects of the answer set. Then, given this partitioning, a comprehensive and non-redundant set of answers can be constructed by picking one answer from each group. To initiate research on answer consolidation, we construct a dataset consisting of 4,699 questions and 24,006 sentences and evaluate multiple models. Despite a promising performance achieved by the best-performing supervised models, we still believe this task has room for further improvements.
@article{zhou-etal-2022-answer,title={Answer Consolidation: Formulation and Benchmarking},author={Zhou, Wenxuan and Ning, Qiang and Elfardy, Heba and Small, Kevin and Chen, Muhao},journal={NAACL},year={2022}}
NLP
Extracting Temporal Event Relation with Syntax-guided Graph Transformer
Extracting temporal relations (e.g., before, after, and simultaneous) among events is crucial to natural language understanding. One of the key challenges of this problem is that when the events of interest are far away in text, the context in-between often becomes complicated, making it challenging to resolve the temporal relationship between them. This paper thus proposes a new Syntax-guided Graph Transformer network (SGT) to mitigate this issue, by (1) explicitly exploiting the connection between two events based on their dependency parsing trees, and (2) automatically locating temporal cues between two events via a novel syntax-guided attention mechanism. Experiments on two benchmark datasets, MATRES and TB-DENSE, show that our approach significantly outperforms previous state-of-the-art methods on both end-to-end temporal relation extraction and temporal relation classification with up to 7.9% absolute F-score gain; This improvement also proves to be robust on the contrast set of MATRES. We will make all the programs publicly available once the paper is accepted.
@article{zhang-etal-2022-extracting,title={Extracting Temporal Event Relation with Syntax-guided Graph Transformer},author={Zhang, Shuaicheng and Ning, Qiang and Huang, Lifu},journal={Findings of NAACL},year={2022}}
NLP
A Meta-framework for Spatiotemporal Quantity Extraction from Text
News events are often associated with quantities (e.g., the number of COVID-19 patients or the number of arrests in a protest), and it is often important to extract their type, time, and location from unstructured text in order to analyze these quantity events. This paper thus formulates the NLP problem of spatiotemporal quantity extraction, and proposes the first meta-framework for solving it. This meta-framework contains a formalism that decomposes the problem into several information extraction tasks, a shareable crowdsourcing pipeline, and transformer-based baseline models. We demonstrate the meta-framework in three domains—the COVID-19 pandemic, Black Lives Matter protests, and 2020 California wildfires—to show that the formalism is general and extensible, the crowdsourcing pipeline facilitates fast and high-quality data annotation, and the baseline system can handle spatiotemporal quantity extraction well enough to be practically useful. We release all resources for future research on this topic at \urlhttps://github.com/steqe.
@article{ning-etal-2022-meta,title={A Meta-framework for Spatiotemporal Quantity Extraction from Text},author={Ning, Qiang and Zhou, Ben and Wu, Hao and Peng, Haoruo and Fan, Chuchu and Gardner, Matt},journal={ACL},year={2022}}
Control
Controller Synthesis for Linear System With Reach-Avoid Specifications
@article{9390193,bibtex_show=true,author={Fan, Chuchu and Qin, Zengyi and Mathur, Umang and Ning, Qiang and Mitra, Sayan and Viswanathan, Mahesh},journal={IEEE Transactions on Automatic Control},title={Controller Synthesis for Linear System With Reach-Avoid Specifications},year={2022},volume={67},number={4},pages={1713-1727},keywords={Trajectory;Linear systems;Encoding;Ellipsoids;Control systems;Computational modeling;Benchmark testing;Controller synthesis;disturbance;linear system;reach-avoid specification},doi={10.1109/TAC.2021.3069723}}
2021
NLP
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations
Rujun Han, I-Hung Hsu, Jiao Sun, Julia Baylon, Qiang Ning, Dan Roth, and Nanyun Peng
Understanding how events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus mostly on event arguments or temporal relations. While these tasks partially evaluate machines’ ability of narrative understanding, human-like reading comprehension requires the capability to process event-based information beyond arguments and temporal reasoning. For example, to understand causality between events, we need to infer motivation or purpose; to establish event hierarchy, we need to understand the composition of events. To facilitate these tasks, we introduce **ESTER**, a comprehensive machine reading comprehension (MRC) dataset for Event Semantic Relation Reasoning. The dataset leverages natural language queries to reason about the five most common event semantic relations, provides more than 6K questions, and captures 10.1K event relation pairs. Experimental results show that the current SOTA systems achieve 22.1%, 63.3% and 83.5% for token-based exact-match (**EM**), **F1** and event-based **HIT@1** scores, which are all significantly below human performances (36.0%, 79.6%, 100% respectively), highlighting our dataset as a challenging benchmark.
@article{han-etal-2021-ester,title={{ESTER}: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations},author={Han, Rujun and Hsu, I-Hung and Sun, Jiao and Baylon, Julia and Ning, Qiang and Roth, Dan and Peng, Nanyun},journal={EMNLP},year={2021}}
Real-world applications often require improved models by leveraging *a range of cheap incidental supervision signals*. These could include partial labels, noisy labels, knowledge-based constraints, and cross-domain or cross-task annotations – all having statistical associations with gold annotations but not exactly the same. However, we currently lack a principled way to measure the benefits of these signals to a given target task, and the common practice of evaluating these benefits is through exhaustive experiments with various models and hyperparameters. This paper studies whether we can, *in a single framework, quantify the benefits of various types of incidental signals for a given target task without going through combinatorial experiments*. We propose a unified PAC-Bayesian motivated informativeness measure, PABI, that characterizes the uncertainty reduction provided by incidental supervision signals. We demonstrate PABI’s effectiveness by quantifying the value added by various types of incidental signals to sequence tagging tasks. Experiments on named entity recognition (NER) and question answering (QA) show that PABI’s predictions correlate well with learning performance, providing a promising way to determine, ahead of learning, which supervision signals would be beneficial.
@article{he-etal-2021-foreseeing,title={Foreseeing the Benefits of Incidental Supervision},author={He, Hangfeng and Zhang, Mingyuan and Ning, Qiang and Roth, Dan},journal={EMNLP},year={2021}}
NLP
SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning
Roshanak Mirzaee, Hossein Rajaby Faghihi, Qiang Ning, and Parisa Kordjamshidi
This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs’ capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.
@article{mirzaee-etal-2021-spartqa,title={{SPARTQA}: A Textual Question Answering Benchmark for Spatial Reasoning},author={Mirzaee, Roshanak and Rajaby Faghihi, Hossein and Ning, Qiang and Kordjamshidi, Parisa},journal={NAACL},year={2021}}
NLP
Temporal Reasoning on Implicit Events from Distant Supervision
Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, and Dan Roth
We propose TRACIE, a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events—events that are not mentioned explicitly in natural language text but can be inferred from it. This introduces a new challenge in temporal reasoning research, where prior work has focused on explicitly mentioned events. Human readers can infer implicit events via commonsense reasoning, resulting in a more comprehensive understanding of the situation and, consequently, better reasoning about time. We find, however, that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events. To address this, we propose a neuro-symbolic temporal reasoning model, SymTime, which exploits distant supervision signals from large-scale text and uses temporal rules to combine start times and durations to infer end times. SymTime outperforms strong baseline systems on TRACIE by 5%, and by 11% in a zero prior knowledge training setting. Our approach also generalizes to other temporal reasoning tasks, as evidenced by a gain of 1%-9% on MATRES, an explicit event benchmark.
@article{zhou-etal-2021-temporal,title={Temporal Reasoning on Implicit Events from Distant Supervision},author={Zhou, Ben and Richardson, Kyle and Ning, Qiang and Khot, Tushar and Sabharwal, Ashish and Roth, Dan},journal={NAACL},year={2021}}
NLP
Event Time Extraction and Propagation via Graph Attention Networks
Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong, and Dan Roth
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work. This problem is challenging due to the inherent ambiguity of language and the requirement for information propagation over inter-related events. This paper first formulates this problem based on a 4-tuple temporal representation used in entity slot filling, which allows us to represent fuzzy time spans more conveniently. We then propose a graph attention network-based approach to propagate temporal information over document-level event graphs constructed by shared entity arguments and temporal relations. To better evaluate our approach, we present a challenging new benchmark on the ACE2005 corpus, where more than 78% of events do not have time spans mentioned explicitly in their local contexts. The proposed approach yields an absolute gain of 7.0% in match rate over contextualized embedding approaches, and 16.3% higher match rate compared to sentence-level manual event time argument annotation.
@article{wen-etal-2021-event,title={Event Time Extraction and Propagation via Graph Attention Networks},author={Wen, Haoyang and Qu, Yanru and Ji, Heng and Ning, Qiang and Han, Jiawei and Sil, Avi and Tong, Hanghang and Roth, Dan},journal={NAACL},year={2021}}
@article{NEURIPS2020_67ff32d4,author={Wang, Kaifu and Ning, Qiang and Roth, Dan},journal={NeurIPS},title={Learnability with Indirect Supervision Signals},year={2020}}
NLP
Evaluating models’ local decision boundaries via contrast sets
Matt Gardner, Yoav Artzi, Victoria Basmova, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, and 2 more authors
@article{gardner2020evaluating,title={Evaluating models' local decision boundaries via contrast sets},author={Gardner, Matt and Artzi, Yoav and Basmova, Victoria and Berant, Jonathan and Bogin, Ben and Chen, Sihao and Dasigi, Pradeep and Dua, Dheeru and Elazar, Yanai and Gottumukkala, Ananth and others},journal={Findings of EMNLP},year={2020}}
NLP
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly stated. However, current machine reading comprehension benchmarks have practically no questions that test temporal phenomena, so systems trained on these benchmarks have no capacity to answer questions such as “what happened before/after [some event]?” We introduce TORQUE, a new English reading comprehension benchmark built on 3.2k news snippets with 21k human-generated questions querying temporal relationships. Results show that RoBERTa-large achieves an exact-match score of 51% on the test set of TORQUE, about 30% behind human performance.
@article{ning-etal-2020-torque,title={{TORQUE}: A Reading Comprehension Dataset of Temporal Ordering Questions},author={Ning, Qiang and Wu, Hao and Han, Rujun and Peng, Nanyun and Gardner, Matt and Roth, Dan},journal={EMNLP},year={2020}}
NLP
Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ
Qiang Ning, Hao Wu, Pradeep Dasigi, Dheeru Dua, Matt Gardner, Robert L. Logan IV, Ana Marasović, and Zhen Nie
High-quality and large-scale data are key to success for AI systems. However, large-scale data annotation efforts are often confronted with a set of common challenges: (1) designing a user-friendly annotation interface; (2) training enough annotators efficiently; and (3) reproducibility. To address these problems, we introduce CROWDAQ, an open-source platform that standardizes the data collection pipeline with customizable user-interface components, automated annotator qualification, and saved pipelines in a re-usable format. We show that CROWDAQ simplifies data annotation significantly on a diverse set of data collection use cases and we hope it will be a convenient tool for the community.
@article{ning-etal-2020-easy,bibtex_show=true,title={Easy, Reproducible and Quality-Controlled Data Collection with {CROWDAQ}},author={Ning, Qiang and Wu, Hao and Dasigi, Pradeep and Dua, Dheeru and Gardner, Matt and Logan IV, Robert L. and Marasovi{\'c}, Ana and Nie, Zhen},journal={EMNLP Demo},year={2020}}
Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, \textitcan we use QAMR (Michael et al., 2017) to improve named entity recognition? We suggest that simply further pre-training BERT is often not the best option, and propose the \textitquestion-answer driven sentence encoding (QuASE) framework. QuASE learns representations from QA data, using BERT or other state-of-the-art contextual language models. In particular, we observe the need to distinguish between two types of sentence encodings, depending on whether the target task is a single- or multi-sentence input; in both cases, the resulting encoding is shown to be an easy-to-use plugin for many downstream tasks. This work may point out an alternative way to supervise NLP tasks.
@article{he-etal-2020-quase,bibtex_show=true,title={{Q}u{ASE}: Question-Answer Driven Sentence Encoding},author={He, Hangfeng and Ning, Qiang and Roth, Dan},journal={ACL},year={2020}}
LLM
Temporal Common Sense Acquisition with Minimal Supervision
Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on such concepts is costly. This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TacoLM, a temporal common sense language model. Our method is shown to give quality predictions of various dimensions of temporal common sense (on UDST and a newly collected dataset from RealNews). It also produces representations of events for relevant tasks such as duration comparison, parent-child relations, event coreference and temporal QA (on TimeBank, HiEVE and MCTACO) that are better than using the standard BERT. Thus, it will be an important component of temporal NLP.
@article{zhou-etal-2020-temporal,bibtex_show=true,title={Temporal Common Sense Acquisition with Minimal Supervision},author={Zhou, Ben and Ning, Qiang and Khashabi, Daniel and Roth, Dan},journal={ACL},year={2020}}
2019
NLP
"Going on a vacation" takes longer than" Going for a walk": A Study of Temporal Commonsense Understanding
@article{zhou2019going,title={"Going on a vacation" takes longer than" Going for a walk": A Study of Temporal Commonsense Understanding},author={Zhou, Ben and Khashabi, Daniel and Ning, Qiang and Roth, Dan},journal={EMNLP},year={2019}}
LLM
KnowSemLM: A Knowledge Infused Semantic Language Model
Story understanding requires developing expectations of what events come next in text. Prior knowledge – both statistical and declarative – is essential in guiding such expectations. While existing semantic language models (SemLM) capture event co-occurrence information by modeling event sequences as semantic frames, entities, and other semantic units, this paper aims at augmenting them with causal knowledge (i.e., one event is likely to lead to another). Such knowledge is modeled at the frame and entity level, and can be obtained either statistically from text or stated declaratively. The proposed method, KnowSemLM, infuses this knowledge into a semantic LM by joint training and inference, and is shown to be effective on both the event cloze test and story/referent prediction tasks.
@article{peng-etal-2019-knowsemlm,bibtex_show=true,title={{K}now{S}em{LM}: A Knowledge Infused Semantic Language Model},author={Peng, Haoruo and Ning, Qiang and Roth, Dan},journal={CoNLL},year={2019}}
NLP
Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction
We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction. The proposed method has two advantages over existing work. First, it improves event representation by allowing the event and relation modules to share the same contextualized embeddings and neural representation learner. Second, it avoids error propagation in the conventional pipeline systems by leveraging structured inference and learning methods to assign both the event labels and the temporal relation labels jointly. Experiments show that the proposed method can improve both event extraction and temporal relation extraction over state-of-the-art systems, with the end-to-end F1 improved by 10% and 6.8% on two benchmark datasets respectively.
@article{han-etal-2019-joint,bibtex_show=true,title={Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction},author={Han, Rujun and Ning, Qiang and Peng, Nanyun},journal={EMNLP},year={2019}}
NLP
An Improved Neural Baseline for Temporal Relation Extraction
Determining temporal relations (e.g., before or after) between events has been a challenging natural language understanding task, partly due to the difficulty to generate large amounts of high-quality training data. Consequently, neural approaches have not been widely used on it, or showed only moderate improvements. This paper proposes a new neural system that achieves about 10% absolute improvement in accuracy over the previous best system (25% error reduction) on two benchmark datasets. The proposed system is trained on the state-of-the-art MATRES dataset and applies contextualized word embeddings, a Siamese encoder of a temporal common sense knowledge base, and global inference via integer linear programming (ILP). We suggest that the new approach could serve as a strong baseline for future research in this area.
@article{ning-etal-2019-improved,bibtex_show=true,title={An Improved Neural Baseline for Temporal Relation Extraction},author={Ning, Qiang and Subramanian, Sanjay and Roth, Dan},journal={EMNLP},year={2019}}
Theory
An information theoretic model for summarization, and some basic results
A basic information theoretic model for summarization is formulated. Here summarization is considered as the process of taking a report of v binary objects, and producing from it a j element subset that captures most of the important features of the original report, with importance being defined via an arbitrary set function endemic to the model. The loss of information is measured by a weight average of variational distances, which we term the semantic loss.Our results include both cases where the probability distribution generating the v-length reports are known and unknown. In the case where the generating distribution is known, our results demonstrate how to construct minimal semantic loss summarizers. For the case where the probability distribution is unknown, we show how to construct summarizers which minimize the semantic loss averaged uniformly over all possible distribution converges to the minimum.
@article{8849755,bibtex_show=true,author={Graves, Eric and Ning, Qiang and Basu, Prithwish},journal={ISIT},title={An information theoretic model for summarization, and some basic results},year={2019}}
For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low quality and could hurt the learning process. This paper questions this common perception, motivated by the fact that structures consist of interdependent sets of variables. Thus, given a fixed budget, partly annotating each structure may provide the same level of supervision, while allowing for more structures to be annotated. We provide an information theoretic formulation for this perspective and use it, in the context of three diverse structured learning tasks, to show that learning from partial structures can sometimes outperform learning from complete ones. Our findings may provide important insights into structured data annotation schemes and could support progress in learning protocols for structured tasks.
@article{ning-etal-2019-partial,bibtex_show=true,title={Partial Or Complete, That{'}s The Question},author={Ning, Qiang and He, Hangfeng and Fan, Chuchu and Roth, Dan},journal={NAACL},year={2019}}
LLM
Roadmap of word embedding techniques and how that leads to BERT
Automatic extraction of temporal information is important for natural language understanding. It involves two basic tasks: (1) Understanding time expressions that are mentioned explicitly in text (e.g., February 27, 1998 or tomorrow), and (2) Understanding temporal information that is conveyed implicitly via relations. This paper introduces CogCompTime, a system that has these two important functionalities. It incorporates the most recent progress, achieves state-of-the-art performance, and is publicly available at \urlhttp://cogcomp.org/page/publication_view/844.
@article{ning-etal-2018-cogcomptime,bibtex_show=true,title={{C}og{C}omp{T}ime: A Tool for Understanding Time in Natural Language},author={Ning, Qiang and Zhou, Ben and Feng, Zhili and Peng, Haoruo and Roth, Dan},journal={EMNLP Demo},year={2018}}
NLP
A Multi-Axis Annotation Scheme for Event Temporal Relations
Existing temporal relation (TempRel) annotation schemes often have low inter-annotator agreements (IAA) even between experts, suggesting that the current annotation task needs a better definition. This paper proposes a new multi-axis modeling to better capture the temporal structure of events. In addition, we identify that event end-points are a major source of confusion in annotation, so we also propose to annotate TempRels based on start-points only. A pilot expert annotation effort using the proposed scheme shows significant improvement in IAA from the conventional 60’s to 80’s (Cohen’s Kappa). This better-defined annotation scheme further enables the use of crowdsourcing to alleviate the labor intensity for each annotator. We hope that this work can foster more interesting studies towards event understanding.
@article{ning-etal-2018-multi,bibtex_show=true,title={A Multi-Axis Annotation Scheme for Event Temporal Relations},author={Ning, Qiang and Wu, Hao and Roth, Dan},journal={ACL},year={2018}}
Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must occur earlier than its effect, temporal and causal relations are closely related and one relation often dictates the value of the other. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints that are inherent in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
@article{ning-etal-2018-joint,bibtex_show=true,title={Joint Reasoning for Temporal and Causal Relations},author={Ning, Qiang and Feng, Zhili and Wu, Hao and Roth, Dan},journal={ACL},year={2018}}
NLP
Exploiting Partially Annotated Data in Temporal Relation Extraction
Annotating temporal relations (TempRel) between events described in natural language is known to be labor intensive, partly because the total number of TempRels is quadratic in the number of events. As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena. In order to improve existing approaches, one possibility is to make use of the readily available, partially annotated data (P as in partial) that cover more documents. However, missing annotations in P are known to hurt, rather than help, existing systems. This work is a case study in exploring various usages of P for TempRel extraction. Results show that despite missing annotations, P is still a useful supervision signal for this task within a constrained bootstrapping learning framework. The system described in this system is publicly available.
@article{ning-etal-2018-exploiting,bibtex_show=true,title={Exploiting Partially Annotated Data in Temporal Relation Extraction},author={Ning, Qiang and Yu, Zhongzhi and Fan, Chuchu and Roth, Dan},journal={Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics},year={2018}}
NLP
Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource
Extracting temporal relations (before, after, overlapping, etc.) is a key aspect of understanding events described in natural language. We argue that this task would gain from the availability of a resource that provides prior knowledge in the form of the temporal order that events usually follow. This paper develops such a resource – a probabilistic knowledge base acquired in the news domain – by extracting temporal relations between events from the New York Times (NYT) articles over a 20-year span (1987–2007). We show that existing temporal extraction systems can be improved via this resource. As a byproduct, we also show that interesting statistics can be retrieved from this resource, which can potentially benefit other time-aware tasks. The proposed system and resource are both publicly available.
@article{ning-etal-2018-improving,bibtex_show=true,title={Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource},author={Ning, Qiang and Wu, Hao and Peng, Haoruo and Roth, Dan},journal={NAACL},year={2018}}
2017
NLP
A Structured Learning Approach to Temporal Relation Extraction
Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively identifying temporal relations between events is a challenging problem even for human annotators. This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. As a byproduct, this provides a new perspective on handling missing relations, a known issue that hurts existing methods. As we show, the proposed approach results in significant improvements on the two commonly used data sets for this problem.
@article{ning-etal-2017-structured,bibtex_show=true,title={A Structured Learning Approach to Temporal Relation Extraction},author={Ning, Qiang and Feng, Zhili and Roth, Dan},journal={EMNLP},year={2017}}
Brain
Spectral Quantification for High-Resolution MR Spectroscopic Imaging With Spatiospectral Constraints
@article{ning-et-al-tbme17,author={Ning, Qiang and Ma, Chao and Lam, Fan and Liang, Zhi-Pei},journal={IEEE Transactions on Biomedical Engineering},title={Spectral Quantification for High-Resolution MR Spectroscopic Imaging With Spatiospectral Constraints},year={2017},doi={10.1109/TBME.2016.2594583}}
Brain
High-resolution 1H-MRSI of the brain using short-TE SPICE
@article{MRM17,bibtex_show=true,title={High-resolution 1H-MRSI of the brain using short-TE SPICE},author={Ma, Chao and Lam, Fan and Ning, Qiang and Johnson, Curtis L and Liang, Zhi-Pei},journal={Magn Reson Med.},year={2017},doi={10.1002/mrm.26130}}
@article{nuisance-removal,bibtex_show=true,title={Removal of Nuisance Signal from Sparsely Sampled 1H-MRSI Data Using Physics-based Spectral Bases},author={Ning, Qiang and Ma, Chao and Lam, Fan and Clifford, Bryan and Liang, Zhi-Pei},journal={Annual ISMRM Scientific Meeting and Exhibition},year={2016},}
2015
Brain
Spectral estimation for magnetic resonance spectroscopic imaging with spatial sparsity constraints
@article{7164157,bibtex_show=true,author={Ning, Qiang and Ma, Chao and Liang, Zhi-Pei},journal={2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)},title={Spectral estimation for magnetic resonance spectroscopic imaging with spatial sparsity constraints},year={2015},doi={10.1109/ISBI.2015.7164157}}
Brain
Joint Estimation of Spectral Parameters from MR Spectroscopic Imaging Data
@article{ismrm15,bibtex_show=true,title={Joint Estimation of Spectral Parameters from MR Spectroscopic Imaging Data},author={Ning, Qiang and Ma, Chao and Liang, Zhi-Pei},journal={Annual ISMRM Scientific Meeting and Exhibition},year={2015},}
Theory
A Summary of Some Interesting Bounds in Estimation and Learning
@article{embc14,bibtex_show=true,title={Towards Short-TE MR Spectroscopic Imaging: Spectral Decomposition and Removal of Baseline Signals},author={Ning, Qiang and Ma, Chao and Johnson, Curtis L and Liang, Zhi-Pei},journal={Annual International Conference of the IEEE Engineering in Medicine and Biology Society},year={2014},}
Brain
Constrained Spectral Estimation for Magnetic Resonance Spectroscopic Imaging
@article{6417962,bibtex_show=true,author={Ning, Qiang and Chen, Kan and Yi, Li and Fan, Chuchu and Lu, Yao and Wen, Jiangtao},journal={IEEE Signal Processing Letters},title={Image Super-Resolution Via Analysis Sparse Prior},year={2013},volume={20},number={4},pages={399-402},keywords={Analytical models;Algorithm design and analysis;Image resolution;Image color analysis;Image reconstruction;Dictionaries;Electronic mail;Analysis sparsity;image super-resolution;neighbor compatibility;variance prediction},doi={10.1109/LSP.2013.2242198}}
Theory
Matrix Derivatives and Descent Optimization Methods
Gradient Calculation for Nonlinear Linear Squares Problems with Complex NumbersTech notes, 2013
