Search Results for author:
Found 77 papers, 5 papers with code
Conundrums in Event Coreference Resolution: Making Sense of the State of the Art
Despite recent promising results on the application of span-based models for event reference interpretation, there is a lack of understanding of what has been improved.
Constrained Multi-Task Learning for Bridging Resolution
We examine the extent to which supervised bridging resolvers can be improved without employing additional labeled bridging data by proposing a novel constrained multi-task learning framework for bridging resolution, within which we (1) design cross-task consistency constraints to guide the learning process; (2) pre-train the entity coreference model in the multi-task framework on the large amount of publicly available coreference data; and (3) integrating prior knowledge encoded in rule-based resolvers.
Legal Judgment Prediction via Event Extraction with Constraints
While significant progress has been made on the task of Legal Judgment Prediction (LJP) in recent years, the incorrect predictions made by SOTA LJP models can be attributed in part to their failure to (1) locate the key event information that determines the judgment, and (2) exploit the cross-task consistency constraints that exist among the subtasks of LJP.
The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora Resolution in Dialogue.
End-to-End Neural Bridging Resolution
The state of bridging resolution research is rather unsatisfactory: not only are state-of-the-art resolvers evaluated in unrealistic settings, but the neural models underlying these resolvers are weaker than those used for entity coreference resolution.
Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting
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.
The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis Resolution in Dialogue: A Cross-Team Analysis
The CODI-CRAC 2021 shared task is the first shared task that focuses exclusively on anaphora resolution in dialogue and provides three tracks, namely entity coreference resolution, bridging resolution, and discourse deixis resolution.
Neural Anaphora Resolution in Dialogue
We describe the systems that we developed for the three tracks of the CODI-CRAC 2021 shared task, namely entity coreference resolution, bridging resolution, and discourse deixis resolution.
The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
The CODI-CRAC 2022 Shared Task on Anaphora Resolution in Dialogues is the second edition of an initiative focused on detecting different types of anaphoric relations in conversations of different kinds.
Neural Anaphora Resolution in Dialogue Revisited
We present the systems that we developed for all three tracks of the CODI-CRAC 2022 shared task, namely the anaphora resolution track, the bridging resolution track, and the discourse deixis resolution track.
Conundrums in Entity Coreference Resolution: Making Sense of the State of the Art
Despite the significant progress on entity coreference resolution observed in recent years, there is a general lack of understanding of what has been improved.
Identifying Exaggerated Language
While hyperbole is one of the most prevalent rhetorical devices, it is arguably one of the least studied devices in the figurative language processing community.
Oversampling Higher-Performing Minorities During Machine Learning Model Training Reduces Adverse Impact Slightly but Also Reduces Model Accuracy
In this study, we systematically under- and oversampled minority (Black and Hispanic) applicants to manipulate adverse impact ratios in training data and investigated how training data adverse impact ratios affect ML model adverse impact and accuracy.
Multimodal Propaganda Processing
Propaganda campaigns have long been used to influence public opinion via disseminating biased and/or misleading information.
CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models
Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amount of data on the target task for fine-tuning.
End-to-End Neural Discourse Deixis Resolution in Dialogue
We adapt Lee et al.'s (2018) span-based entity coreference model to the task of end-to-end discourse deixis resolution in dialogue, specifically by proposing extensions to their model that exploit task-specific characteristics.
DiscoSense: Commonsense Reasoning with Discourse Connectives
We present DiscoSense, a benchmark for commonsense reasoning via understanding a wide variety of discourse connectives.
Ranked #8 on
Sentence Completion
on HellaSwag
Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code
In particular, the development and use of pre-trained models of source code has enabled state-of-the-art results to be achieved on a wide variety of SE tasks.
Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey
While commonsense knowledge acquisition and reasoning has traditionally been a core research topic in the knowledge representation and reasoning community, recent years have seen a surge of interest in the natural language processing community in developing pre-trained models and testing their ability to address a variety of newly designed commonsense knowledge reasoning and generation tasks.
Bridging Resolution: Making Sense of the State of the Art
While Yu and Poesio (2020) have recently demonstrated the superiority of their neural multi-task learning (MTL) model to rule-based approaches for bridging anaphora resolution, there is little understanding of (1) how it is better than the rule-based approaches (e. g., are the two approaches making similar or complementary mistakes?)
Constrained Multi-Task Learning for Event Coreference Resolution
We propose a neural event coreference model in which event coreference is jointly trained with five tasks: trigger detection, entity coreference, anaphoricity determination, realis detection, and argument extraction.
Bridging Resolution: A Survey of the State of the Art
Bridging reference resolution is an anaphora resolution task that is arguably more challenging and less studied than entity coreference resolution.
Event Coreference Resolution with Non-Local Information
We present two extensions to a state-of-theart joint model for event coreference resolution, which involve incorporating (1) a supervised topic model for improving trigger detection by providing global context, and (2) a preprocessing module that seeks to improve event coreference by discarding unlikely candidate antecedents of an event mention using discourse contexts computed based on salient entities.
Synergy between Machine/Deep Learning and Software Engineering: How Far Are We?
To improve the applicability and generalizability of research results, we analyzed what ingredients in a study would facilitate an understanding of why a ML/DL technique was selected for a specific SE problem.
Aspect-Based Sentiment Analysis as Fine-Grained Opinion Mining
We show how the general fine-grained opinion mining concepts of opinion target and opinion expression are related to aspect-based sentiment analysis (ABSA) and discuss their benefits for resource creation over popular ABSA annotation schemes.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Unsupervised Argumentation Mining in Student Essays
State-of-the-art systems for argumentation mining are supervised, thus relying on training data containing manually annotated argument components and the relationships between them.
Give Me More Feedback II: Annotating Thesis Strength and Related Attributes in Student Essays
While the vast majority of existing work on automated essay scoring has focused on holistic scoring, researchers have recently begun work on scoring specific dimensions of essay quality.
Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data
Argument compatibility is a linguistic condition that is frequently incorporated into modern event coreference resolution systems.
Modeling and Prediction of Online Product Review Helpfulness: A Survey
This paper provides an overview of the most relevant work in helpfulness prediction and understanding in the past decade, discusses the insights gained from said work, and provides guidelines for future research.
Give Me More Feedback: Annotating Argument Persuasiveness and Related Attributes in Student Essays
While argument persuasiveness is one of the most important dimensions of argumentative essay quality, it is relatively little studied in automated essay scoring research.
WikiRank: Improving Keyphrase Extraction Based on Background Knowledge
Keyphrase is an efficient representation of the main idea of documents.
Lightly-Supervised Modeling of Argument Persuasiveness
We propose the first lightly-supervised approach to scoring an argument{'}s persuasiveness.
Joint Learning for Event Coreference Resolution
While joint models have been developed for many NLP tasks, the vast majority of event coreference resolvers, including the top-performing resolvers competing in the recent TAC KBP 2016 Event Nugget Detection and Coreference task, are pipeline-based, where the propagation of errors from the trigger detection component to the event coreference component is a major performance limiting factor.
Joint Inference for Event Coreference Resolution
Event coreference resolution is a challenging problem since it relies on several components of the information extraction pipeline that typically yield noisy outputs.
Markov Logic Networks for Text Mining: A Qualitative and Empirical Comparison with Integer Linear Programming
Joint inference approaches such as Integer Linear Programming (ILP) and Markov Logic Networks (MLNs) have recently been successfully applied to many natural language processing (NLP) tasks, often outperforming their pipeline counterparts.
Event Coreference Resolution with Multi-Pass Sieves
Multi-pass sieve approaches have been successfully applied to entity coreference resolution and many other tasks in natural language processing (NLP), owing in part to the ease of designing high-precision rules for these tasks.
SinoCoreferencer: An End-to-End Chinese Event Coreference Resolver
Compared to entity coreference resolution, there is a relatively small amount of work on event coreference resolution.
Annotating Inter-Sentence Temporal Relations in Clinical Notes
Our goals in this paper are to (1) manually annotate certain types of missing links that cannot be automatically recovered in the i2b2 Clinical Temporal Relations Challenge Corpus, one of the recently released evaluation corpora for temporal relation extraction; and (2) empirically determine the usefulness of these additional annotations.
Which Clustering Do You Want? Inducing Your Ideal Clustering with Minimal Feedback
While traditional research on text clustering has largely focused on grouping documents by topic, it is conceivable that a user may want to cluster documents along other dimensions, such as the authors mood, gender, age, or sentiment.
Narrowing the Modeling Gap: A Cluster-Ranking Approach to Coreference Resolution
Traditional learning-based coreference resolvers operate by training the mention-pair model for determining whether two mentions are coreferent or not.
Cause Identification from Aviation Safety Incident Reports via Weakly Supervised Semantic Lexicon Construction
The Aviation Safety Reporting System collects voluntarily submitted reports on aviation safety incidents to facilitate research work aiming to reduce such incidents.
