Papers by Owen Rambow
Re-Examining FactBank: Predicting the Author’s Presentation of Factuality (2022.coling-1)
Copied to clipboard
| Challenge: | Previously published results on FactBank are no longer valid. |
| Approach: | They propose to correct a subset of FactBank data to improve performance . they use multiple training paradigms, data smoothing techniques, and polarity classifiers . |
| Outcome: | The proposed model improves performance on the FactBank dataset. |
End-to-End Graph-Based TAG Parsing with Neural Networks (N18-1)
Copied to clipboard
| Challenge: | Using BiLSTMs, highway connections, and character-level CNNs, we propose a graph-based Tree Adjoining Grammar (TAG) parser. |
| Approach: | They propose a graph-based Tree Adjoining Grammar parser that uses BiLSTMs, highway connections, and character-level CNNs. |
| Outcome: | The proposed parser outperforms the previously reported best by more than 2.2 LAS and UAS points. |
Machine Theory of Mind Needs Machine Validation (2025.findings-acl)
Copied to clipboard
| Challenge: | In recent years there has been an explosion of interest in studying the extent to which language models (LMs) display a theory of mind (ToM) despite the growth of evaluation tools, the extent of evidence for ToM remains unclear. |
| Approach: | They conduct a survey of 16 recent studies aimed at measuring ToM in language models and found that only half do so for patterns only a machine might exploit. |
| Outcome: | The results show that the datasets that show high LM performance on ToM tasks are easier than their peers, likely due to the presence of spurious patterns in the data. |
Towards Generative Event Factuality Prediction (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event factuality prediction focus on author's presentation of factuity . a novel end-to-end generative task is proposed to predict event factuality holders, targets, and their associated factual values. |
| Approach: | They propose a generative task and system for predicting event factuality holders, targets, and their associated factual values. |
| Outcome: | The proposed system improves on the FactBank corpus and other corpora . it can predict presentation of factuality of nested sources alongside their target events . |
The MADAR Arabic Dialect Corpus and Lexicon (L18-1)
Copied to clipboard
Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alexander Erdmann, Kemal Oflazer
| Challenge: | Using a corpus of 25 Arabic city dialects and a lexicon of 1,045 concepts, we study 25 cities in a travel domain . focus on cities opens new avenues for research from dialectology to dialect identification and machine translation. |
| Approach: | They present two Arabic language resources that are part of the Multi Arabic Dialect Applications and Resources project. |
| Outcome: | The proposed resources are the first of their kind in terms of their coverage and fine granularity. |
Residualized Similarity for Faithfully Explainable Authorship Verification (2025.findings-emnlp)
Copied to clipboard
Peter Zeng, Pegah Alipoormolabashi, Jihu Mun, Gourab Dey, Nikita Soni, Niranjan Balasubramanian, Owen Rambow, H. Schwartz
| Challenge: | Neural methods achieve high accuracy, but their representations lack direct interpretability. |
| Approach: | They propose a method that supplements systems using interpretable features with a neural network to improve their performance while maintaining interpretability. |
| Outcome: | The proposed method improves the performance of state-of-the-art models while maintaining interpretability. |
Author Commitment and Social Power: Automatic Belief Tagging to Infer the Social Context of Interactions (N18-1)
Copied to clipboard
| Challenge: | Social power is a difficult concept to define, but is often manifested in how we interact with one another. |
| Approach: | They employ extra-propositional semantics extraction within NLP to study author commitment . they find that subordinates use significantly more instances of non-commitment than superiors . |
| Outcome: | The proposed method shows that subordinates use significantly more instances of non-commitment than superiors, and that enriching lexical features with commitment labels captures important distinctions in social meanings. |
BeSt: The Belief and Sentiment Corpus (2022.lrec-1)
Copied to clipboard
Jennifer Tracey, Owen Rambow, Claire Cardie, Adam Dalton, Hoa Trang Dang, Mona Diab, Bonnie Dorr, Louise Guthrie, Magdalena Markowska, Smaranda Muresan, Vinodkumar Prabhakaran, Samira Shaikh, Tomek Strzalkowski
| Challenge: | a corpus of propositional content is a set of cognitive attitudes of different agents towards a text . propositional attitudes are a cognitive attitude, including belief and sentiment, towards . |
| Approach: | They propose a corpus which records cognitive state: who believes what, who has what sentiment . they use newswire and discussion forums in Chinese, English, and Spanish . |
| Outcome: | The proposed corpus records who believes what (i.e., factuality) and who has what sentiment towards what. |
A Cautious Generalization Goes a Long Way: Learning Morphophonological Rules (2023.acl-long)
Copied to clipboard
| Challenge: | Explicit linguistic knowledge encoded by rule-based morphological analyzers is expensive and non-trivial . creating such resources is tedious and requires additional efforts to extract human-interpretable patterns from them. |
| Approach: | They propose a method for automatically learning morphophonological rules of Arabic from a corpus. |
| Outcome: | The proposed approach produces a set of generalizable rules from a dataset. |
Computational Benchmarks for Egyptian Arabic Child Directed Speech (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing CDS corpora in English are limited due to their limited size or lack of linguistic annotation. |
| Approach: | They propose to map Egyptian Arabic IPA tokens to Arabic script and add core part-of-speech tags and lemmas aligned with existing Arabic morphological resources. |
| Outcome: | The proposed version of the Egyptian Arabic CHILDES corpus is available online. |
Unified Guidelines and Resources for Arabic Dialect Orthography (L18-1)
Copied to clipboard
Nizar Habash, Fadhl Eryani, Salam Khalifa, Owen Rambow, Dana Abdulrahim, Alexander Erdmann, Reem Faraj, Wajdi Zaghouani, Houda Bouamor, Nasser Zalmout, Sara Hassan, Faisal Al-Shargi, Sakhar Alkhereyf, Basma Abdulkareem, Ramy Eskander, Mohammad Salameh, Hind Saddiki
| Challenge: | Existing efforts to conventionalize the dialectal orthography of Arabic have focused on specific dialects and made ad hoc decisions. |
| Approach: | They propose a set of guidelines and meta-guidelines for conventional orthography of Arabic dialects . they apply them to 28 Arab city dialects from Rabat to Muscat . |
| Outcome: | The proposed guidelines and resources are being used by three large Arabic dialect processing projects in three universities. |
Deep Active Learning for Morphophonological Processing (2023.acl-short)
Copied to clipboard
Seyed Morteza Mirbostani, Yasaman Boreshban, Salam Khalifa, SeyedAbolghasem Mirroshandel, Owen Rambow
| Challenge: | Existing deep learning models for morphological processing require a large amount of annotated data. |
| Approach: | They propose a deep active learning method that uses only informative samples to reduce the need for annotated data. |
| Outcome: | The proposed method achieves the same results as the state-of-the-art model on Egyptian Arabic with only about 30% of annotated data. |
Email Classification Incorporating Social Networks and Thread Structure (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for document classification in social networks capture only semantics of texts . incorporating social network information in addition to textual information is effective . |
| Approach: | They propose to incorporate social network information into document classification tasks . they use email as a feature and model email thread structure . |
| Outcome: | The proposed method improves over a state-of-the-art baseline based on textual information . the proposed method is based in two corpora, one of which we train on . |
LVLMs and Humans Ground Differently in Referential Communication (2026.acl-long)
Copied to clipboard
Peter Zeng, Weiling Li, Amie J. Paige, Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras, Gregory J. Zelinsky, Susan Brennan, Owen Rambow
| Challenge: | generative AI agents cannot model common ground in a way that enables smooth communication . a recent study examined whether large language models and large vision language models engage in grounding as human discourse partners do . |
| Approach: | They propose to use referential communication to model common ground between a pair of directors and a picture matching system. |
| Outcome: | The proposed experiment shows that generative AI agents cannot model common ground . human conversation relies on common ground accrued and updated by interacting partners . |
BeLeaf: Belief Prediction as Tree Generation (2024.naacl-demo)
Copied to clipboard
| Challenge: | a novel approach to predicting source-and-target factuality is presented . our linearized tree generation task fully accounts for the factuity tree structure . |
| Approach: | They propose a linearized tree generation task which fully accounts for factuality . they then create a system which leverages the linearized representation to create visualizations . |
| Outcome: | The proposed model and representation fully account for the factuality tree structure, generating the full chain of nested sources instead of the last source only. |
Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground (2024.findings-acl)
Copied to clipboard
Adil Soubki, John Murzaku, Arash Yousefi Jordehi, Peter Zeng, Magdalena Markowska, Seyed Abolghasem Mirroshandel, Owen Rambow
| Challenge: | Existing benchmarks for theory of mind (ToM) use synthetic data, which can misalign with human behavior. |
| Approach: | They propose a question-answer benchmark based on naturally occurring spoken dialogs to evaluate theory of mind capabilities of language models. |
| Outcome: | The proposed dataset shows that LMs struggle to demonstrate theory of mind (ToM) . |
To Test Machine Comprehension, Start by Defining Comprehension (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to machine reading comprehension do not adequately define comprehension, authors argue . authors argue that existing systems are not up to the task of narrative understanding as they define it . |
| Approach: | They propose a detailed definition of comprehension for short narratives . they argue existing systems are not up to the task of narrative understanding . |
| Outcome: | The proposed task definitions suggest existing systems are not up to the task of narrative understanding as they define it. |
Synthetic Audio Helps for Cognitive State Tasks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Prior work in NLP focuses on tasks that involve extracting information about the cognitive states of human entities from text. |
| Approach: | They propose a framework for learning to add synthetic audio to text-only corpora and a system that automatically tracks audio signals to produce naturalistic audio. |
| Outcome: | The proposed framework improves on 7 cognitive state modeling tasks on text and synthetic audio data from an off-the-shelf TTS system. |
Intention and Face in Dialog (2024.lrec-main)
Copied to clipboard
| Challenge: | a theory of politeness focuses on how intentions mediate the planning of turns which impose upon face. |
| Approach: | They propose to train a model which classifies intention and politeness using existing corpus and a new model which incorporates annotations. |
| Outcome: | The proposed model improves face act detection for minority classes and points to a close relationship between aspects of face and intent. |
LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing (2025.acl-long)
Copied to clipboard
| Challenge: | a growing number of studies have indicated the general usefulness of LLMs for automated writing assessments. |
| Approach: | They propose a framework that evaluates LLMs' ability to provide scores and comments based on multiple assessment criteria. |
| Outcome: | The proposed framework is interpretable, cost-efficient, scalable, and reproducible . it is compared to existing methods that rely on manual judgments . |
Radical Allomorphy: Phonological Surface Forms without Phonology (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work typically frames morphophonology as generating surface forms from abstract underlying representations (URs) this theory-laden assumption is expensive to annotate, especially in low-resource settings. |
| Approach: | a new approach frames morphophonology as generating surface forms from abstract underlying representations by applying phonological rules or constraints. |
| Outcome: | The proposed model removes the need to posit or label URs and lets the model exploit the surface evidence directly. |
Syntax-aware Neural Semantic Role Labeling with Supertags (N19-1)
Copied to clipboard
| Challenge: | a new syntax-aware model for dependency-based semantic role labeling outperforms syntax-based models for English and Spanish. |
| Approach: | They propose a syntax-aware model for dependency-based semantic role labeling that outperforms syntax-based models for English and Spanish. |
| Outcome: | The proposed model outperforms syntax-agnostic models for English and Spanish. |
From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing paradigms for propositional analysis use stances and concerns to generate explanatory representations. |
| Approach: | They propose a generalized paradigm for adaptation of propositional analysis to new tasks and domains by using an analogy between stances and concerns. |
| Outcome: | The proposed model yields 231% improvement in recall over baseline, with only 10% loss in precision. |
LVLMs are Bad at Overhearing Human Referential Communication (2025.emnlp-main)
Copied to clipboard
| Challenge: | a crucial skill for embodied AI agents working with humans is grounding in referential communication. |
| Approach: | They use large vision language models to overhear spontaneous conversations between humans . they find that current LVLMs fail to show consistent performance improvement . |
| Outcome: | The proposed models fail to show consistent performance improvement over previous models . the authors release the results to facilitate future research . |
NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to understand acceptable behavior have focused on a single culture and manually built datasets from non-conversational settings. |
| Approach: | They propose a framework to automatically extract culture-specific norms from multi-lingual conversations. |
| Outcome: | The proposed framework extracts culture-specific norms from multi-lingual conversations. |
Active Few-Shot Learning for Text Classification (2025.naacl-long)
Copied to clipboard
Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran, Seyed Abolghasem Mirroshandel, Owen Rambow, Cornelia Caragea
| Challenge: | Recent advances in Large Language Models (LLMs) have boosted the use of Few-Shot Learning (FSL) methods in natural language processing. |
| Approach: | They propose a method that identifies effective support instances from the unlabeled pool and can work with different LLMs. |
| Outcome: | The proposed method improves on five tasks on which it is tested on five LLMs. |
Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States (2024.lrec-main)
Copied to clipboard
Saeed Ahmadnia, Arash Yousefi Jordehi, Mahsa Hosseini Khasheh Heyran, SeyedAbolghasem Mirroshandel, Owen Rambow
| Challenge: | Existing research on opinion mining has focused on a small subset of the MPQA 2.0 dataset . a recent study focused on the subjective expressions of people who express opinions, sentiments, and attitudes toward targets. |
| Approach: | They propose to use MPQA 2.0 to analyze the entire dataset . they propose to provide a clean version of the MPQA Opinion Corpus in a more interpretable format . |
| Outcome: | The proposed methods establish high baselines for future work. |
Finding Common Ground: Annotating and Predicting Common Ground in Spoken Conversations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Creating and updating common ground (CG) between interlocutors is the key to a successful conversation. |
| Approach: | They propose a new annotation and corpus to capture common ground in human communication . they then conduct experiments to extract propositions from dialog and track their status in common ground from the perspective of each speaker . |
| Outcome: | The proposed corpus captures common ground from the perspective of two speakers in a dialog. |