Owen Rambow
YOU?
Author Swipe
View article: Residualized Similarity for Faithfully Explainable Authorship Verification
Residualized Similarity for Faithfully Explainable Authorship Verification Open
Responsible use of Authorship Verification (AV) systems not only requires high accuracy but also interpretable solutions. More importantly, for systems to be used to make decisions with real-world consequences requires the model's predicti…
View article: LVLMs are Bad at Overhearing Human Referential Communication
LVLMs are Bad at Overhearing Human Referential Communication Open
During spontaneous conversations, speakers collaborate on novel referring expressions, which they can then re-use in subsequent conversations. Understanding such referring expressions is an important ability for an embodied agent, so that …
View article: OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs
OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs Open
The use of omni-LLMs (large language models that accept any modality as input), particularly for multimodal cognitive state tasks involving speech, is understudied. We present OmniVox, the first systematic evaluation of four omni-LLMs on t…
View article: Active Few-Shot Learning for Text Classification
Active Few-Shot Learning for Text Classification Open
The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working with limited training data. The goal of FSL is to effectivel…
View article: LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing
LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing Open
The paper explores the performance of LLMs in the context of multi-dimensional analytic writing assessments, i.e. their ability to provide both scores and comments based on multiple assessment criteria. Using a corpus of literature reviews…
View article: Zero-Shot Belief: A Hard Problem for LLMs
Zero-Shot Belief: A Hard Problem for LLMs Open
We present two LLM-based approaches to zero-shot source-and-target belief prediction on FactBank: a unified system that identifies events, sources, and belief labels in a single pass, and a hybrid approach that uses a fine-tuned DeBERTa ta…
View article: Synthetic Audio Helps for Cognitive State Tasks
Synthetic Audio Helps for Cognitive State Tasks Open
The NLP community has broadly focused on text-only approaches of cognitive state tasks, but audio can provide vital missing cues through prosody. We posit that text-to-speech models learn to track aspects of cognitive state in order to pro…
View article: Training LLMs to Recognize Hedges in Spontaneous Narratives
Training LLMs to Recognize Hedges in Spontaneous Narratives Open
Hedges allow speakers to mark utterances as provisional, whether to signal non-prototypicality or "fuzziness", to indicate a lack of commitment to an utterance, to attribute responsibility for a statement to someone else, to invite input f…
View article: Examining Gender and Power on Wikipedia Through Face and Politeness
Examining Gender and Power on Wikipedia Through Face and Politeness Open
We propose a framework for analyzing discourse by combining two interdependent concepts from sociolinguistic theory: face acts and politeness. While politeness has robust existing tools and data, face acts are less resourced. We introduce …
View article: Gram2Vec: An Interpretable Document Vectorizer
Gram2Vec: An Interpretable Document Vectorizer Open
We present Gram2Vec, a grammatical style embedding system that embeds documents into a higher dimensional space by extracting the normalized relative frequencies of grammatical features present in the text. Compared to neural approaches, G…
View article: Evaluating LLMs with Multiple Problems at once
Evaluating LLMs with Multiple Problems at once Open
This paper shows the benefits and fruitfulness of evaluating LLMs with multiple problems at once, a paradigm we call multi-problem evaluation (MPE). Unlike conventional single-problem evaluation, where a prompt presents a single problem an…
View article: Multimodal Belief Prediction
Multimodal Belief Prediction Open
Recognizing a speaker's level of commitment to a belief is a difficult task; humans do not only interpret the meaning of the words in context, but also understand cues from intonation and other aspects of the audio signal. Many papers and …
View article: Intention and Face in Dialog
Intention and Face in Dialog Open
The notion of face described by Brown and Levinson (1987) has been studied in great detail, but a critical aspect of the framework, that which focuses on how intentions mediate the planning of turns which impose upon face, has received far…
View article: Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground
Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Ground Open
Evaluating the theory of mind (ToM) capabilities of language models (LMs) has recently received a great deal of attention. However, many existing benchmarks rely on synthetic data, which risks misaligning the resulting experiments with hum…
View article: Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents
Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents Open
We propose a novel clustering pipeline to detect and characterize influence campaigns from documents. This approach clusters parts of document, detects clusters that likely reflect an influence campaign, and then identifies documents linke…
View article: Finding Common Ground: Annotating and Predicting Common Ground in Spoken Conversations
Finding Common Ground: Annotating and Predicting Common Ground in Spoken Conversations Open
When we communicate with other humans, we do not simply generate a sequence of words. Rather, we use our cognitive state (beliefs, desires, intentions) and our model of the audience's cognitive state to create utterances that affect the au…
View article: Deep Active Learning for Morphophonological Processing
Deep Active Learning for Morphophonological Processing Open
Seyed Morteza Mirbostani, Yasaman Boreshban, Salam Khalifa, SeyedAbolghasem Mirroshandel, Owen Rambow. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023.
View article: NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly
NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly Open
Knowledge of norms is needed to understand and reason about acceptable behavior in human communication and interactions across sociocultural scenarios. Most computational research on norms has focused on a single culture, and manually buil…
View article: Towards Generative Event Factuality Prediction
Towards Generative Event Factuality Prediction Open
We present a novel end-to-end generative task and system for predicting event factuality holders, targets, and their associated factuality values. We perform the first experiments using all sources and targets of factuality statements from…