Search Results for author:
Found 152 papers, 26 papers with code
Investigating the Impact of Various Partial Diacritization Schemes on Arabic-English Statistical Machine Translation
The absence of these diacritics naturally leads to significant word ambiguity to top the inherent ambiguity present in fully diacritized words.
BeSt: The Belief and Sentiment Corpus
We present the BeSt corpus, which records cognitive state: who believes what (i. e., factuality), and who has what sentiment towards what.
Active Learning for Rumor Identification on Social Media
We discuss the impact of multiple classifiers on a limited amount of annotated data followed by an interactive approach to gradually update the models by adding the least certain samples (LCS) from the pool of unlabeled data.
Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies
We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available.
Towards Responsible Natural Language Annotation for the Varieties of Arabic
When building NLP models, there is a tendency to aim for broader coverage, often overlooking cultural and (socio)linguistic nuance.
SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model.
CoRAG: Collaborative Retrieval-Augmented Generation
We introduce CoRAG, a framework extending RAG to collaborative settings, where clients jointly train a shared model using a collaborative passage store.
Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders
Studying 131 unique CLIP models, trained on 26 datasets, using 55 architectures, and in a variety of sizes, we evaluate bias in each model using 26 well-established unimodal and cross-modal principled Embedding Association Tests.
Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)
This work aims to address critical gaps in AI terminology resources and fosters global inclusivity and collaboration in AI research.
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods.
BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
In this work, we tackle the challenge of embedding realistic human personality traits into LLMs.
The FIGNEWS Shared Task on News Media Narratives
The shared task addresses bias and propaganda annotation in multilingual news posts.
Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory.
Evaluating Large Language Model Biases in Persona-Steered Generation
Models that we evaluate that are fine-tuned with Reinforcement Learning from Human Feedback (RLHF) are more steerable, especially towards stances associated with political liberals and women, but present significantly less diverse views of personas.
Automatic Generation of Model and Data Cards: A Step Towards Responsible AI
In an era of model and data proliferation in machine learning/AI especially marked by the rapid advancement of open-sourced technologies, there arises a critical need for standardized consistent documentation.
Analyzing the Role of Semantic Representations in the Era of Large Language Models
We find that it is difficult to predict which input examples AMR may help or hurt on, but errors tend to arise with multi-word expressions, named entities, and in the final inference step where the LLM must connect its reasoning over the AMR to its prediction.
Emotion Classification in Low and Moderate Resource Languages
There are 7100+ active languages spoken around the world and building emotion classification for each language is labor intensive.
Investigating Cultural Alignment of Large Language Models
The intricate relationship between language and culture has long been a subject of exploration within the realm of linguistic anthropology.
A Note on Bias to Complete
Minimizing social bias strengthens societal bonds, promoting shared understanding and better decision-making.
Can Large Language Models Infer Causation from Correlation?
In this work, we propose the first benchmark dataset to test the pure causal inference skills of large language models (LLMs).
OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models
Our study entails finetuning three different sizes of OPT on a carefully curated reasoning corpus, resulting in two sets of finetuned models: OPT-R, finetuned without explanations, and OPT-RE, finetuned with explanations.
ALERT: Adapting Language Models to Reasoning Tasks
Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning.
Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Therefore, we introduce a framework for value-aligned classification that performs prediction based on explicitly written human values in the command.
Text Characterization Toolkit
In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis.
Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification
To test this, we propose a new layer fusion method: Depth-Wise Attention (DWAtt), to help re-surface signals from non-final layers.
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection
Hate speech detection is complex; it relies on commonsense reasoning, knowledge of stereotypes, and an understanding of social nuance that differs from one culture to the next.
Cultural Vocal Bursts Intensity Prediction
Few-Shot Learning
+1
GisPy: A Tool for Measuring Gist Inference Score in Text
Decision making theories such as Fuzzy-Trace Theory (FTT) suggest that individuals tend to rely on gist, or bottom-line meaning, in the text when making decisions.
Consistent Human Evaluation of Machine Translation across Language Pairs
Obtaining meaningful quality scores for machine translation systems through human evaluation remains a challenge given the high variability between human evaluators, partly due to subjective expectations for translation quality for different language pairs.
Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification
The tasks are to predict if a tweet contains (1) Offensive language; and whether it is considered (2) Hate Speech or not and if so, then predict the (3) Fine-Grained Hate Speech label from one of six categories.
OPT: Open Pre-trained Transformer Language Models
Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning.
Ranked #2 on
Stereotypical Bias Analysis
on CrowS-Pairs
A Review on Language Models as Knowledge Bases
Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs).
CALCS 2021 Shared Task: Machine Translation for Code-Switched Data
For the unsupervised setting, we provide the following language pairs: English and Spanish-English (Eng-Spanglish), and English and Modern Standard Arabic-Egyptian Arabic (Eng-MSAEA) in both directions.
A Quantitative and Qualitative Analysis of Schizophrenia Language
They score lower in most of the linguistic features of cohesion with significant p-values.
Few-shot Learning with Multilingual Language Models
Large-scale generative language models such as GPT-3 are competitive few-shot learners.
Efficient Large Scale Language Modeling with Mixtures of Experts
This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings: in- and out-of-domain language modeling, zero- and few-shot priming, and full-shot fine-tuning.
Knowledge-Augmented Language Models for Cause-Effect Relation Classification
Previous studies have shown the efficacy of knowledge augmentation methods in pretrained language models.
Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
In this paper, we discuss approaches to detecting when models have beliefs about the world, and we improve on methods for updating model beliefs to be more truthful, with a focus on methods based on learned optimizers or hypernetworks.
AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer Summarization
One goal of answer summarization is to produce a summary that reflects the range of answer perspectives.
Discrete Cosine Transform as Universal Sentence Encoder
Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs.
Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
Is bias amplified when neural machine translation (NMT) models are optimized for speed and evaluated on generic test sets using BLEU?
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages.
Multi-Perspective Abstractive Answer Summarization
A major obstacle for multi-perspective, abstractive answer summarization is the absence of a dataset to provide supervision for producing such summaries.
Predicting Directionality in Causal Relations in Text
In this work, we test the performance of two bidirectional transformer-based language models, BERT and SpanBERT, on predicting directionality in causal pairs in the textual content.
White Paper: Challenges and Considerations for the Creation of a Large Labelled Repository of Online Videos with Questionable Content
This white paper presents a summary of the discussions regarding critical considerations to develop an extensive repository of online videos annotated with labels indicating questionable content.
Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages
We adopt cross-lingual embeddings constructed using different methods to extract features of the tweets, including a few state-of-the-art contextual embeddings such as BERT, RoBERTa and XLM-R. We train classifiers of different architectures on the extracted features.
Detecting Hallucinated Content in Conditional Neural Sequence Generation
Neural sequence models can generate highly fluent sentences, but recent studies have also shown that they are also prone to hallucinate additional content not supported by the input.
A Multitask Learning Approach for Diacritic Restoration
Such diacritics are often omitted in written text, increasing the number of possible pronunciations and meanings for a word.
FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization
We tackle the problem of evaluating faithfulness of a generated summary given its source document.
Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies
We make use of supervised syntactic parsing as an auxiliary task in a multitask learning framework, and show that with different multitask learning settings, we consistently improve over the single-task baseline.
DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking
The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence.
Learning to Classify Intents and Slot Labels Given a Handful of Examples
Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets.
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point.
Efficient Convolutional Neural Networks for Diacritic Restoration
Diacritic restoration has gained importance with the growing need for machines to understand written texts.
Homograph Disambiguation Through Selective Diacritic Restoration
Diacritic restoration could theoretically help disambiguate these words, but in practice, the increase in overall sparsity leads to performance degradation in NLP applications.
Multi-Domain Goal-Oriented Dialogues (MultiDoGO): Strategies toward Curating and Annotating Large Scale Dialogue Data
With a total of over 81K dialogues harvested across six domains, MultiDoGO is over 8 times the size of MultiWOZ, the other largest comparable dialogue dataset currently available to the public.
Identifying Nuances in Fake News vs. Satire: Using Semantic and Linguistic Cues
As avenues for future work, we consider studying additional linguistic features related to the humor aspect, and enriching the data with current news events, to help identify a political or social message.
Creating a Large Multi-Layered Representational Repository of Linguistic Code Switched Arabic Data
We present our effort to create a large Multi-Layered representational repository of Linguistic Code-Switched Arabic data.
Part of speech tagging for code switched data
We address the problem of Part of Speech tagging (POS) in the context of linguistic code switching (CS).
Overview for the Second Shared Task on Language Identification in Code-Switched Data
We present an overview of the second shared task on language identification in code-switched data.
WASA: A Web Application for Sequence Annotation
Data annotation is an important and necessary task for all NLP applications.
CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots
In this work, we propose a context-aware self-attentive NLU (CASA-NLU) model that uses multiple signals, such as previous intents, slots, dialog acts and utterances over a variable context window, in addition to the current user utterance.
Efficient Sentence Embedding using Discrete Cosine Transform
Vector averaging remains one of the most popular sentence embedding methods in spite of its obvious disregard for syntactic structure.
Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task
In the third shared task of the Computational Approaches to Linguistic Code-Switching (CALCS) workshop, we focus on Named Entity Recognition (NER) on code-switched social-media data.
Does Causal Coherence Predict Online Spread of Social Media?
In this paper, we test the hypothesis that causal and semantic coherence are associated with online sharing of misinformative social media content using Coh-Metrix – a widely-used set of psycholinguistic measures.
GWU NLP at SemEval-2019 Task 7: Hybrid Pipeline for Rumour Veracity and Stance Classification on Social Media
Social media plays a crucial role as the main resource news for information seekers online.
GWU NLP Lab at SemEval-2019 Task 3 : EmoContext: Effectiveness ofContextual Information in Models for Emotion Detection inSentence-level at Multi-genre Corpus
Our aim is to build a robust emotion classifier that can generalize emotion detection, which is to learn emotion cues in a noisy training environment.
Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data
In this paper, we address the problem of Part-of-Speech tagging (POS) in the context of linguistic code switching (CS).
GWU NLP Lab at SemEval-2019 Task 3: EmoContext: Effective Contextual Information in Models for Emotion Detection in Sentence-level in a Multigenre Corpus
In this paper we present an emotion classifier model submitted to the SemEval-2019 Task 3: EmoContext.
Scalable Cross-Lingual Transfer of Neural Sentence Embeddings
We develop and investigate several cross-lingual alignment approaches for neural sentence embedding models, such as the supervised inference classifier, InferSent, and sequential encoder-decoder models.
Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles
We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available.
The ARIEL-CMU Systems for LoReHLT18
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
Team SWEEPer: Joint Sentence Extraction and Fact Checking with Pointer Networks
We present experiments on the FEVER (Fact Extraction and VERification) task, a shared task that involves selecting sentences from Wikipedia and predicting whether a claim is supported by those sentences, refuted, or there is not enough information.
Predictive Linguistic Features of Schizophrenia
As such, we examine the writings of schizophrenia patients analyzing their syntax, semantics and pragmatics.
Emotion Detection and Classification in a Multigenre Corpus with Joint Multi-Task Deep Learning
Detection and classification of emotion categories expressed by a sentence is a challenging task due to subjectivity of emotion.
Emotion Detection and Classification
General Classification
+2
Evaluation of Unsupervised Compositional Representations
We evaluated various compositional models, from bag-of-words representations to compositional RNN-based models, on several extrinsic supervised and unsupervised evaluation benchmarks.
Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings
We show empirically that the performance of bilingual correspondents learned using our proposed unsupervised method is comparable to that of using supervised bilingual correspondents from a seed dictionary.
Transferring Semantic Roles Using Translation and Syntactic Information
Our paper addresses the problem of annotation projection for semantic role labeling for resource-poor languages using supervised annotations from a resource-rich language through parallel data.
GW\_QA at SemEval-2017 Task 3: Question Answer Re-ranking on Arabic Fora
This paper describes our submission to SemEval-2017 Task 3 Subtask D, {``}Question Answer Ranking in Arabic Community Question Answering{''}.
SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation
Semantic Textual Similarity (STS) measures the meaning similarity of sentences.
SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation
Semantic Textual Similarity (STS) measures the meaning similarity of sentences.
Arabic Textual Entailment with Word Embeddings
Determining the textual entailment between texts is important in many NLP tasks, such as summarization, question answering, and information extraction and retrieval.
A Layered Language Model based Hybrid Approach to Automatic Full Diacritization of Arabic
In this paper we present a system for automatic Arabic text diacritization using three levels of analysis granularity in a layered back off manner.
The Power of Language Music: Arabic Lemmatization through Patterns
The interaction between roots and patterns in Arabic has intrigued lexicographers and morphologists for centuries.
LILI: A Simple Language Independent Approach for Language Identification
We introduce a generic Language Independent Framework for Linguistic Code Switch Point Detection.
Using Ambiguity Detection to Streamline Linguistic Annotation
Arabic writing is typically underspecified for short vowels and other markups, referred to as diacritics.
SAMER: A Semi-Automatically Created Lexical Resource for Arabic Verbal Multiword Expressions Tokens Paradigm and their Morphosyntactic Features
We propose an automated method that identifies the morphological and syntactic flexibility of Arabic Verbal Multiword Expressions (AVMWE).
Automatic Verification and Augmentation of Multilingual Lexicons
We present an approach for automatic verification and augmentation of multilingual lexica.
Processing Dialectal Arabic: Exploiting Variability and Similarity to Overcome Challenges and Discover Opportunities
We recently witnessed an exponential growth in dialectal Arabic usage in both textual data and speech recordings especially in social media.
The GW/LT3 VarDial 2016 Shared Task System for Dialects and Similar Languages Detection
This paper describes the GW/LT3 contribution to the 2016 VarDial shared task on the identification of similar languages (task 1) and Arabic dialects (task 2).
SPLIT: Smart Preprocessing (Quasi) Language Independent Tool
Text preprocessing is an important and necessary task for all NLP applications.
Guidelines and Framework for a Large Scale Arabic Diacritized Corpus
This paper presents the annotation guidelines developed as part of an effort to create a large scale manually diacritized corpus for various Arabic text genres.
Explicit Fine grained Syntactic and Semantic Annotation of the Idafa Construction in Arabic
Identifying the various types of the Idafa construction (IC) is of importance to Natural Language processing (NLP) applications.
Statistical modality tagging from rule-based annotations and crowdsourcing
We explore training an automatic modality tagger.
SANA: A Large Scale Multi-Genre, Multi-Dialect Lexicon for Arabic Subjectivity and Sentiment Analysis
The computational treatment of subjectivity and sentiment in natural language is usually significantly improved by applying features exploiting lexical resources where entries are tagged with semantic orientation (e. g., positive, negative values).
MADAMIRA: A Fast, Comprehensive Tool for Morphological Analysis and Disambiguation of Arabic
In this paper, we present MADAMIRA, a system for morphological analysis and disambiguation of Arabic that combines some of the best aspects of two previously commonly used systems for Arabic processing, MADA (Habash and Rambow, 2005; Habash et al., 2009; Habash et al., 2013) and AMIRA (Diab et al., 2007).
Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon
Multiple levels of quality checks are performed on the output of each step in the creation process.
LDC Arabic Treebanks and Associated Corpora: Data Divisions Manual
The Linguistic Data Consortium (LDC) has developed hundreds of data corpora for natural language processing (NLP) research.
Annotations for Power Relations on Email Threads
In this paper, we describe a multi-layer annotation scheme for social power relations that are recognizable from online written interactions.
Conventional Orthography for Dialectal Arabic
Dialectal Arabic (DA) refers to the day-to-day vernaculars spoken in the Arab world.
AWATIF: A Multi-Genre Corpus for Modern Standard Arabic Subjectivity and Sentiment Analysis
We present AWATIF, a multi-genre corpus of Modern Standard Arabic (MSA) labeled for subjectivity and sentiment analysis (SSA) at the sentence level.
Simplified guidelines for the creation of Large Scale Dialectal Arabic Annotations
In this paper, we present a simplified Set of guidelines for detecting code switching in Arabic on the word/token level.
