Search Results for author:
Found 102 papers, 43 papers with code
DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect Extraction
We name this scheme DILBERT: Domain Invariant Learning with BERT, and customize it for aspect extraction in the unsupervised domain adaptation setting.
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Crosslingual Lexical Semantic Similarity
We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering data sets for 12 typologically diverse languages, including major languages (e. g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e. g., Welsh, Kiswahili).
On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs
This surge in usage has led to an explosion in NLP model interpretability and analysis research, accompanied by numerous technical surveys.
Can LLMs Learn Macroeconomic Narratives from Social Media?
This study empirically tests the $\textit{Narrative Economics}$ hypothesis, which posits that narratives (ideas that are spread virally and affect public beliefs) can influence economic fluctuations.
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
In this work, we study the impact of such exposure to new knowledge on the capability of the fine-tuned model to utilize its pre-existing knowledge.
Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language
Automatic conversion of free-text radiology reports into structured data using Natural Language Processing (NLP) techniques is crucial for analyzing diseases on a large scale.
Bored to Death: Artificial Intelligence Research Reveals the Role of Boredom in Suicide Behavior
This secondary dataset included responses by 1, 062 participants to the same suicide scale as well as to well-validated scales measuring depression and boredom.
The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth
Queer youth face increased mental health risks, such as depression, anxiety, and suicidal ideation.
Systematic Biases in LLM Simulations of Debates
Recent advancements in natural language processing, especially the emergence of Large Language Models (LLMs), have opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately.
Can LLMs Replace Economic Choice Prediction Labs? The Case of Language-based Persuasion Games
Human choice prediction in economic contexts is crucial for applications in marketing, finance, public policy, and more.
Decoding Stumpers: Large Language Models vs. Human Problem-Solvers
This paper investigates the problem-solving capabilities of Large Language Models (LLMs) by evaluating their performance on stumpers, unique single-step intuition problems that pose challenges for human solvers but are easily verifiable.
The Temporal Structure of Language Processing in the Human Brain Corresponds to The Layered Hierarchy of Deep Language Models
Our results reveal a connection between human language processing and DLMs, with the DLM's layer-by-layer accumulation of contextual information mirroring the timing of neural activity in high-order language areas.
Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
Text-To-Image (TTI) models, such as DALL-E and StableDiffusion, have demonstrated remarkable prompt-based image generation capabilities.
Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space.
Measuring the Robustness of NLP Models to Domain Shifts
We then conducted a comprehensive large-scale DR study involving over 14, 000 domain shifts across 21 fine-tuned models and few-shot LLMs.
Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation
Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents.
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training
In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users.
A Picture May Be Worth a Thousand Lives: An Interpretable Artificial Intelligence Strategy for Predictions of Suicide Risk from Social Media Images
Notably, the study illustrates the advantages of hybrid models in such complicated tasks and provides simple and flexible prediction strategies that could be utilized to develop real-life monitoring tools of suicide.
Text2Model: Text-based Model Induction for Zero-shot Image Classification
Our approach generates non-linear classifiers and can handle rich textual descriptions.
Domain Adaptation from Scratch
In this setup, we aim to efficiently annotate data from a set of source domains such that the trained model performs well on a sensitive target domain from which data is unavailable for annotation.
Multi-task Active Learning for Pre-trained Transformer-based Models
Multi-task learning, in which several tasks are jointly learned by a single model, allows NLP models to share information from multiple annotations and may facilitate better predictions when the tasks are inter-related.
On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method
We find that high benchmark scores do not necessarily translate to strong robustness, and that various methods can perform extremely differently under different settings.
A Functional Information Perspective on Model Interpretation
This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input.
In the Eye of the Beholder: Robust Prediction with Causal User Modeling
Accurately predicting the relevance of items to users is crucial to the success of many social platforms.
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
We introduce CEBaB, a new benchmark dataset for assessing concept-based explanation methods in Natural Language Processing (NLP).
Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies
Discrete variational auto-encoders (VAEs) are able to represent semantic latent spaces in generative learning.
Example-based Hypernetworks for Out-of-Distribution Generalization
Our innovative framework employs example-based Hypernetwork adaptation: a T5 encoder-decoder initially generates a unique signature from an input example, embedding it within the source domains' semantic space.
DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation
Natural language processing (NLP) algorithms have become very successful, but they still struggle when applied to out-of-distribution examples.
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
A fundamental goal of scientific research is to learn about causal relationships.
DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction
We name this scheme DILBERT: Domain Invariant Learning with BERT, and customize it for aspect extraction in the unsupervised domain adaptation setting.
Towards Zero-shot Language Modeling
Motivated by this question, we aim at constructing an informative prior over neural weights, in order to adapt quickly to held-out languages in the task of character-level language modeling.
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions
Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with.
Designing an Automatic Agent for Repeated Language based Persuasion Games
Persuasion games are fundamental in economics and AI research and serve as the basis for important applications.
PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains
We address a challenging and underexplored version of this domain adaptation problem, where an algorithm is trained on several source domains, and then applied to examples from unseen domains that are unknown at training time.
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP.
Model Compression for Domain Adaptation through Causal Effect Estimation
Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters.
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT.
Predicting Decisions in Language Based Persuasion Games
Our results demonstrate that given a prefix of the interaction sequence, our models can predict the future decisions of the decision-maker, particularly when a sequential modeling approach and hand-crafted textual features are applied.
Semantically Driven Sentence Fusion: Modeling and Evaluation
Sentence fusion is the task of joining related sentences into coherent text.
PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models
Pivot-based neural representation models have lead to significant progress in domain adaptation for NLP.
CausaLM: Causal Model Explanation Through Counterfactual Language Models
Concretely, we show that by carefully choosing auxiliary adversarial pre-training tasks, language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest, and be used to estimate its true causal effect on model performance.
Multidirectional Associative Optimization of Function-Specific Word Representations
We present a neural framework for learning associations between interrelated groups of words such as the ones found in Subject-Verb-Object (SVO) structures.
The Structured Weighted Violations MIRA
We present the Structured Weighted Violation MIRA (SWVM), a new structured prediction algorithm that is based on an hybridization between MIRA (Crammer and Singer, 2003) and the structured weighted violations perceptron (SWVP) (Dror and Reichart, 2016).
Predicting Strategic Behavior from Free Text
In ablation analysis, we demonstrate the importance of our modeling choices---the representation of the text with the commonsensical personality attributes and our classifier---to the predictive power of our model.
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity
We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering datasets for 12 typologically diverse languages, including major languages (e. g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones (e. g., Welsh, Kiswahili).
Geosocial Location Classification: Associating Type to Places Based on Geotagged Social-Media Posts
We explore two approaches to the problem: (a) a pipeline approach, where each message is first classified, and then the location associated with the message set is inferred from the individual message labels; and (b) a joint approach where the individual messages are simultaneously processed to yield the desired location type.
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
In this work, we propose a Bayesian generative model for the space of neural parameters.
The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures
Performance in cross-lingual NLP tasks is impacted by the (dis)similarity of languages at hand: e. g., previous work has suggested there is a connection between the expected success of bilingual lexicon induction (BLI) and the assumption of (approximate) isomorphism between monolingual embedding spaces.
Zero-Shot Semantic Parsing for Instructions
We consider a zero-shot semantic parsing task: parsing instructions into compositional logical forms, in domains that were not seen during training.
Deep Contextualized Self-training for Low Resource Dependency Parsing
Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages.
Cross-lingual Semantic Specialization via Lexical Relation Induction
Semantic specialization integrates structured linguistic knowledge from external resources (such as lexical relations in WordNet) into pretrained distributional vectors in the form of constraints.
Predicting In-game Actions from Interviews of NBA Players
We find that our best performing textual model is most associated with topics that are intuitively related to each prediction task and that better models yield higher correlation with more informative topics.
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages
Recent work has validated the importance of subword information for word representation learning.
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?
A series of bilingual lexicon induction (BLI) experiments with 15 diverse languages (210 language pairs) show that fully unsupervised CLWE methods still fail for a large number of language pairs (e. g., they yield zero BLI performance for 87/210 pairs).
Deep Dominance - How to Properly Compare Deep Neural Models
Comparing between Deep Neural Network (DNN) models based on their performance on unseen data is crucial for the progress of the NLP field.
Task Refinement Learning for Improved Accuracy and Stability of Unsupervised Domain Adaptation
Pivot Based Language Modeling (PBLM) (Ziser and Reichart, 2018a), combining LSTMs with pivot-based methods, has yielded significant progress in unsupervised domain adaptation.
Bayesian Learning for Neural Dependency Parsing
While neural dependency parsers provide state-of-the-art accuracy for several languages, they still rely on large amounts of costly labeled training data.
Perturbation Based Learning for Structured NLP Tasks with Application to Dependency Parsing
In this paper we propose a perturbation-based approach where sampling from a probabilistic model is computationally efficient.
Neural Transition Based Parsing of Web Queries: An Entity Based Approach
Pinter et al. (2016) has formalized the grammar of these queries and proposed semi-supervised algorithms for the adaptation of parsers originally designed to parse according to the standard dependency grammar, so that they can account for the unique forest grammar of queries.
On the Relation between Linguistic Typology and (Limitations of) Multilingual Language Modeling
A key challenge in cross-lingual NLP is developing general language-independent architectures that are equally applicable to any language.
Deep Pivot-Based Modeling for Cross-language Cross-domain Transfer with Minimal Guidance
In the full setup the model has access to unlabeled data from both pairs, while in the lazy setup, which is more realistic for truly resource-poor languages, unlabeled data is available for both domains but only for the source language.
Appendix - Recommended Statistical Significance Tests for NLP Tasks
Statistical significance testing plays an important role when drawing conclusions from experimental results in NLP papers.
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
Linguistic typology aims to capture structural and semantic variation across the world's languages.
Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP
The transfer or share of knowledge between languages is a potential solution to resource scarcity in NLP.
The Hitchhiker's Guide to Testing Statistical Significance in Natural Language Processing
We establish the fundamental concepts of significance testing and discuss the specific aspects of NLP tasks, experimental setups and evaluation measures that affect the choice of significance tests in NLP research.
Bridging Languages through Images with Deep Partial Canonical Correlation Analysis
We present a deep neural network that leverages images to improve bilingual text embeddings.
Pivot Based Language Modeling for Improved Neural Domain Adaptation
Particularly, our model processes the information in the text with a sequential NN (LSTM) and its output consists of a representation vector for every input word.
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction
Neural architectures are prominent in the construction of language models (LMs).
Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets
With the ever-growing amounts of textual data from a large variety of languages, domains, and genres, it has become standard to evaluate NLP algorithms on multiple datasets in order to ensure consistent performance across heterogeneous setups.
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.
Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules
Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that have similar distributional signatures.
Sarcasm SIGN: Interpreting Sarcasm with Sentiment Based Monolingual Machine Translation
Sarcasm is a form of speech in which speakers say the opposite of what they truly mean in order to convey a strong sentiment.
Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.
Survey on the Use of Typological Information in Natural Language Processing
In recent years linguistic typology, which classifies the world's languages according to their functional and structural properties, has been widely used to support multilingual NLP.
Neural Structural Correspondence Learning for Domain Adaptation
Particularly, our model is a three-layer neural network that learns to encode the nonpivot features of an input example into a low-dimensional representation, so that the existence of pivot features (features that are prominent in both domains and convey useful information for the NLP task) in the example can be decoded from that representation.
Effective Combination of Language and Vision Through Model Composition and the R-CCA Method
We address the problem of integrating textual and visual information in vector space models for word meaning representation.
A Factorized Model for Transitive Verbs in Compositional Distributional Semantics
We present a factorized compositional distributional semantics model for the representation of transitive verb constructions.
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations
With our selected context configurations, we train on only 14% (A), 26. 2% (V), and 33. 6% (N) of all dependency-based contexts, resulting in a reduced training time.
SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity
Verbs play a critical role in the meaning of sentences, but these ubiquitous words have received little attention in recent distributional semantics research.
The Yahoo Query Treebank, V. 1.0
A description and annotation guidelines for the Yahoo Webscope release of Query Treebank, Version 1. 0, May 2016.
Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL
This work examines the impact of cross-linguistic transfer on grammatical errors in English as Second Language (ESL) texts.
The Structured Weighted Violations Perceptron Algorithm
We present the Structured Weighted Violations Perceptron (SWVP) algorithm, a new structured prediction algorithm that generalizes the Collins Structured Perceptron (CSP).
Edge-Linear First-Order Dependency Parsing with Undirected Minimum Spanning Tree Inference
The run time complexity of state-of-the-art inference algorithms in graph-based dependency parsing is super-linear in the number of input words (n).
Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling
A common evaluation practice in the vector space models (VSMs) literature is to measure the models' ability to predict human judgments about lexical semantic relations between word pairs.
Unsupervised Declarative Knowledge Induction for Constraint-Based Learning of Information Structure in Scientific Documents
Inferring the information structure of scientific documents is useful for many NLP applications.
SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation
We present SimLex-999, a gold standard resource for evaluating distributional semantic models that improves on existing resources in several important ways.
Reconstructing Native Language Typology from Foreign Language Usage
Linguists and psychologists have long been studying cross-linguistic transfer, the influence of native language properties on linguistic performance in a foreign language.
Multi-Modal Models for Concrete and Abstract Concept Meaning
Multi-modal models that learn semantic representations from both linguistic and perceptual input outperform language-only models on a range of evaluations, and better reflect human concept acquisition.
