research
∙
09/18/2023
Hierarchy Builder: Organizing Textual Spans into a Hierarchy to Facilitate Navigation
Information extraction systems often produce hundreds to thousands of st...
share
research
∙
06/24/2023
Unsupervised Mapping of Arguments of Deverbal Nouns to Their Corresponding Verbal Labels
Deverbal nouns are nominal forms of verbs commonly used in written Engli...
research
∙
06/15/2023
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
Text-conditioned image generation models often generate incorrect associ...
research
∙
05/28/2023
An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation
Sign language translation systems are complex and require many component...
research
∙
05/26/2023
Conjunct Resolution in the Face of Verbal Omissions
Verbal omissions are complex syntactic phenomena in VP coordination stru...
research
∙
05/24/2023
ChatGPT and Simple Linguistic Inferences: Blind Spots and Blinds
This paper sheds light on the limitations of ChatGPT's understanding cap...
research
∙
05/21/2023
Retrieving Texts based on Abstract Descriptions
In this work, we aim to connect two research areas: instruction models a...
research
∙
05/17/2023
Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks
Data contamination has become especially prevalent and challenging with ...
research
∙
05/04/2023
Neighboring Words Affect Human Interpretation of Saliency Explanations
Word-level saliency explanations ("heat maps over words") are often used...
research
∙
05/04/2023
Conformal Nucleus Sampling
Language models generate text based on successively sampling the next wo...
research
∙
03/19/2023
Two Kinds of Recall
It is an established assumption that pattern-based models are good at pr...
research
∙
03/07/2023
At Your Fingertips: Extracting Piano Fingering Instructions from Videos
Piano fingering – knowing which finger to use to play each note in a mus...
research
∙
10/23/2022
Lexical Generalization Improves with Larger Models and Longer Training
While fine-tuned language models perform well on many tasks, they were a...
research
∙
10/19/2022
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models
We study the way DALLE-2 maps symbols (words) in the prompt to their ref...
research
∙
10/18/2022
Linear Guardedness and its Implications
Previous work on concept identification in neural representations has fo...
research
∙
10/12/2022
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
Recently, the community has achieved substantial progress on many common...
research
∙
10/07/2022
Understanding Transformer Memorization Recall Through Idioms
To produce accurate predictions, language models (LMs) must balance betw...
research
∙
09/09/2022
F-COREF: Fast, Accurate and Easy to Use Coreference Resolution
We introduce fastcoref, a python package for fast, accurate, and easy-to...
research
∙
07/28/2022
Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Large amounts of training data are one of the major reasons for the high...
research
∙
06/26/2022
Rivendell: Project-Based Academic Search Engine
Finding relevant research literature in online databases is a familiar c...
research
∙
05/25/2022
LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
While coreference resolution typically involves various linguistic chall...
research
∙
05/04/2022
A Dataset for N-ary Relation Extraction of Drug Combinations
Combination therapies have become the standard of care for diseases such...
research
∙
04/26/2022
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models
The opaque nature and unexplained behavior of transformer-based language...
research
∙
04/20/2022
Analyzing Gender Representation in Multilingual Models
Multilingual language models were shown to allow for nontrivial transfer...
research
∙
03/28/2022
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Transformer-based language models (LMs) are at the core of modern NLP, b...
research
∙
01/28/2022
Adversarial Concept Erasure in Kernel Space
The representation space of neural models for textual data emerges in an...
research
∙
01/28/2022
Linear Adversarial Concept Erasure
Modern neural models trained on textual data rely on pre-trained represe...
research
∙
01/27/2022
Human Interpretation of Saliency-based Explanation Over Text
While a lot of research in explainable AI focuses on producing effective...
research
∙
01/27/2022
Diagnosing AI Explanation Methods with Folk Concepts of Behavior
When explaining AI behavior to humans, how is the communicated informati...
research
∙
12/28/2021
Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
The problem of comparing two bodies of text and searching for words that...
research
∙
10/14/2021
Large Scale Substitution-based Word Sense Induction
We present a word-sense induction method based on pre-trained masked lan...
research
∙
09/24/2021
Text-based NP Enrichment
Understanding the relations between entities denoted by NPs in text is a...
research
∙
09/10/2021
Asking It All: Generating Contextualized Questions for any Semantic Role
Asking questions about a situation is an inherent step towards understan...
research
∙
06/30/2021
On the Power of Saturated Transformers: A View from Circuit Complexity
Transformers have become a standard architecture for many NLP problems. ...
research
∙
06/18/2021
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
We show that with small-to-medium training data, fine-tuning only the bi...
research
∙
06/13/2021
Thinking Like Transformers
What is the computational model behind a Transformer? Where recurrent ne...
research
∙
06/08/2021
Neural Extractive Search
Domain experts often need to extract structured information from large c...
research
∙
05/14/2021
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction
When language models process syntactically complex sentences, do they us...
research
∙
04/22/2021
Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand?
Language models trained on billions of tokens have recently led to unpre...
research
∙
04/17/2021
Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
We explore Few-Shot Learning (FSL) for Relation Classification (RC). Foc...
research
∙
04/16/2021
Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema
The Winograd Schema (WS) has been proposed as a test for measuring commo...
research
∙
04/15/2021
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
Large Transformers pretrained over clinical notes from Electronic Health...
research
∙
03/02/2021
Contrastive Explanations for Model Interpretability
Contrastive explanations clarify why an event occurred in contrast to an...
research
∙
02/09/2021
Bootstrapping Relation Extractors using Syntactic Search by Examples
The advent of neural-networks in NLP brought with it substantial improve...
research
∙
01/18/2021
A simple geometric proof for the benefit of depth in ReLU networks
We present a simple proof for the benefit of depth in multi-layer feedfo...
research
∙
12/08/2020
Facts2Story: Controlling Text Generation by Key Facts
Recent advancements in self-attention neural network architectures have ...
research
∙
10/19/2020
Parameter Norm Growth During Training of Transformers
The capacity of neural networks like the widely adopted transformer is k...
research
∙
10/16/2020
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Recent works have demonstrated that multilingual BERT (mBERT) learns ric...
research
∙
10/15/2020
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Trust is a central component of the interaction between people and AI, i...
research
∙
10/12/2020