Search Results for author:
Found 78 papers, 37 papers with code
On the Cross-lingual Transferability of Contextualized Sense Embeddings
In this paper we analyze the extent to which contextualized sense embeddings, i. e., sense embeddings that are computed based on contextualized word embeddings, are transferable across languages. To this end, we compiled a unified cross-lingual benchmark for Word Sense Disambiguation.
Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task
As a recent development in few-shot learning, prompt-based techniques have demonstrated promising potential in a variety of natural language processing tasks.
Incorporating Stock Market Signals for Twitter Stance Detection
Research in stance detection has so far focused on models which leverage purely textual input.
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models.
DadmaTools: Natural Language Processing Toolkit for Persian Language
We introduce DadmaTools, an open-source Python Natural Language Processing toolkit for the Persian language.
Synthetic Examples Improve Cross-Target Generalization: A Study on Stance Detection on a Twitter corpus.
Cross-target generalization is a known problem in stance detection (SD), where systems tend to perform poorly when exposed to targets unseen during training.
Don’t Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques
A common core assumption of these techniques is that the main model handles biased instances similarly to the biased model, in that it will resort to biases whenever available.
Adversarial Training for News Stance Detection: Leveraging Signals from a Multi-Genre Corpus.
Cross-target generalization constitutes an important issue for news Stance Detection (SD).
Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against such exploits.
Gender Encoding Patterns in Pretrained Language Model Representations
Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges.
PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian
Large language models predominantly reflect Western cultures, largely due to the dominance of English-centric training data.
Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets
The multifaceted challenge of accurately measuring gender stereotypical bias in language models is akin to discerning different segments of a broader, unseen entity.
FarExStance: Explainable Stance Detection for Farsi
We compare the performance of a fine-tuned multilingual RoBERTa model to several large language models in zero-shot, few-shot, and parameter-efficient fine-tuned settings on our new dataset.
NormXLogit: The Head-on-Top Never Lies
Despite recent successes in the interpretability of LLMs, many existing approaches rely on complex methods that are often tied to a specific model design and come with a significant computational cost.
LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
Why do gradient-based explanations struggle with Transformers, and how can we improve them?
RepMatch: Quantifying Cross-Instance Similarities in Representation Space
Advances in dataset analysis techniques have enabled more sophisticated approaches to analyzing and characterizing training data instances, often categorizing data based on attributes such as ``difficulty''.
SkipPLUS: Skip the First Few Layers to Better Explain Vision Transformers
Despite their remarkable performance, the explainability of Vision Transformers (ViTs) remains a challenge.
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
To address this issue, we introduce BLEnD, a hand-crafted benchmark designed to evaluate LLMs' everyday knowledge across diverse cultures and languages.
Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models
This paper presents a comprehensive analysis of explainable fact-checking through a series of experiments, focusing on the ability of large language models to verify public health claims and provide explanations or justifications for their veracity assessments.
DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias
We use DiFair as a benchmark for a number of widely-used pretained language models and debiasing techniques.
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
An emerging solution for explaining Transformer-based models is to use vector-based analysis on how the representations are formed.
Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities
A popular workaround is to train a robust model by re-weighting training examples based on a secondary biased model.
An Empirical Study on the Transferability of Transformer Modules in Parameter-Efficient Fine-Tuning
Parameter-efficient fine-tuning approaches have recently garnered a lot of attention.
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
In this work, we employ these two metrics for the first time in NLP.
Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference
It has been shown that NLI models are usually biased with respect to the word-overlap between premise and hypothesis; they take this feature as a primary cue for predicting the entailment label.
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
There has been a growing interest in interpreting the underlying dynamics of Transformers.
On the Importance of Data Size in Probing Fine-tuned Models
The analysis also reveals that larger training data mainly affects higher layers, and that the extent of this change is a factor of the number of iterations updating the model during fine-tuning rather than the diversity of the training samples.
AdapLeR: Speeding up Inference by Adaptive Length Reduction
To determine the importance of each token representation, we train a Contribution Predictor for each layer using a gradient-based saliency method.
An Isotropy Analysis in the Multilingual BERT Embedding Space
However, we observe no such dimensions in the multilingual BERT.
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models.
How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy
It is widely accepted that fine-tuning pre-trained language models usually brings about performance improvements in downstream tasks.
Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques
A common core assumption of these techniques is that the main model handles biased instances similarly to the biased model, in that it will resort to biases whenever available.
ParsFEVER: a Dataset for Farsi Fact Extraction and Verification
Training and evaluation of automatic fact extraction and verification techniques require large amounts of annotated data which might not be available for low-resource languages.
A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space
Based on this observation, we propose a local cluster-based method to address the degeneration issue in contextual embedding spaces.
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
Several studies have been carried out on revealing linguistic features captured by BERT.
SemEval-2020 Task 3: Graded Word Similarity in Context
This paper presents the Graded Word Similarity in Context (GWSC) task which asked participants to predict the effects of context on human perception of similarity in English, Croatian, Slovene and Finnish.
Embeddings in Natural Language Processing
Embeddings have been one of the most important topics of interest in NLP for the past decade.
STANDER: An Expert-Annotated Dataset for News Stance Detection and Evidence Retrieval
We present a new challenging news dataset that targets both stance detection (SD) and fine-grained evidence retrieval (ER).
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization
The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques.
Analysis and Evaluation of Language Models for Word Sense Disambiguation
We also perform an in-depth comparison of the two main language model based WSD strategies, i. e., fine-tuning and feature extraction, finding that the latter approach is more robust with respect to sense bias and it can better exploit limited available training data.
Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter
We present a new challenging stance detection dataset, called Will-They-Won't-They (WT-WT), which contains 51, 284 tweets in English, making it by far the largest available dataset of the type.
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context
More specifically, we introduce a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as a binary classification task thus being independent of external sense inventories, and the coverage of various domains.
Ranked #1 on
Entity Linking
on WiC-TSV
(Task 3 Accuracy: all metric)
On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation
While the explicit constraint naturally avoids posterior collapse, we use it to further understand the significance of the KL term in controlling the information transmitted through the VAE channel.
On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping
Meaning conflation deficiency is one of the main limiting factors of word representations which, given their widespread use at the core of many NLP systems, can lead to inaccurate semantic understanding of the input text and inevitably hamper the performance.
Generating Knowledge Graph Paths from Textual Definitions using Sequence-to-Sequence Models
We present a novel method for mapping unrestricted text to knowledge graph entities by framing the task as a sequence-to-sequence problem.
Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces
Word embedding techniques heavily rely on the abundance of training data for individual words.
Towards Automatic Fake News Detection: Cross-Level Stance Detection in News Articles
In this paper, we propose to adapt the four-staged pipeline proposed by Zubiaga et al. (2018) for the Rumor Verification task to the problem of Fake News Detection.
A Pragmatic Guide to Geoparsing Evaluation
Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems.
Large-scale Exploration of Neural Relation Classification Architectures
Experimental performance on the task of relation classification has generally improved using deep neural network architectures.
Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models
Rare word representation has recently enjoyed a surge of interest, owing to the crucial role that effective handling of infrequent words can play in accurate semantic understanding.
WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations
By design, word embeddings are unable to model the dynamic nature of words' semantics, i. e., the property of words to correspond to potentially different meanings.
Ranked #14 on
Word Sense Disambiguation
on Words in Context
Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs
Further, the knowledge base space is prepared by collecting random walks from a graph enhanced with textual features, which act as a set of semantic bridges between text and knowledge base entities.
The Interplay between Lexical Resources and Natural Language Processing
Incorporating linguistic, world and common sense knowledge into AI/NLP systems is currently an important research area, with several open problems and challenges.
Which Melbourne? Augmenting Geocoding with Maps
The purpose of text geolocation is to associate geographic information contained in a document with a set (or sets) of coordinates, either implicitly by using linguistic features and/or explicitly by using geographic metadata combined with heuristics.
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning
Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications.
Towards a Seamless Integration of Word Senses into Downstream NLP Applications
Lexical ambiguity can impede NLP systems from accurate understanding of semantics.
SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity
This paper introduces a new task on Multilingual and Cross-lingual SemanticThis paper introduces a new task on Multilingual and Cross-lingual Semantic Word Similarity which measures the semantic similarity of word pairs within and across five languages: English, Farsi, German, Italian and Spanish.
Learning Rare Word Representations using Semantic Bridging
We propose a methodology that adapts graph embedding techniques (DeepWalk (Perozzi et al., 2014) and node2vec (Grover and Leskovec, 2016)) as well as cross-lingual vector space mapping approaches (Least Squares and Canonical Correlation Analysis) in order to merge the corpus and ontological sources of lexical knowledge.
On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis
In this paper we investigate the impact of simple text preprocessing decisions (particularly tokenizing, lemmatizing, lowercasing and multiword grouping) on the performance of a standard neural text classifier.
Ranked #10 on
Text Classification
on Ohsumed
Vancouver Welcomes You! Minimalist Location Metonymy Resolution
Named entities are frequently used in a metonymic manner.
Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources
We put forward an approach that exploits the knowledge encoded in lexical resources in order to induce representations for words that were not encountered frequently during training.
Word Vector Space Specialisation
Specialising vector spaces to maximise their content with respect to one key property of vector space models (e. g. semantic similarity vs. relatedness or lexical entailment) while mitigating others has become an active and attractive research topic in representation learning.
De-Conflated Semantic Representations
One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have.
Semantic Representations of Word Senses and Concepts
Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days.
