Search Results for author: Mohammad Taher Pilehvar

Found 60 papers, 24 papers with code

Don’t Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques

1 code implementation Findings (EMNLP) 2021 Hossein Amirkhani, Mohammad Taher Pilehvar

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.

Bias Detection

On the Cross-lingual Transferability of Contextualized Sense Embeddings

no code implementations EMNLP (MRL) 2021 Kiamehr Rezaee, Daniel Loureiro, Jose Camacho-Collados, Mohammad Taher Pilehvar

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.

Word Embeddings Word Sense Disambiguation

Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task

no code implementations ACL 2022 Mohsen Tabasi, Kiamehr Rezaee, Mohammad Taher Pilehvar

As a recent development in few-shot learning, prompt-based techniques have demonstrated promising potential in a variety of natural language processing tasks.

Few-Shot Learning Language Modelling

On the Importance of Data Size in Probing Fine-tuned Models

1 code implementation Findings (ACL) 2022 Houman Mehrafarin, Sara Rajaee, Mohammad Taher Pilehvar

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

1 code implementation ACL 2022 Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar

To determine the importance of each token representation, we train a Contribution Predictor for each layer using a gradient-based saliency method.

Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations

no code implementations13 Sep 2021 Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar

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

no code implementations Findings (EMNLP) 2021 Sara Rajaee, Mohammad Taher Pilehvar

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

1 code implementation1 Sep 2021 Hossein Amirkhani, Mohammad Taher Pilehvar

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.

Bias Detection

ParsFEVER: a Dataset for Farsi Fact Extraction and Verification

1 code implementation Joint Conference on Lexical and Computational Semantics 2021 Majid Zarharan, Mahsa Ghaderan, Amin Pourdabiri, Zahra Sayedi, Behrouz Minaei-Bidgoli, Sauleh Eetemadi, Mohammad Taher Pilehvar

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

1 code implementation ACL 2021 Sara Rajaee, Mohammad Taher Pilehvar

Based on this observation, we propose a local cluster-based method to address the degeneration issue in contextual embedding spaces.

Embeddings in Natural Language Processing

no code implementations COLING 2020 Jose Camacho-Collados, Mohammad Taher Pilehvar

Embeddings have been one of the most important topics of interest in NLP for the past decade.

Word Embeddings

SemEval-2020 Task 3: Graded Word Similarity in Context

no code implementations SEMEVAL 2020 Carlos Santos Armendariz, Matthew Purver, Senja Pollak, Nikola Ljube{\v{s}}i{\'c}, Matej Ul{\v{c}}ar, Ivan Vuli{\'c}, Mohammad Taher Pilehvar

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.

Translation Word Similarity

Analysis and Evaluation of Language Models for Word Sense Disambiguation

1 code implementation CL (ACL) 2021 Daniel Loureiro, Kiamehr Rezaee, Mohammad Taher Pilehvar, Jose Camacho-Collados

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.

Language Modelling Word Sense Disambiguation

Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter

2 code implementations ACL 2020 Costanza Conforti, Jakob Berndt, Mohammad Taher Pilehvar, Chryssi Giannitsarou, Flavio Toxvaerd, Nigel Collier

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.

Stance Detection

WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context

1 code implementation EACL 2021 Anna Breit, Artem Revenko, Kiamehr Rezaee, Mohammad Taher Pilehvar, Jose Camacho-Collados

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)

Entity Linking Word Sense Disambiguation

On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation

1 code implementation WS 2019 Victor Prokhorov, Ehsan Shareghi, Yingzhen Li, Mohammad Taher Pilehvar, Nigel Collier

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.

Text Generation

On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping

no code implementations NAACL 2019 Mohammad Taher Pilehvar

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

1 code implementation NAACL 2019 Victor Prokhorov, Mohammad Taher Pilehvar, Nigel Collier

We present a novel method for mapping unrestricted text to knowledge graph entities by framing the task as a sequence-to-sequence problem.

Towards Automatic Fake News Detection: Cross-Level Stance Detection in News Articles

no code implementations WS 2018 Costanza Conforti, Mohammad Taher Pilehvar, Nigel Collier

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.

Fake News Detection Stance Detection

A Pragmatic Guide to Geoparsing Evaluation

1 code implementation29 Oct 2018 Milan Gritta, Mohammad Taher Pilehvar, Nigel Collier

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.

Named Entity Recognition NER +1

Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models

no code implementations EMNLP 2018 Mohammad Taher Pilehvar, Dimitri Kartsaklis, Victor Prokhorov, Nigel Collier

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.

Word Embeddings Word Similarity

WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations

1 code implementation NAACL 2019 Mohammad Taher Pilehvar, Jose Camacho-Collados

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.

Word Embeddings Word Similarity

Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs

no code implementations EMNLP 2018 Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier

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.

General Classification Word Embeddings

The Interplay between Lexical Resources and Natural Language Processing

no code implementations NAACL 2018 Jose Camacho-Collados, Luis Espinosa-Anke, Mohammad Taher Pilehvar

Incorporating linguistic, world and common sense knowledge into AI/NLP systems is currently an important research area, with several open problems and challenges.

Common Sense Reasoning

Which Melbourne? Augmenting Geocoding with Maps

no code implementations ACL 2018 Milan Gritta, Mohammad Taher Pilehvar, Nigel Collier

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

no code implementations10 May 2018 Jose Camacho-Collados, Mohammad Taher Pilehvar

Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications.

SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity

no code implementations SEMEVAL 2017 Jose Camacho-Collados, Mohammad Taher Pilehvar, Nigel Collier, Roberto Navigli

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.

14 Information Retrieval +8

Learning Rare Word Representations using Semantic Bridging

no code implementations24 Jul 2017 Victor Prokhorov, Mohammad Taher Pilehvar, Dimitri Kartsaklis, Pietro Lió, Nigel Collier

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.

Graph Embedding Word Similarity

On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis

3 code implementations WS 2018 Jose Camacho-Collados, Mohammad Taher Pilehvar

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.

Sentiment Analysis Text Categorization +1

Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources

no code implementations EACL 2017 Mohammad Taher Pilehvar, Nigel Collier

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 Embeddings

Word Vector Space Specialisation

no code implementations EACL 2017 Ivan Vuli{\'c}, Nikola Mrk{\v{s}}i{\'c}, Mohammad Taher Pilehvar

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.

Lexical Entailment Representation Learning +2

De-Conflated Semantic Representations

1 code implementation EMNLP 2016 Mohammad Taher Pilehvar, Nigel Collier

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 Similarity Semantic Textual Similarity

Semantic Representations of Word Senses and Concepts

no code implementations2 Aug 2016 José Camacho-Collados, Ignacio Iacobacci, Roberto Navigli, Mohammad Taher Pilehvar

Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days.

Cannot find the paper you are looking for? You can Submit a new open access paper.