Nafise Sadat Moosavi | DeepAI

DeepAI AI Chat

Featured Co-authors

Iryna Gurevych
161 publications
Dan Roth
151 publications
Kristian Kersting
114 publications
Steffen Eger
48 publications
Michael Strube
21 publications
Victor Sanh
17 publications
Gözde Gül Şahin
16 publications
Massimo Poesio
15 publications
Andreas Rücklé
15 publications
Benjamin Heinzerling
12 publications
Juntao Yu
11 publications

∙ 05/27/2023

FERMAT: An Alternative to Accuracy for Numerical Reasoning

While pre-trained language models achieve impressive performance on vari...

0 Jasivan Alex Sivakumar, et al. ∙

∙ 04/25/2023

Lessons Learned from a Citizen Science Project for Natural Language Processing

Many Natural Language Processing (NLP) systems use annotated corpora for...

0 Jan-Christoph Klie, et al. ∙

∙ 09/06/2022

Layer or Representation Space: What makes BERT-based Evaluation Metrics Robust?

The evaluation of recent embedding-based evaluation metrics for text gen...

0 Doan Nam Long Vu, et al. ∙

∙ 08/30/2022

Transformers with Learnable Activation Functions

Activation functions can have a significant impact on reducing the topol...

0 Haishuo Fang, et al. ∙

∙ 05/24/2022

Scoring Coreference Chains with Split-Antecedent Anaphors

Anaphoric reference is an aspect of language interpretation covering a v...

0 Silviu Paun, et al. ∙

∙ 05/13/2022

Improving the Numerical Reasoning Skills of Pretrained Language Models

State-of-the-art pretrained language models tend to perform below their ...

12 Dominic Petrak, et al. ∙

∙ 05/12/2022

Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization

Neural abstractive summarization models are prone to generate summaries ...

21 Prasetya Ajie Utama, et al. ∙

∙ 05/03/2022

Adaptable Adapters

State-of-the-art pretrained NLP models contain a hundred million to tril...

1 Nafise Sadat Moosavi, et al. ∙

∙ 09/09/2021

Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning

Recent prompt-based approaches allow pretrained language models to achie...

16 Prasetya Ajie Utama, et al. ∙

∙ 04/16/2021

Learning to Reason for Text Generation from Scientific Tables

In this paper, we introduce SciGen, a new challenge dataset for the task...

0 Nafise Sadat Moosavi, et al. ∙

∙ 04/12/2021

Stay Together: A System for Single and Split-antecedent Anaphora Resolution

The state-of-the-art on basic, single-antecedent anaphora has greatly im...

0 Juntao Yu, et al. ∙

∙ 12/31/2020

Coreference Reasoning in Machine Reading Comprehension

The ability to reason about multiple references to a given entity is ess...

2 Mingzhu Wu, et al. ∙

∙ 10/31/2020

Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution

Now that the performance of coreference resolvers on the simpler forms o...

0 Juntao Yu, et al. ∙

∙ 10/23/2020

Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures

Existing NLP datasets contain various biases, and models tend to quickly...

0 Nafise Sadat Moosavi, et al. ∙

∙ 10/07/2020

Improving QA Generalization by Concurrent Modeling of Multiple Biases

Existing NLP datasets contain various biases that models can easily expl...

0 Mingzhu Wu, et al. ∙

∙ 09/25/2020

Towards Debiasing NLU Models from Unknown Biases

NLU models often exploit biases to achieve high dataset-specific perform...

0 Prasetya Ajie Utama, et al. ∙

∙ 05/01/2020

Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance

Models for natural language understanding (NLU) tasks often rely on the ...

0 Prasetya Ajie Utama, et al. ∙

∙ 11/13/2019

Neural Duplicate Question Detection without Labeled Training Data

Supervised training of neural models to duplicate question detection in ...

0 Andreas Rücklé, et al. ∙

∙ 09/19/2019

Improving Generalization by Incorporating Coverage in Natural Language Inference

The task of natural language inference (NLI) is to identify the relation...

0 Nafise Sadat Moosavi, et al. ∙

∙ 06/16/2019

Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection

The common practice in coreference resolution is to identify and evaluat...

0 Nafise Sadat Moosavi, et al. ∙

∙ 08/01/2017

Enhancing the Input Representation: From Complexity to Simplicity

We introduce an efficient algorithm for mining informative combinations ...

0 Nafise Sadat Moosavi, et al. ∙

∙ 07/20/2017

Revisiting Selectional Preferences for Coreference Resolution

Selectional preferences have long been claimed to be essential for coref...

0 Benjamin Heinzerling, et al. ∙

∙ 04/22/2017

Lexical Features in Coreference Resolution: To be Used With Caution

Lexical features are a major source of information in state-of-the-art c...

0 Nafise Sadat Moosavi, et al. ∙

∙ 02/24/2017

Use Generalized Representations, But Do Not Forget Surface Features

Only a year ago, all state-of-the-art coreference resolvers were using a...

0 Nafise Sadat Moosavi, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world