Search Results for author:
Found 29 papers, 16 papers with code
A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition
To do this, we developed a pipeline for OCR processing and labeling of comic books and created the first text detection and recognition datasets for western comics, called "COMICS Text+: Detection" and "COMICS Text+: Recognition".
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings
Drawings are powerful means of pictorial abstraction and communication.
Ranked #1 on
Weakly Supervised Object Detection
on Watercolor2k
(using extra training data)
Transformers on Multilingual Clause-Level Morphology
While transformer architectures with data augmentation achieved the most promising results for inflection and reinflection tasks, prefix-tuning on mGPT received the highest results for the analysis task.
Self-Supervised Learning with an Information Maximization Criterion
In this article, we argue that a straightforward application of information maximization among alternative latent representations of the same input naturally solves the collapse problem and achieves competitive empirical results.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Mukayese: Turkish NLP Strikes Back
As a solution, we present Mukayese, a set of NLP benchmarks for the Turkish language that contains several NLP tasks.
Language Controls More Than Top-Down Attention: Modulating Bottom-Up Visual Processing with Referring Expressions
How to best integrate linguistic and perceptual processing in multimodal tasks is an important open problem.
CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions
Humans are able to perceive, understand and reason about causal events.
KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media
In this paper, we describe our approach to utilize pre-trained BERT models with Convolutional Neural Networks for sub-task A of the Multilingual Offensive Language Identification shared task (OffensEval 2020), which is a part of the SemEval 2020.
Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference
End-to-end models trained on natural language inference (NLI) datasets show low generalization on out-of-distribution evaluation sets.
Natural Language Inference
Out-of-Distribution Generalization
+1
Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters
Our experiments reveal that using language to control the filters for bottom-up visual processing in addition to top-down attention leads to better results on both tasks and achieves competitive performance.
KU\_ai at MEDIQA 2019: Domain-specific Pre-training and Transfer Learning for Medical NLI
In this paper, we describe our system and results submitted for the Natural Language Inference (NLI) track of the MEDIQA 2019 Shared Task.
Learning from Implicit Information in Natural Language Instructions for Robotic Manipulations
Therefore, we further propose Bayesian learning to resolve such inconsistencies between the natural language grounding and a robot's world representation by exploiting spatio-relational information that is implicitly present in instructions given by a human.
Tree-Stack LSTM in Transition Based Dependency Parsing
We introduce tree-stack LSTM to model state of a transition based parser with recurrent neural networks.
SParse: Ko\cc University Graph-Based Parsing System for the CoNLL 2018 Shared Task
We present SParse, our Graph-Based Parsing model submitted for the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (Zeman et al., 2018).
A new dataset and model for learning to understand navigational instructions
Our goal is to develop a model that can learn to follow new instructions given prior instruction-perception-action examples.
Morphological analysis using a sequence decoder
Our Morse implementation and the TrMor2018 dataset are available online to support future research\footnote{See \url{https://github. com/ai-ku/Morse. jl} for a Morse implementation in Julia/Knet \cite{knet2016mlsys} and \url{https://github. com/ai-ku/TrMor2018} for the new Turkish dataset.
Parsing with Context Embeddings
We introduce context embeddings, dense vectors derived from a language model that represent the left/right context of a word instance, and demonstrate that context embeddings significantly improve the accuracy of our transition based parser.
CharNER: Character-Level Named Entity Recognition
We describe and evaluate a character-level tagger for language-independent Named Entity Recognition (NER).
Learning grammatical categories using paradigmatic representations: Substitute words for language acquisition
Learning syntactic categories is a fundamental task in language acquisition.
Transfer Learning for Low-Resource Neural Machine Translation
Ensembling and unknown word replacement add another 2 Bleu which brings the NMT performance on low-resource machine translation close to a strong syntax based machine translation (SBMT) system, exceeding its performance on one language pair.
Substitute Based SCODE Word Embeddings in Supervised NLP Tasks
The results show that the proposed method achieves as good as or better results compared to the other word embeddings in the tasks we investigate.
FASTSUBS: An Efficient and Exact Procedure for Finding the Most Likely Lexical Substitutes Based on an N-gram Language Model
Lexical substitutes have found use in areas such as paraphrasing, text simplification, machine translation, word sense disambiguation, and part of speech induction.
