Search Results for author:
Found 40 papers, 12 papers with code
Representing Online Handwriting for Recognition in Large Vision-Language Models
In this paper, we study online handwriting recognition with VLMs, going beyond naive OCR.
InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form, known as digital ink.
DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation
As text generative models can give increasingly long answers, we tackle the problem of synthesizing long text in digital ink.
Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation
On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to produce a precise segmentation.
Sampling and Ranking for Digital Ink Generation on a tight computational budget
We use and compare the effect of multiple sampling and ranking techniques, in the first ablation study of its kind in the digital ink domain.
Inkorrect: Online Handwriting Spelling Correction
We show that Inkorrect's Pareto frontier dominates the points that correspond to prior work.
Recommending Burgers based on Pizza Preferences: Addressing Data Sparsity with a Product of Experts
The intuition is that user-item interactions in a source domain can augment the recommendation quality in a target domain.
OpenCSI: An Open-Source Dataset for Indoor Localization Using CSI-Based Fingerprinting
Many applications require accurate indoor localization.
Modeling Online Behavior in Recommender Systems: The Importance of Temporal Context
Finally, we validate that the Pareto Fronts obtained with the added objective dominate those produced by state-of-the-art models that are only optimized for accuracy on three real-world publicly available datasets.
Momentum-based Gradient Methods in Multi-Objective Recommendation
We evaluate the benefits of Multi-objective Adamize on two multi-objective recommender systems and for three different objective combinations, both correlated or conflicting.
Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm
The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender.
Benefiting from Bicubically Down-Sampled Images for Learning Real-World Image Super-Resolution
First, we train a network to transform real LR images to the space of bicubically downsampled images in a supervised manner, by using both real LR/HR pairs and synthetic pairs.
Interacting with Explanations through Critiquing
Using personalized explanations to support recommendations has been shown to increase trust and perceived quality.
Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation
We introduce CGA, a conditional VAE architecture, to control, generate, and augment text.
A Swiss German Dictionary: Variation in Speech and Writing
To alleviate the uncertainty associated with this diversity, we complement the pairs of Swiss German - High German words with the Swiss German phonetic transcriptions (SAMPA).
Fast Cross-domain Data Augmentation through Neural Sentence Editing
We thus aim to learn this in a source domain where data is abundant and apply it in a different, target domain, where data is scarce - cross-domain augmentation.
Multi-Gradient Descent for Multi-Objective Recommender Systems
Recommender systems need to mirror the complexity of the environment they are applied in.
Ranked #1 on
Recommendation Systems
on MovieLens 20M
(Recall@20 metric)
Automatic Creation of Text Corpora for Low-Resource Languages from the Internet: The Case of Swiss German
This paper presents SwissCrawl, the largest Swiss German text corpus to date.
Multi-Dimensional Explanation of Target Variables from Documents
Past work used attention and rationale mechanisms to find words that predict the target variable of a document.
Multi-Dimensional Explanation of Reviews
Neural models achieved considerable improvement for many natural language processing tasks, but they offer little transparency, and interpretability comes at a cost.
Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes
We denote this a token order imbalance (TOI) and we link the partial sequence information loss to a diminished performance of the system as a whole, both in text and speech processing tasks.
Ranked #30 on
Language Modelling
on WikiText-2
Benefiting from Multitask Learning to Improve Single Image Super-Resolution
Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem.
Resilient Combination of Complementary CNN and RNN Features for Text Classification through Attention and Ensembling
State-of-the-art methods for text classification include several distinct steps of pre-processing, feature extraction and post-processing.
Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
In particular, we test the hypothesis that embeddings with context are more effective, by multi-tasking the learning of multilingual word embeddings and text classification; we explore neural architectures for CLTC; and we move from bi- to multi-lingual word embeddings.
Interpretable Structure-aware Document Encoders with Hierarchical Attention
We show our model's interpretability by visualizing how our model distributes attention inside a document.
Evaluating the Search Phase of Neural Architecture Search
Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks.
Overcoming Multi-Model Forgetting
We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, due to the overwriting of shared parameters.
Embedding Individual Table Columns for Resilient SQL Chatbots
Most of the world's data is stored in relational databases.
Churn Intent Detection in Multilingual Chatbot Conversations and Social Media
To this end, we crowdsource and publish a dataset of churn intent expressions in chatbot interactions in German and English.
DataBright: Towards a Global Exchange for Decentralized Data Ownership and Trusted Computation
We illustrate that trusted computation can enable the creation of an AI market, where each data point has an exact value that should be paid to its creator.
Diverse Beam Search for Increased Novelty in Abstractive Summarization
Text summarization condenses a text to a shorter version while retaining the important informations.
Submodularity-Inspired Data Selection for Goal-Oriented Chatbot Training Based on Sentence Embeddings
Spoken language understanding (SLU) systems, such as goal-oriented chatbots or personal assistants, rely on an initial natural language understanding (NLU) module to determine the intent and to extract the relevant information from the user queries they take as input.
Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning
The success of the dialogue system depends on the quality of the policy, which is in turn reliant on the availability of high-quality training data for the policy learning method, for instance Deep Reinforcement Learning.
GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining
The dramatic success of deep neural networks across multiple application areas often relies on experts painstakingly designing a network architecture specific to each task.
Simple Unsupervised Keyphrase Extraction using Sentence Embeddings
EmbedRank achieves higher F-scores than graph-based state of the art systems on standard datasets and is suitable for real-time processing of large amounts of Web data.
Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German
The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written.
Dataset Construction via Attention for Aspect Term Extraction with Distant Supervision
Publicly available review corpora contain a plethora of opinionated aspect terms and cover a larger domain spectrum.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets
Our second contribution is a method to automatically construct datasets for ATE.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Unsupervised Aspect Term Extraction with B-LSTM \& CRF using Automatically Labelled Datasets
Our second contribution is a method to automatically construct datasets for ATE.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
