Search Results for author:
Found 33 papers, 12 papers with code
Teaching Small Language Models to Reason
Chain of thought prompting successfully improves the reasoning capabilities of large language models, achieving state of the art results on a range of datasets.
Text Generation with Text-Editing Models
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer.
EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start
This is achieved by decomposing the generation process into three sub-tasks: (1) tagging to decide on the subset of input tokens to be preserved in the output, (2) re-ordering to define their order in the output text, and (3) insertion to infill the missing tokens that are not present in the input.
Controlled Text Generation as Continuous Optimization with Multiple Constraints
As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate.
A Simple Recipe for Multilingual Grammatical Error Correction
This paper presents a simple recipe to train state-of-the-art multilingual Grammatical Error Correction (GEC) models.
Ranked #1 on
Grammatical Error Correction
on Falko-MERLIN
(using extra training data)
Unsupervised Text Style Transfer with Padded Masked Language Models
This allows us to identify the source tokens to delete to transform the source text to match the style of the target domain.
Felix: Flexible Text Editing Through Tagging and Insertion
We achieve this by decomposing the text-editing task into two sub-tasks: tagging to decide on the subset of input tokens and their order in the output text and insertion to in-fill the missing tokens in the output not present in the input.
Encode, Tag, Realize: High-Precision Text Editing
We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task.
Ranked #1 on
Sentence Fusion
on DiscoFuse
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks
Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing.
Ranked #1 on
Split and Rephrase
on WikiSplit
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities
The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks.
Adversarial Neural Networks for Cross-lingual Sequence Tagging
We study cross-lingual sequence tagging with little or no labeled data in the target language.
On Accurate Evaluation of GANs for Language Generation
Generative Adversarial Networks (GANs) are a promising approach to language generation.
Prosody Modifications for Question-Answering in Voice-Only Settings
Many popular form factors of digital assistants---such as Amazon Echo, Apple Homepod, or Google Home---enable the user to hold a conversation with these systems based only on the speech modality.
Eval all, trust a few, do wrong to none: Comparing sentence generation models
In this paper, we study recent neural generative models for text generation related to variational autoencoders.
Learning to Learn from Weak Supervision by Full Supervision
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels.
Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision
Thus we avoid that the weight updates computed from noisy labels harm the quality of the target network model.
Neural Ranking Models with Weak Supervision
Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections.
Ranked #8 on
Ad-Hoc Information Retrieval
on TREC Robust04
(MAP metric)
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification
This paper presents a novel approach for multi-lingual sentiment classification in short texts.
A Hybrid Convolutional Variational Autoencoder for Text Generation
In this paper we explore the effect of architectural choices on learning a Variational Autoencoder (VAE) for text generation.
Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks
In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences.
Globally Normalized Transition-Based Neural Networks
Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models.
Ranked #17 on
Dependency Parsing
on Penn Treebank
Recurrent Dropout without Memory Loss
This paper presents a novel approach to recurrent neural network (RNN) regularization.
SenTube: A Corpus for Sentiment Analysis on YouTube Social Media
In this paper we present SenTube -- a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity.
