Search Results for author:
Found 24 papers, 10 papers with code
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Despite their unprecedented success, even the largest language models make mistakes.
Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations
This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models.
DUnE: Dataset for Unified Editing
In this study, we broaden the scope of the editing problem to include an array of editing cases such as debiasing and rectifying reasoning errors and define an edit as any natural language expression that solicits a change in the model's outputs.
On Measuring Social Biases in Prompt-Based Multi-Task Learning
Large language models trained on a mixture of NLP tasks that are converted into a text-to-text format using prompts, can generalize into novel forms of language and handle novel tasks.
AugCSE: Contrastive Sentence Embedding with Diverse Augmentations
Data augmentation techniques have been proven useful in many applications in NLP fields.
OpenFraming: We brought the ML; you bring the data. Interact with your data and discover its frames
The degree of user involvement is flexible: they can run models that have been pre-trained on select issues; submit labeled documents and train a new model for frame classification; or submit unlabeled documents and obtain potential frames of the documents.
Challenges in Measuring Bias via Open-Ended Language Generation
Researchers have devised numerous ways to quantify social biases vested in pretrained language models.
Deriving Verb Predicates By Clustering Verbs with Arguments
Hand-built verb clusters such as the widely used Levin classes (Levin, 1993) have proved useful, but have limited coverage.
Learning to mirror speaking styles incrementally
Our method extracts ngrams that capture a persons speaking styles and uses the ngrams to create patterns for transforming sentences to the persons speaking styles.
Learning to Scale Multilingual Representations for Vision-Language Tasks
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added.
Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world's languages and the researchers working on these languages.
Sentiment-based Candidate Selection for NMT
Using n-best candidates generated by a baseline MT model with beam search and we select the candidate that minimizes the absolute difference between the sentiment score of the source sentence and that of the translation and and perform two human evaluations to assess the produced translations.
Informativity in Image Captions vs. Referring Expressions
We hope that an understanding of the systematic differences among these human datasets will ultimately allow them to be leveraged more effectively in the associated engineering tasks.
Explore the Potential Performance of Vision-and-Language Navigation Model: a Snapshot Ensemble Method
Vision-and-Language Navigation (VLN) is a challenging task in the field of artificial intelligence.
Better Quality Estimation for Low Resource Corpus Mining
We show that State-of-the-art QE models, when tested in a Parallel Corpus Mining (PCM) setting, perform unexpectedly bad due to a lack of robustness to out-of-domain examples.
Creating Multimedia Summaries Using Tweets and Videos
While popular televised events such as presidential debates or TV shows are airing, people provide commentary on them in real-time.
Referring Expressions with Rational Speech Act Framework: A Probabilistic Approach
This paper focuses on a referring expression generation (REG) task in which the aim is to pick out an object in a complex visual scene.
Knowledge Based Template Machine Translation In Low-Resource Setting
Incorporating tagging into neural machine translation (NMT) systems has shown promising results in helping translate rare words such as named entities (NE).
Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia
Neural machine translation (NMT) for low-resource local languages in Indonesia faces significant challenges, including the need for a representative benchmark and limited data availability.
COVID-19 Vaccine Misinformation in Middle Income Countries
This paper introduces a multilingual dataset of COVID-19 vaccine misinformation, consisting of annotated tweets from three middle-income countries: Brazil, Indonesia, and Nigeria.
Relevance-guided Neural Machine Translation
With the advent of the Transformer architecture, Neural Machine Translation (NMT) results have shown great improvement lately.
An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contribution
Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised methods and analyzing its output in aspects other than translation accuracy.
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
Given a collection of seed documents, DCT prompts LMs to generate additional text implied by these documents, reason globally about the correctness of this generated text, and finally fine-tune on text inferred to be correct.
Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?
Large Language Models (LLMs) demonstrate strong machine translation capabilities on languages they are trained on.
