Search Results for author:
Found 19 papers, 3 papers with code
Controlling Machine Translation for Multiple Attributes with Additive Interventions
Fine-grained control of machine translation (MT) outputs along multiple attributes is critical for many modern MT applications and is a requirement for gaining users’ trust.
Dissecting Recall of Factual Associations in Auto-Regressive Language Models
Given a subject-relation query, we study how the model aggregates information about the subject and relation to predict the correct attribute.
Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets
Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP.
Understanding Text Classification Data and Models Using Aggregated Input Salience
Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers.
Diagnosing AI Explanation Methods with Folk Concepts of Behavior
We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with.
Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data
Neural text generation (data- or text-to-text) demonstrates remarkable performance when training data is abundant which for many applications is not the case.
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?
There is a recent surge of interest in using attention as explanation of model predictions, with mixed evidence on whether attention can be used as such.
We Need to Talk About Random Splits
We argue that random splits, like standard splits, lead to overly optimistic performance estimates.
Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!
Motivated by recent findings on the probabilistic modeling of acceptability judgments, we propose syntactic log-odds ratio (SLOR), a normalized language model score, as a metric for referenceless fluency evaluation of natural language generation output at the sentence level.
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.
Fast k-best Sentence Compression
A popular approach to sentence compression is to formulate the task as a constrained optimization problem and solve it with integer linear programming (ILP) tools.
