相关论文: Translating between Horn Representations and their…

Alternation of forward and backward analyses is a standard technique in abstract interpretation of programs, which is in particular useful when we wish to prove unreachability of some undesired program states. The current state-of-the-art…

Representing graphs by their homomorphism counts has led to the beautiful theory of homomorphism indistinguishability in recent years. Moreover, homomorphism counts have promising applications in database theory and machine learning, where…

Even though Transformers are extensively used for Natural Language Processing tasks, especially for machine translation, they lack an explicit memory to store key concepts of processed texts. This paper explores the properties of the…

Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet…

Machine transliteration is a method for automatically converting words in one language into phonetically equivalent ones in another language. Machine transliteration plays an important role in natural language applications such as…

Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a…

Machine learning is permeating every conceivable domain to promote data-driven decision support. The focus is often on advanced black-box models due to their assumed performance advantages, whereas interpretable models are often associated…

Evaluating translation models is a trade-off between effort and detail. On the one end of the spectrum there are automatic count-based methods such as BLEU, on the other end linguistic evaluations by humans, which arguably are more…

Hypergraph representations are both more efficient and better suited to describe data characterized by relations between two or more objects. In this work, we present a new graph neural network based on message passing capable of processing…

Machine translation (MT) plays an important role in benefiting linguists, sociologists, computer scientists, etc. by processing natural language to translate it into some other natural language. And this demand has grown exponentially over…

Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network…

Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation. Recent work suggests that the…

Training fair machine learning models, aiming for their interpretability and solving the problem of domain shift has gained a lot of interest in the last years. There is a vast amount of work addressing these topics, mostly in separation.…

With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…

In this paper we present a novel tool to evaluate problem solving systems. Instead of using a system to solve a problem, we suggest using the problem to evaluate the system. By finding a numerical representation of a problem's complexity,…

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a principled notion of interpretability to formally compare…

Algorithmic case-based decision support provides examples to help human make sense of predicted labels and aid human in decision-making tasks. Despite the promising performance of supervised learning, representations learned by supervised…

Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model…

Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges,…