相关论文: Using Shapley interactions to understand how model…

As Transformers have become state-of-the-art models for natural language processing (NLP) tasks, the need to understand and explain their predictions is increasingly apparent. Especially in unsupervised applications, such as information…

Nature language inference (NLI) task is a predictive task of determining the inference relationship of a pair of natural language sentences. With the increasing popularity of NLI, many state-of-the-art predictive models have been proposed…

We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing their conditional distributions. In this space, distances between models approximate the KL…

We present our latest findings on backchannel modeling novelly motivated by the canonical use of the minimal responses Yeah and Uh-huh in English and their correspondent tokens in German, and the effect of encoding the speaker-listener…

Contact between languages has the potential to transmit vocabulary and other language features; however, this does not always happen. Here, an iterated learning model is used to examine, in a simple way, the resistance of languages to…

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

Silent speech interfaces (SSI) has been an exciting area of recent interest. In this paper, we present a non-invasive silent speech interface that uses inaudible acoustic signals to capture people's lip movements when they speak. We exploit…

End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on the other hand, are…

We propose probabilistic Shapley inference (PSI), a novel probabilistic framework to model and infer sufficient statistics of feature attributions in flexible predictive models, via latent random variables whose mean recovers Shapley…

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In…

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

Human interlocutors tend to engage in adaptive behavior known as entrainment to become more similar to each other. Isolating the effect of consistency, i.e., speakers adhering to their individual styles, is a critical part of the analysis…

Natural Language Inference is a challenging task that has received substantial attention, and state-of-the-art models now achieve impressive test set performance in the form of accuracy scores. Here, we go beyond this single evaluation…

Human beings possess the most sophisticated computational machinery in the known universe. We can understand language of rich descriptive power, and communicate in the same environment with astonishing clarity. Two of the many contributors…

Both humans and large language models are able to learn language without explicit structural supervision. What inductive biases make this learning possible? We address this fundamental cognitive question by leveraging transformer language…

In the era of digitalization, as individuals increasingly rely on digital platforms for communication and news consumption, various actors employ linguistic strategies to influence public perception. While models have become proficient at…

Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general. Spatial relations between objects can either be explicit --…

The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based…

Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…

Financial markets are a classical example of complex systems as they comprise many interacting stocks. As such, we can obtain a surprisingly good description of their structure by making the rough simplification of binary daily returns.…