Matthew Lee

Anna Kawakami, Luke Guerdan, Yanghuidi Cheng et al. · cmu

A growing body of research has explored how to support humans in making better use of AI-based decision support, including via training and onboarding. Existing research has focused on decision-making tasks where it is possible to evaluate "appropriate reliance" by comparing each decision against a ground truth label that cleanly maps to both the AI's predictive target and the human decision-maker's goals. However, this assumption does not hold in many real-world settings where AI tools are deployed today (e.g., social work, criminal justice, and healthcare). In this paper, we introduce a process-oriented notion of appropriate reliance called critical use that centers the human's ability to situate AI predictions against knowledge that is uniquely available to them but unavailable to the AI model. To explore how training can support critical use, we conduct a randomized online experiment in a complex social decision-making setting: child maltreatment screening. We find that, by providing participants with accelerated, low-stakes opportunities to practice AI-assisted decision-making in this setting, novices came to exhibit patterns of disagreement with AI that resemble those of experienced workers. A qualitative examination of participants' explanations for their AI-assisted decisions revealed that they drew upon qualitative case narratives, to which the AI model did not have access, to learn when (not) to rely on AI predictions. Our findings open new questions for the study and design of training for real-world AI-assisted decision-making.

K R Prajwal, Bowen Shi, Matthew Lee et al. · oxford

We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the conditional distribution of semantic and acoustic features. Additionally, we leverage masked prediction as the training objective, enabling the model to generalize to other tasks such as music infilling and continuation in a zero-shot manner. Experiments on MusicCaps reveal that the music generated by MusicFlow exhibits superior quality and text coherence despite being over $2\sim5$ times smaller and requiring $5$ times fewer iterative steps. Simultaneously, the model can perform other music generation tasks and achieves competitive performance in music infilling and continuation. Our code and model will be publicly available.

Talip Ucar, Adrian Gonzalez-Martin, Matthew Lee et al.

Humans can infer a great deal about the meaning of a word, using the syntax and semantics of surrounding words even if it is their first time reading or hearing it. We can also generalise the learned concept of the word to new tasks. Despite great progress in achieving human-level performance in certain tasks (Silver et al., 2016), learning from one or few examples remains a key challenge in machine learning, and has not thoroughly been explored in Natural Language Processing (NLP). In this work we tackle the problem of oneshot learning for an NLP task by employing ideas from recent developments in machine learning: embeddings, attention mechanisms (softmax) and similarity measures (cosine, Euclidean, Poincare, and Minkowski). We adapt the framework suggested in matching networks (Vinyals et al., 2016), and explore the effectiveness of the aforementioned methods in one, two and three-shot learning problems on the task of predicting missing word explored in (Vinyals et al., 2016) by using the WikiText-2 dataset. Our work contributes in two ways: Our first contribution is that we explore the effectiveness of different distance metrics on k-shot learning, and show that there is no single best distance metric for k-shot learning, which challenges common belief. We found that the performance of a distance metric depends on the number of shots used during training. The second contribution of our work is that we establish a benchmark for one, two, and three-shot learning on a language task with a publicly available dataset that can be used to benchmark against in future research.

Matthew Lee

Flow-like experiences at work are important for productivity and worker well-being. However, it is difficult to objectively detect when workers are experiencing flow in their work. In this paper, we investigate how to predict a worker's focus state based on physiological signals. We conducted a lab study to collect physiological data from knowledge workers experienced different levels of flow while performing work tasks. We used the nine characteristics of flow to design tasks that would induce different focus states. A manipulation check using the Flow Short Scale verified that participants experienced three distinct flow states, one overly challenging non-flow state, and two types of flow states, balanced flow, and automatic flow. We built machine learning classifiers that can distinguish between non-flow and flow states with 0.889 average AUC and rest states from working states with 0.98 average AUC. The results show that physiological sensing can detect focused flow states of knowledge workers and can enable ways to for individuals and organizations to improve both productivity and worker satisfaction.

Graham Neubig, Shruti Rijhwani, Alexis Palmer et al.

Despite recent advances in natural language processing and other language technology, the application of such technology to language documentation and conservation has been limited. In August 2019, a workshop was held at Carnegie Mellon University in Pittsburgh to attempt to bring together language community members, documentary linguists, and technologists to discuss how to bridge this gap and create prototypes of novel and practical language revitalization technologies. This paper reports the results of this workshop, including issues discussed, and various conceived and implemented technologies for nine languages: Arapaho, Cayuga, Inuktitut, Irish Gaelic, Kidaw'ida, Kwak'wala, Ojibwe, San Juan Quiahije Chatino, and Seneca.

Xinjian Li, Siddharth Dalmia, Juncheng Li et al.

Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can support lexical contrasts in a particular language) and their corresponding phones (the sounds that are actually spoken, which are language independent). This can lead to performance degradation when combining a variety of training languages, as identically annotated phonemes can actually correspond to several different underlying phonetic realizations. In this work, we propose a joint model of both language-independent phone and language-dependent phoneme distributions. In multilingual ASR experiments over 11 languages, we find that this model improves testing performance by 2% phoneme error rate absolute in low-resource conditions. Additionally, because we are explicitly modeling language-independent phones, we can build a (nearly-)universal phone recognizer that, when combined with the PHOIBLE large, manually curated database of phone inventories, can be customized into 2,000 language dependent recognizers. Experiments on two low-resourced indigenous languages, Inuktitut and Tusom, show that our recognizer achieves phone accuracy improvements of more than 17%, moving a step closer to speech recognition for all languages in the world.