Song Feng

Afroza Shirin, Isaac Klickstein, Song Feng et al.

The effects of molecularly targeted drug perturbations on cellular activities and fates are difficult to predict using intuition alone because of the complex behaviors of cellular regulatory networks. An approach to overcoming this problem is to develop mathematical models for predicting drug effects. Such an approach beckons for co-development of computational methods for extracting insights useful for guiding therapy selection and optimizing drug scheduling. Here, we present and evaluate a generalizable strategy for identifying drug dosing schedules that minimize the amount of drug needed to achieve sustained suppression or elevation of an important cellular activity/process, the recycling of cytoplasmic contents through (macro)autophagy. Therapeutic targeting of autophagy is currently being evaluated in diverse clinical trials but without the benefit of a control engineering perspective. Using a nonlinear ordinary differential equation (ODE) model that accounts for activating and inhibiting influences among protein and lipid kinases that regulate autophagy (MTORC1, ULK1, AMPK and VPS34) and methods guaranteed to find locally optimal control strategies, we find optimal drug dosing schedules (open-loop controllers) for each of six classes of drugs and drug pairs. Our approach is generalizable to designing monotherapy and multi therapy drug schedules that affect different cell signaling networks of interest.

Han He, Song Feng, Daniele Bonadiman et al.

DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks. Despite the availability of a large dataset SMCalFlow and a simplified syntax, the development and evaluation of DataFlow-based chatbots remain challenging due to the system complexity and the lack of downstream toolchains. In this demonstration, we present DFEE, an interactive DataFlow Execution and Evaluation toolkit that supports execution, visualization and benchmarking of semantic parsers given dialogue input and backend database. We demonstrate the system via a complex dialog task: event scheduling that involves temporal reasoning. It also supports diagnosing the parsing results via a friendly interface that allows developers to examine dynamic DataFlow and the corresponding execution results. To illustrate how to benchmark SoTA models, we propose a novel benchmark that covers more sophisticated event scheduling scenarios and a new metric on task success evaluation. The codes of DFEE have been released on https://github.com/amazonscience/dataflow-evaluation-toolkit.

Wanyu Du, Song Feng, James Gung et al.

Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on increasing diversity in language, topics, or dialogue acts at the utterance level, largely neglecting a critical aspect of task logic diversity at the dialogue level. This paper proposes a novel data simulation method designed to enhance the diversity of synthetic dialogues by focusing on task execution logic. Our method uses LLMs to generate decision tree-structured task plans, which enables the derivation of diverse dialogue trajectories for a given task. Each trajectory, referred to as a "dialog flow", guides the generation of a multi-turn dialogue that follows a unique trajectory. We apply this method to generate a task-oriented dialogue dataset comprising 3,886 dialogue flows across 15 different domains. We validate the effectiveness of this dataset using the next action prediction task, where models fine-tuned on our dataset outperform strong baselines, including GPT-4. Upon acceptance of this paper, we plan to release the code and data publicly.

Qingyang Wu, Song Feng, Derek Chen et al.

Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the unstructured documents to answer the users' questions. As a result, existing document-grounded dialog datasets are relatively small-scale and obstruct the effective training of dialogue systems. In this paper, we propose an automatic data augmentation technique grounded on documents through a generative dialogue model. The dialogue model consists of a user bot and agent bot that can synthesize diverse dialogues given an input document, which are then used to train a downstream model. When supplementing the original dataset, our method achieves significant improvement over traditional data augmentation methods. We also achieve great performance in the low-resource setting.