To assess the performance of Mobile-Agent, we introduced Mobile-Eval, a benchmark for evaluating mobile device operations.
Each component is implemented by a single LLM that focuses on a specific capability and collaborates with others to accomplish the task.
The results demonstrate that when combined with meta knowledge, the response generator can effectively leverage high-quality knowledge records from the retriever and enhance the quality of generated responses.
1 code implementation • 2 Sep 2023 • Chenliang Li, Hehong Chen, Ming Yan, Weizhou Shen, Haiyang Xu, Zhikai Wu, Zhicheng Zhang, Wenmeng Zhou, Yingda Chen, Chen Cheng, Hongzhu Shi, Ji Zhang, Fei Huang, Jingren Zhou
Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior.
Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses.
To model the dependencies between utterances in multi-party conversations, we propose a simple and generic framework based on the dependency parsing results of utterances.
Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates.
In this paper, we put forward a novel idea of encoding the utterances with a directed acyclic graph (DAG) to better model the intrinsic structure within a conversation, and design a directed acyclic neural network, namely DAG-ERC, to implement this idea.
Ranked #10 on Emotion Recognition in Conversation on EmoryNLP
Specifically, we first modify the recurrence mechanism of XLNet from segment-level to utterance-level in order to better model the conversational data.
Ranked #2 on Emotion Recognition in Conversation on CPED
One of the remaining challenges for aspect term extraction in sentiment analysis resides in the extraction of phrase-level aspect terms, which is non-trivial to determine the boundaries of such terms.
Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.