Yi Su


2022

pdf bib
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
Charlie Snell | Sherry Yang | Justin Fu | Yi Su | Sergey Levine
Findings of the Association for Computational Linguistics: NAACL 2022

Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task relabeling, to derive a simple and effective method to finetune language models in a goal-aware way, leading to significantly improved task performance. We additionally introduce a number of training strategies that serve to better focus the model on the task at hand. We evaluate our method, Context-Aware Language Models (CALM), on a practical flight-booking task using AirDialogue. Empirically, CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance.

2021

pdf bib
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling
Xiang Hu | Haitao Mi | Zujie Wen | Yafang Wang | Yi Su | Jing Zheng | Gerard de Melo
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Human language understanding operates at multiple levels of granularity (e.g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined. However, existing deep models with stacked layers do not explicitly model any sort of hierarchical process. In this paper, we propose a recursive Transformer model based on differentiable CKY style binary trees to emulate this composition process, and we extend the bidirectional language model pre-training objective to this architecture, attempting to predict each word given its left and right abstraction nodes. To scale up our approach, we also introduce an efficient pruning and growing algorithm to reduce the time complexity and enable encoding in linear time. Experimental results on language modeling and unsupervised parsing show the effectiveness of our approach.

2009

pdf bib
Model Adaptation via Model Interpolation and Boosting for Web Search Ranking
Jianfeng Gao | Qiang Wu | Chris Burges | Krysta Svore | Yi Su | Nazan Khan | Shalin Shah | Hongyan Zhou
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing