Tur, Gokhan
Language Model is All You Need: Natural Language Understanding as Question Answering
Namazifar, Mahdi, Papangelis, Alexandros, Tur, Gokhan, Hakkani-Tür, Dilek
Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a specific family of transfer learning, where the target domain is mapped to the source domain. Specifically we map Natural Language Understanding (NLU) problems to QuestionAnswering (QA) problems and we show that in low data regimes this approach offers significant improvements compared to other approaches to NLU. Moreover we show that these gains could be increased through sequential transfer learning across NLU problems from different domains. We show that our approach could reduce the amount of required data for the same performance by up to a factor of 10.
Warped Language Models for Noise Robust Language Understanding
Namazifar, Mahdi, Tur, Gokhan, Tür, Dilek Hakkani
Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken language understanding, especially for spontaneous conversational speech recognition noise. In this work we introduce Warped Language Models (WLM) in which input sentences at training time go through the same modifications as in MLM, plus two additional modifications, namely inserting and dropping random tokens. These two modifications extend and contract the sentence in addition to the modifications in MLMs, hence the word "warped" in the name. The insertion and drop modification of the input text during training of WLM resemble the types of noise due to Automatic Speech Recognition (ASR) errors, and as a result WLMs are likely to be more robust to ASR noise. Through computational results we show that natural language understanding systems built on top of WLMs perform better compared to those built based on MLMs, especially in the presence of ASR errors.
Flexibly-Structured Model for Task-Oriented Dialogues
Shu, Lei, Molino, Piero, Namazifar, Mahdi, Xu, Hu, Liu, Bing, Zheng, Huaixiu, Tur, Gokhan
This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot. The policy engine and language generation tasks are modeled jointly following that. The copy-augmented sequential decoder deals with new or unknown values in the conversation, while the multi-label decoder combined with the sequential decoder ensures the explicit assignment of values to slots. On the generation part, slot binary classifiers are used to improve performance. This architecture is scalable to real-world scenarios and is shown through an empirical evaluation to achieve state-of-the-art performance on both the Cambridge Restaurant dataset and the Stanford in-car assistant dataset\footnote{The code is available at \url{https://github.com/uber-research/FSDM}}
OCC: A Smart Reply System for Efficient In-App Communications
Weng, Yue, Zheng, Huaixiu, Bell, Franziska, Tur, Gokhan
Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber's smart reply system: one-click-chat (OCC), which is a key enhanced feature on top of the Uber in-app chat system. It enables driver-partners to quickly respond to rider messages using smart replies. The smart replies are dynamically selected according to conversation content using machine learning algorithms. Our system consists of two major components: intent detection and reply retrieval, which are very different from standard smart reply systems where the task is to directly predict a reply. It is designed specifically for mobile applications with short and non-canonical messages. Reply retrieval utilizes pairings between intent and reply based on their popularity in chat messages as derived from historical data. For intent detection, a set of embedding and classification techniques are experimented with, and we choose to deploy a solution using unsupervised distributed embedding and nearest-neighbor classifier. It has the advantage of only requiring a small amount of labeled training data, simplicity in developing and deploying to production, and fast inference during serving and hence highly scalable. At the same time, it performs comparably with deep learning architectures such as word-level convolutional neural network. Overall, the system achieves a high accuracy of 76% on intent detection. Currently, the system is deployed in production for English-speaking countries and 71% of in-app communications between riders and driver-partners adopted the smart replies to speedup the communication process.
User Modeling for Task Oriented Dialogues
Gur, Izzeddin, Hakkani-Tur, Dilek, Tur, Gokhan, Shah, Pararth
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspectives: (i) automatic evaluation of different dialogue models, and (ii) training task-oriented dialogue systems. We design a hierarchical sequence-to-sequence model that first encodes the initial user goal and system turns into fixed length representations using Recurrent Neural Networks (RNN). It then encodes the dialogue history using another RNN layer. At each turn, user responses are decoded from the hidden representations of the dialogue level RNN. This hierarchical user simulator (HUS) approach allows the model to capture undiscovered parts of the user goal without the need of an explicit dialogue state tracking. We further develop several variants by utilizing a latent variable model to inject random variations into user responses to promote diversity in simulated user responses and a novel goal regularization mechanism to penalize divergence of user responses from the initial user goal. We evaluate the proposed models on movie ticket booking domain by systematically interacting each user simulator with various dialogue system policies trained with different objectives and users.
The Workshops at the Twentieth National Conference on Artificial Intelligence
Aliod, Diego Molla, Alonso, Eduardo, Bangalore, Srinivas, Beck, Joseph, Bhanu, Bir, Blythe, Jim, Boddy, Mark, Cesta, Amedeo, Grobelink, Marko, Hakkani-Tur, Dilek, Harabagiu, Sanda, Lege, Alain, McGuinness, Deborah L., Marsella, Stacy, Milic-Frayling, Natasha, Mladenic, Dunja, Oblinger, Dan, Rybski, Paul, Shvaiko, Pavel, Smith, Stephen, Srivastava, Biplav, Tejada, Sheila, Vilhjalmsson, Hannes, Thorisson, Kristinn, Tur, Gokhan, Vicedo, Jose Luis, Wache, Holger
The AAAI-05 workshops were held on Saturday and Sunday, July 9-10, in Pittsburgh, Pennsylvania. The thirteen workshops were Contexts and Ontologies: Theory, Practice and Applications, Educational Data Mining, Exploring Planning and Scheduling for Web Services, Grid and Autonomic Computing, Human Comprehensible Machine Learning, Inference for Textual Question Answering, Integrating Planning into Scheduling, Learning in Computer Vision, Link Analysis, Mobile Robot Workshop, Modular Construction of Humanlike Intelligence, Multiagent Learning, Question Answering in Restricted Domains, and Spoken Language Understanding.
The Workshops at the Twentieth National Conference on Artificial Intelligence
Aliod, Diego Molla, Alonso, Eduardo, Bangalore, Srinivas, Beck, Joseph, Bhanu, Bir, Blythe, Jim, Boddy, Mark, Cesta, Amedeo, Grobelink, Marko, Hakkani-Tur, Dilek, Harabagiu, Sanda, Lege, Alain, McGuinness, Deborah L., Marsella, Stacy, Milic-Frayling, Natasha, Mladenic, Dunja, Oblinger, Dan, Rybski, Paul, Shvaiko, Pavel, Smith, Stephen, Srivastava, Biplav, Tejada, Sheila, Vilhjalmsson, Hannes, Thorisson, Kristinn, Tur, Gokhan, Vicedo, Jose Luis, Wache, Holger
The AAAI-05 workshops were held on Saturday and Sunday, July 9-10, in Pittsburgh, Pennsylvania. The thirteen workshops were Contexts and Ontologies: Theory, Practice and Applications, Educational Data Mining, Exploring Planning and Scheduling for Web Services, Grid and Autonomic Computing, Human Comprehensible Machine Learning, Inference for Textual Question Answering, Integrating Planning into Scheduling, Learning in Computer Vision, Link Analysis, Mobile Robot Workshop, Modular Construction of Humanlike Intelligence, Multiagent Learning, Question Answering in Restricted Domains, and Spoken Language Understanding.