Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay Yoon Lee, Lizhen Tan, Lazaros Polymenakos, Andrew McCallum. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

Jonathan K. Kummerfeld, Sai R. Gouravajhala, Joseph J. Peper, Vignesh Athreya, Chulaka Gunasekara, Jatin Ganhotra, Siva Sankalp Patel, Lazaros C Polymenakos, Walter Lasecki. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

Neural end-to-end goal-oriented dialog systems showed promise to reduce the workload of human agents for customer service, as well as reduce wait time for users. However, their inability to handle new user behavior at deployment has limited their usage in real world. In this work, we propose an end-to-end trainable method for neural goal-oriented dialog systems that handles new user behaviors at deployment by transferring the dialog to a human agent intelligently. The proposed method has three goals: 1) maximize user’s task success by transferring to human agents, 2) minimize the load on the human agents by transferring to them only when it is essential, and 3) learn online from the human agent’s responses to reduce human agents’ load further. We evaluate our proposed method on a modified-bAbI dialog task, 1 which simulates the scenario of new user behaviors occurring at test time. Experimental results show that our proposed method is effective in achieving the desired goals.

We propose a unified Implicit Dialog framework for goal-oriented, information seeking tasks of Conversational Commerce applications. It aims to enable the dialog interactions with domain data without replying on the explicitly encoded rules but utilizing the underlying data representation to build the components required for the interactions, which we refer as Implicit Dialog in this work. The proposed framework consists of a pipeline of End-to-End trainable modules. It generates a centralized knowledge representation to semantically ground multiple sub-modules. The framework is also integrated with an associated set of tools to gather end users' input for continuous improvement of the system. This framework is designed to facilitate fast development of conversational systems by identifying the components and the data that can be adapted and reused across many end-user applications. We demonstrate our approach by creating conversational agents for several independent domains.

In this paper, we study the problem of addressee and response selection in multi-party conversations. Understanding multi-party conversations is challenging because of complex speaker interactions: multiple speakers exchange messages with each other, playing different roles (sender, addressee, observer), and these roles vary across turns. To tackle this challenge, we propose the Speaker Interaction Recurrent Neural Network (SI-RNN). Whereas the previous state-of-the-art system updated speaker embeddings only for the sender, SI-RNN uses a novel dialog encoder to update speaker embeddings in a role-sensitive way. Additionally, unlike the previous work that selected the addressee and response separately, SI-RNN selects them jointly by viewing the task as a sequence prediction problem. Experimental results show that SI-RNN significantly improves the accuracy of addressee and response selection, particularly in complex conversations with many speakers and responses to distant messages many turns in the past.

In a dialog, there can be multiple valid next utterances at any point.The present end-toend neural methods for dialog do not take this into account.They learn with the assumption that at any time there is only one correct next utterance.In this work, we focus on this problem in the goal-oriented dialog setting where there are different paths to reach a goal.We propose a new method, that uses a combination of supervised learning and reinforcement learning approaches to address this issue.We also propose a new and more effective testbed, permuted-bAbI dialog tasks 1 by introducing multiple valid next utterances to the original-bAbI dialog tasks, which allows evaluation of goal-oriented dialog systems in a more realistic setting.We show that there is a significant drop in performance of existing end-toend neural methods from 81.5% per-dialog accuracy on original-bAbI dialog tasks to 30.3% on permuted-bAbI dialog tasks.We also show that our proposed method improves the performance and achieves 47.3% per-dialog accuracy on permuted-bAbI dialog tasks.* Equal Contribution 1 permuted-bAbI-dialog-tasks -https://github. com/IBM/permuted-bAbI-dialog-tasks

This paper proposes a system for tracking people in three dimensions, utilizing audiovisual information from multiple acoustic and video sensors. The proposed system comprises a video and an audio subsystem combined using a Kalman filter. The video subsystem combines in 3D a number of 2D trackers based on a variation of Stauffer's adaptive background algorithm with spatio-temporal adaptation of the learning parameters and a Kalman tracker in a feedback configuration. The audio subsystem uses an information theoretic metric upon a pair of microphones to estimate the direction from which sound is arriving from. Combining measurements from a series of pairs the actual coordinate of the speaker in space is derived. Experiments show that gains are to be expected when fusion of the separate tracking systems is performed

This letter proposes a novel stochastic gradient algorithm for the online adaptation of the pole position in Laguerre filters. The proposed algorithm exploits the inherent relationship between the values of the filter coefficients and the value of the Laguerre pole. This leads to an unbiased solution and, hence, a more accurate estimate of the error gradient. Simulations in a system identification setting support the analysis

Estimating the direction of arrival (DOA) of an acoustic source relies on the successful estimation of the relative delay between pairs of microphone signals. Processing is performed at the current time by operating on blocks of recorded data. When these recordings are performed in environments of strong multipath reflections, algorithms often fail to distinguish between the true DOA and that of a dominant reflection. In this letter, we assume Gaussianity of the source signal and use an information-theoretical measure, often met in blind source separation algorithms, to derive a robust DOA estimator, even under significant reverberant conditions. We discuss the most popular algorithm for time delay estimation, namely, the generalized cross-correlation method, and demonstrate under certain conditions its connection to the proposed one. Performance is demonstrated for both algorithms with sets of simulated results as a function of different reverberation times, microphone spacing, and data block size. The results indicate that the examined framework can accurately track the DOA of a typical acoustic source.

Web Services is gradually becoming the most popular distributed computing paradigm for the Internet. Although several vendor and research efforts are in progress, fully-fledged deployment of Web Services in a wide scale has not been accomplished yet. The present contribution describes a framework for lightweight deployment of Web Services. This framework can be seen as a contribution to a smooth transition step towards a complete large-scale deployment. The paper starts with a description of data access techniques supporting multiple data providers, devised and used in the scope of a European research project. It is illustrated how schemes employed to provide remote transparent access to the data providers evolved to a lightweight Web Services framework.

The paper describes an architecture for multi-channel and multi-modal applications. First the design problem is explored and a proposal for a system that can handle multi-modal interaction and delivery of Internet content is proposed. The focus is pertained in some development aspects and the way they are addressed by using state-of-the-art tools. The various components are defined and described in detail. Finally, conclusions and a view of future work on the evolution of such systems is given.

This paper describes extensions and improvements to IBM's large vocabulary continuous speech recognition (LVCSR) system for transcription of broadcast news. The recognizer uses an additional 35 hours of training data over the one used in the 1996 Hub4 evaluation. It includes a number of new features: optimal feature space for acoustic modeling (in training and/or testing), filler-word modeling, Bayesian information criterion (BIC) based segment clustering, an improved implementation of iterative MLLR and 4-gram language models. Results using the 1996 DARPA Hub4 evaluation data set are presented.

This paper describes some of the main problems and issues specific to the transcription of broadcast news and describes some of the methods for solving them that have been incorporated into the IBM Large Vocabulary Continuous Speech Recognition System.

We describe three data-parallel implementations of the simplex method for dense linear programming problems. The first implementation uses a full tableau and the most-negative reduced cost pivot rule, the second uses a tableau and the steepest-edge pivot rule, and the third is a revised method with explicit inverse. All are implemented on a Connection Machine CM-2 massively parallel computer system, using a variant of Fortran 90. Using special data structures called stripe arrays, we produce efficient implementations. We compare the implementations to one another and to MINOS 5.4 on a Sun workstation. Test problems are from NETLIB, supplemented by a few additional, genuinely dense models from real applications. An appendix also gives recent results on the Connection Machine CM-5. INFORMS Journal on Computing, ISSN 1091-9856, was published as ORSA Journal on Computing from 1989 to 1995 under ISSN 0899-1499.