Lazaros Polymenakos


2020

pdf bib
Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations
Praveen Kumar Bodigutla | Aditya Tiwari | Spyros Matsoukas | Josep Valls-Vargas | Lazaros Polymenakos
Findings of the Association for Computational Linguistics: EMNLP 2020

Dialogue level quality estimation is vital for optimizing data driven dialogue management. Current automated methods to estimate turn and dialogue level user satisfaction employ hand-crafted features and rely on complex annotation schemes, which reduce the generalizability of the trained models. We propose a novel user satisfaction estimation approach which minimizes an adaptive multi-task loss function in order to jointly predict turn-level Response Quality labels provided by experts and explicit dialogue-level ratings provided by end users. The proposed BiLSTM based deep neural net model automatically weighs each turn’s contribution towards the estimated dialogue-level rating, implicitly encodes temporal dependencies, and removes the need to hand-craft features. On dialogues sampled from 28 Alexa domains, two dialogue systems and three user groups, the joint dialogue-level satisfaction estimation model achieved up to an absolute 27% (0.43 -> 0.70) and 7% (0.63 -> 0.70) improvement in linear correlation performance over baseline deep neural net and benchmark Gradient boosting regression models, respectively.

pdf bib
Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors
Longshaokan Wang | Maryam Fazel-Zarandi | Aditya Tiwari | Spyros Matsoukas | Lazaros Polymenakos
Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users’ audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for natural language understanding and response generation. The ASR output is error-prone; however, the downstream dialog models are often trained on error-free text data, making them sensitive to ASR errors during inference time. To bridge the gap and make dialog models more robust to ASR errors, we leverage an ASR error simulator to inject noise into the error-free text data, and subsequently train the dialog models with the augmented data. Compared to other approaches for handling ASR errors, such as using ASR lattice or end-to-end methods, our data augmentation approach does not require any modification to the ASR or downstream dialog models; our approach also does not introduce any additional latency during inference time. We perform extensive experiments on benchmark data and show that our approach improves the performance of downstream dialog models in the presence of ASR errors, and it is particularly effective in the low-resource situations where there are constraints on model size or the training data is scarce.

2019

pdf bib
DSTC7 Task 1: Noetic End-to-End Response Selection
Chulaka Gunasekara | Jonathan K. Kummerfeld | Lazaros Polymenakos | Walter Lasecki
Proceedings of the First Workshop on NLP for Conversational AI

Goal-oriented dialogue in complex domains is an extremely challenging problem and there are relatively few datasets. This task provided two new resources that presented different challenges: one was focused but small, while the other was large but diverse. We also considered several new variations on the next utterance selection problem: (1) increasing the number of candidates, (2) including paraphrases, and (3) not including a correct option in the candidate set. Twenty teams participated, developing a range of neural network models, including some that successfully incorporated external data to boost performance. Both datasets have been publicly released, enabling future work to build on these results, working towards robust goal-oriented dialogue systems.

pdf bib
NE-Table: A Neural key-value table for Named Entities
Janarthanan Rajendran | Jatin Ganhotra | Xiaoxiao Guo | Mo Yu | Satinder Singh | Lazaros Polymenakos
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)

Many Natural Language Processing (NLP) tasks depend on using Named Entities (NEs) that are contained in texts and in external knowledge sources. While this is easy for humans, the present neural methods that rely on learned word embeddings may not perform well for these NLP tasks, especially in the presence of Out-Of-Vocabulary (OOV) or rare NEs. In this paper, we propose a solution for this problem, and present empirical evaluations on: a) a structured Question-Answering task, b) three related Goal-Oriented dialog tasks, and c) a Reading-Comprehension task, which show that the proposed method can be effective in dealing with both in-vocabulary and OOV NEs. We create extended versions of dialog bAbI tasks 1,2 and 4 and OOV versions of the CBT test set which are available at - https://github.com/IBM/ne-table-datasets/

2018

pdf bib
Learning End-to-End Goal-Oriented Dialog with Multiple Answers
Janarthanan Rajendran | Jatin Ganhotra | Satinder Singh | Lazaros Polymenakos
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In a dialog, there could be multiple valid next utterances at any point. The present end-to-end 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, by introducing multiple valid next utterances to the original-bAbI dialog tasks, which allows evaluation of end-to-end goal-oriented dialog systems in a more realistic setting. We show that there is a significant drop in performance of existing end-to-end 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. We also release permuted-bAbI dialog tasks, our proposed testbed, to the community for evaluating dialog systems in a goal-oriented setting.