Contextual Slot Carryover for Disparate Schemas
- Chetan Naik, Arpit Gupta, Hancheng Ge, Lambert Mathias, R. Sarikaya
- Computer ScienceInterspeech
- 5 June 2018
A neural network architecture is presented that addresses the slot value scalability challenge by reformulating the contextual interpretation as a decision to carryover a slot from a set of possible candidates and a simple data-driven method for trans- forming the candidate slots.
Improving Long Distance Slot Carryover in Spoken Dialogue Systems
- Tongfei Chen, Chetan Naik, Hua He, Pushpendre Rastogi, Lambert Mathias
- Computer ScienceProceedings of the First Workshop on NLP for…
- 4 June 2019
This paper proposes two neural network architectures, one based on pointer networks that incorporate slot ordering information, and the other based on transformer networks that uses self attention mechanism to model the slot interdependencies.
Cross Sentence Inference for Process Knowledge
- Samuel Louvan, Chetan Naik, Sadhana Kumaravel, Heeyoung Kwon, Niranjan Balasubramanian, Peter Clark
- Computer ScienceConference on Empirical Methods in Natural…
- 1 November 2016
This work extends standard within sentence joint inference to inference across multiple sentences, which promotes role assignments that are compatible across different descriptions of the same process.
Semantic Role Labeling for Process Recognition Questions
- Samuel Louvan, Chetan Naik, Veronica E. Lynn, A. Arun, Niranjan Balasubramanian, Peter Clark
- Computer Science
- 2015
Empirical evaluation shows that manually generated roles provide a 12% relative improvement in accuracy over a simpler bag-of-words representation, but automatic role identification is noisy and doesn’t provide gains even with distant supervision and domain adaptation modifications to account for the limited training data.
Cross-Lingual Approaches to Reference Resolution in Dialogue Systems
- Amr Sharaf, Arpit Gupta, Hancheng Ge, Chetan Naik, Lambert Mathias
- Computer ScienceArXiv
- 27 November 2018
The context carryover system is built on, which provides a scalable multi-domain framework for resolving references and shows that multilingual embeddings and delexicalization via data augmentation have a significant impact in the low resource setting, but the gains diminish as the amount of available data in the target language increases.