1 code implementation • 15 Mar 2023 • Rahul Goel, Waleed Ammar, Aditya Gupta, Siddharth Vashishtha, Motoki Sano, Faiz Surani, Max Chang, HyunJeong Choe, David Greene, Kyle He, Rattima Nitisaroj, Anna Trukhina, Shachi Paul, Pararth Shah, Rushin Shah, Zhou Yu
Research interest in task-oriented dialogs has increased as systems such as Google Assistant, Alexa and Siri have become ubiquitous in everyday life.
Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands.
As the top-level intent largely governs the syntax and semantics of a parse, the intent conditioning allows the model to better control beam search and improves the quality and diversity of top-k outputs.
In this paper, we explore how to use a small amount of new data to update a task-oriented semantic parsing model when the desired output for some examples has changed.
To reduce training time, one can fine-tune the previously trained model on each patch, but naive fine-tuning exhibits catastrophic forgetting - degradation of the model performance on the data not represented in the data patch.
However, evaluating a model's robustness to these changes is harder for language since words are discrete and an automated change (e. g. adding `noise') to a query sometimes changes the meaning and thus labels of a query.
We propose a semantic parser for parsing compositional utterances into Task Oriented Parse (TOP), a tree representation that has intents and slots as labels of nesting tree nodes.
Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results [Gupta et al 2018].
We introduce PyText - a deep learning based NLP modeling framework built on PyTorch.
We use this data set to evaluate three different cross-lingual transfer methods: (1) translating the training data, (2) using cross-lingual pre-trained embeddings, and (3) a novel method of using a multilingual machine translation encoder as contextual word representations.
Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots.