Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge.
We present a systematic study on multilingual and cross-lingual intent detection from spoken data.
General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train.
Ranked #1 on Conversational Response Selection on PolyAI AmazonQA
We present PolyResponse, a conversational search engine that supports task-oriented dialogue.
Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks.
Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches.
Our adversarial post-specialization method propagates the external lexical knowledge to the full distributional space.
Word vector specialisation (also known as retrofitting) is a portable, light-weight approach to fine-tuning arbitrary distributional word vector spaces by injecting external knowledge from rich lexical resources such as WordNet.
Dialogue assistants are rapidly becoming an indispensable daily aid.
We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation.
Existing approaches to automatic VerbNet-style verb classification are heavily dependent on feature engineering and therefore limited to languages with mature NLP pipelines.
Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e. g., the dialogue success and the dialogue length.
In doing that, we show that our approach has the potential to facilitate policy optimisation for more sophisticated multi-domain dialogue systems.
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.
Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that have similar distributional signatures.
This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System.
One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user's goal at every step of the dialogue.
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity.
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind.