268 citations · 662 across the 69 of their papers we have counts for
11 papers · 1 filter
ConveRT: Efficient and Accurate Conversational Representations from Transformers
Matthew Henderson, Iñigo Casanueva, Nikola Mrkšić +3
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.…
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages
Yi Zhu, Benjamin Heinzerling, Ivan Vulić +3
Recent work has validated the importance of subword information for word representation learning. Since subwords increase parameter sharing ability in neural models, their value sh…
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?
Ivan Vulić, Goran Glavaš, Roi Reichart +1
Recent efforts in cross-lingual word embedding (CLWE) learning have predominantly focused on fully unsupervised approaches that project monolingual embeddings into a shared cross-l…
PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking
Matthew Henderson, Ivan Vulić, Iñigo Casanueva +7
We present PolyResponse, a conversational search engine that supports task-oriented dialogue. It is a retrieval-based approach that bypasses the complex multi-component design of t…
A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces
Anne Lauscher, Goran Glavaš, Simone Paolo Ponzetto +1
Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have conseque…
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity
Anne Lauscher, Ivan Vulić, Edoardo Maria Ponti +2
Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional stat…