Product Question Answering (PQA) systems are key in e-commerce applicati...
The widely used Fact-based Visual Question Answering (FVQA) dataset cont...
Ensuring that generated utterances are faithful to dialogue actions is
c...
Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQ...
Dense retrieval (DR) approaches based on powerful pre-trained language m...
Vocabulary selection, or lexical shortlisting, is a well-known technique...
In conversational QA, models have to leverage information in previous tu...
Knowledge graph (KG) based Collaborative Filtering is an effective appro...
One of the difficulties in training dialogue systems is the lack of trai...
Neural machine translation inference procedures like beam search generat...
Dialogue State Tracking is a crucial part of multi-domain task-oriented
...
We present a data-driven, end-to-end approach to transaction-based dialo...
The Teacher-Student Chatroom Corpus (TSCC) is a collection of written
co...
Neural Machine Translation (NMT) on logographic source languages struggl...
The 2020 WMT Biomedical translation task evaluated Medline abstract
tran...
Neural Machine Translation (NMT) has been shown to struggle with grammat...
We present Neural Machine Translation (NMT) training using document-leve...
Training data for NLP tasks often exhibits gender bias in that fewer
sen...
Dialogue systems benefit greatly from optimizing on detailed annotations...
A significant barrier to progress in data-driven approaches to building
...
We report on search errors and model errors in neural machine translatio...
We describe two entries from the Cambridge University Engineering Depart...
The 2019 WMT Biomedical translation task involved translating Medline
ab...
Two techniques provide the fabric of the Cambridge University Engineerin...
We investigate adaptive ensemble weighting for Neural Machine Translatio...
Grammatical error correction (GEC) is one of the areas in natural langua...
We propose to achieve explainable neural machine translation (NMT) by
ch...
The University of Cambridge submission to the WMT18 news translation tas...
Despite the impressive quality improvements yielded by neural machine
tr...
We explore strategies for incorporating target syntax into Neural Machin...
We describe a batched beam decoding algorithm for NMT with LMBR n-gram
p...
SGNMT is a decoding platform for machine translation which allows paring...
Comprehending lyrics, as found in songs and poems, can pose a challenge ...
We compare several language models for the word-ordering task and propos...
This paper introduces SGNMT, our experimental platform for machine
trans...
Ensembling is a well-known technique in neural machine translation (NMT)...
We present a novel scheme to combine neural machine translation (NMT) wi...
This paper presents the University of Cambridge submission to WMT16.
Mot...
We investigate the use of hierarchical phrase-based SMT lattices in
end-...
We address the problem of automatically finding the parameters of a
stat...