75 citations · 214 across the 27 of their papers we have counts for
41 papers
xPQA: Cross-Lingual Product Question Answering across 12 Languages
Xiaoyu Shen, Akari Asai, Bill Byrne +1
Product Question Answering (PQA) systems are key in e-commerce applications to provide responses to customers' questions as they shop for products. While existing work on PQA focus…
FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering
Weizhe Lin, Zhilin Wang, Bill Byrne
The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to a…
More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking
A. Coca, B. H. Tseng, W. Lin +1
The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context al…
Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation
Jinghong Chen, Weizhe Lin, Bill Byrne
Ensuring that generated utterances are faithful to dialogue actions is crucial for Task-Oriented Dialogue Response Generation. Slot Error Rate (SER) only partially measures generat…
Retrieval Augmented Visual Question Answering with Outside Knowledge
Weizhe Lin, Bill Byrne
Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems…
Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey
Xiaoyu Shen, Svitlana Vakulenko, Marco del Tredici +3
Dense retrieval (DR) approaches based on powerful pre-trained language models (PLMs) achieved significant advances and have become a key component for modern open-domain question-a…
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation
Tobias Domhan, Eva Hasler, Ke Tran +3
Vocabulary selection, or lexical shortlisting, is a well-known technique to improve latency of Neural Machine Translation models by constraining the set of allowed output words dur…
From Rewriting to Remembering: Common Ground for Conversational QA Models
Marco Del Tredici, Xiaoyu Shen, Gianni Barlacchi +2
In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract releva…
Transformer-Empowered Content-Aware Collaborative Filtering
Weizhe Lin, Linjun Shou, Ming Gong +4
Knowledge graph (KG) based Collaborative Filtering is an effective approach to personalizing recommendation systems for relatively static domains such as movies and books, by lever…
Transferable Dialogue Systems and User Simulators
Bo-Hsiang Tseng, Yinpei Dai, Florian Kreyssig +1
One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue s…
First the worst: Finding better gender translations during beam search
Danielle Saunders, Rosie Sallis, Bill Byrne
Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model.…
Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking
Weizhe Lin, Bo-Hsiang Tseng, Bill Byrne
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architectu…
TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems
Bill Byrne, Karthik Krishnamoorthi, Saravanan Ganesh +1
We present a data-driven, end-to-end approach to transaction-based dialog systems that performs at near-human levels in terms of verbal response quality and factual grounding accur…
The Teacher-Student Chatroom Corpus
Andrew Caines, Helen Yannakoudakis, Helena Edmondson +4
The Teacher-Student Chatroom Corpus (TSCC) is a collection of written conversations captured during one-to-one lessons between teachers and learners of English. The lessons took pl…
Inference-only sub-character decomposition improves translation of unseen logographic characters
Danielle Saunders, Weston Feely, Bill Byrne
Neural Machine Translation (NMT) on logographic source languages struggles when translating `unseen' characters, which never appear in the training data. One possible approach to t…
Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task
Danielle Saunders, Bill Byrne
The 2020 WMT Biomedical translation task evaluated Medline abstract translations. This is a small-domain translation task, meaning limited relevant training data with very distinct…
Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It
Danielle Saunders, Rosie Sallis, Bill Byrne
Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many ex…
Using Context in Neural Machine Translation Training Objectives
Danielle Saunders, Felix Stahlberg, Bill Byrne
We present Neural Machine Translation (NMT) training using document-level metrics with batch-level documents. Previous sequence-objective approaches to NMT training focus exclusive…
Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem
Danielle Saunders, Bill Byrne
Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to reduce…
Semi-supervised Bootstrapping of Dialogue State Trackers for Task Oriented Modelling
Bo-Hsiang Tseng, Marek Rei, Paweł Budzianowski +3
Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels. However,…
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
Bill Byrne, Karthik Krishnamoorthi, Chinnadhurai Sankar +7
A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data. To help satisfy this elementa…
On NMT Search Errors and Model Errors: Cat Got Your Tongue?
Felix Stahlberg, Bill Byrne
We report on search errors and model errors in neural machine translation (NMT). We present an exact inference procedure for neural sequence models based on a combination of beam s…
The CUED's Grammatical Error Correction Systems for BEA-2019
Felix Stahlberg, Bill Byrne
We describe two entries from the Cambridge University Engineering Department to the BEA 2019 Shared Task on grammatical error correction. Our submission to the low-resource track i…
UCAM Biomedical translation at WMT19: Transfer learning multi-domain ensembles
Danielle Saunders, Felix Stahlberg, Bill Byrne
The 2019 WMT Biomedical translation task involved translating Medline abstracts. We approached this using transfer learning to obtain a series of strong neural models on distinct d…