Search Results for author: Bill Byrne

Found 65 papers, 17 papers with code

The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation

1 code implementation NAACL 2022 Tobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne, Felix Hieber

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 during inference.

Machine Translation Sentence +1

Retrieval Augmented Visual Question Answering with Outside Knowledge

1 code implementation7 Oct 2022 Weizhe Lin, Bill Byrne

The strong retrieval ability of our model significantly reduces the number of retrieved documents needed in training, yielding significant benefits in answer quality and computation required for training.

Answer Generation Passage Retrieval +3

Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering

1 code implementation NeurIPS 2023 Weizhe Lin, Jinghong Chen, Jingbiao Mei, Alexandru Coca, Bill Byrne

FLMR addresses two major limitations in RA-VQA's retriever: (1) the image representations obtained via image-to-text transforms can be incomplete and inaccurate and (2) relevance scores between queries and documents are computed with one-dimensional embeddings, which can be insensitive to finer-grained relevance.

Passage Retrieval Question Answering +2

PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers

1 code implementation13 Feb 2024 Weizhe Lin, Jingbiao Mei, Jinghong Chen, Bill Byrne

Large Multimodal Models (LMMs) excel in natural language and visual understanding but are challenged by exacting tasks such as Knowledge-based Visual Question Answering (KB-VQA) which involve the retrieval of relevant information from document collections to use in shaping answers to questions.

 Ranked #1 on Retrieval on InfoSeek (using extra training data)

Question Answering Retrieval +1

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

1 code implementation EMNLP 2021 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.

Dialogue State Tracking Graph Attention +2

Transferable Dialogue Systems and User Simulators

1 code implementation ACL 2021 Bo-Hsiang Tseng, Yinpei Dai, Florian Kreyssig, Bill Byrne

Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents.

Domain Adaptation Transfer Learning

Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset

1 code implementation IJCNLP 2019 Bill Byrne, Karthik Krishnamoorthi, Chinnadhurai Sankar, Arvind Neelakantan, Daniel Duckworth, Semih Yavuz, Ben Goodrich, Amit Dubey, Andy Cedilnik, Kyu-Young Kim

A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data.

Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem

2 code implementations ACL 2020 Danielle Saunders, Bill Byrne

During inference we propose a lattice-rescoring scheme which outperforms all systems evaluated in Stanovsky et al (2019) on WinoMT with no degradation of general test set BLEU, and we show this scheme can be applied to remove gender bias in the output of `black box` online commercial MT systems.

Domain Adaptation Machine Translation +3

xPQA: Cross-Lingual Product Question Answering across 12 Languages

1 code implementation16 May 2023 Xiaoyu Shen, Akari Asai, Bill Byrne, Adrià De Gispert

To study this practical industrial task, we present xPQA, a large-scale annotated cross-lingual PQA dataset in 12 languages across 9 branches, and report results in (1) candidate ranking, to select the best English candidate containing the information to answer a non-English question; and (2) answer generation, to generate a natural-sounding non-English answer based on the selected English candidate.

Answer Generation Machine Translation +3

A Comparison of Neural Models for Word Ordering

1 code implementation WS 2017 Eva Hasler, Felix Stahlberg, Marcus Tomalin, Adri`a de Gispert, Bill Byrne

We compare several language models for the word-ordering task and propose a new bag-to-sequence neural model based on attention-based sequence-to-sequence models.

Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It

1 code implementation11 Oct 2020 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.

Machine Translation NMT +2

Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It

1 code implementation GeBNLP (COLING) 2020 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.

Machine Translation NMT +2

An Operation Sequence Model for Explainable Neural Machine Translation

1 code implementation WS 2018 Felix Stahlberg, Danielle Saunders, Bill Byrne

We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself.

Machine Translation NMT +3

GCDF1: A Goal- and Context- Driven F-Score for Evaluating User Models

1 code implementation EANCS 2021 Alexandru Coca, Bo-Hsiang Tseng, Bill Byrne

The evaluation of dialogue systems in interaction with simulated users has been proposed to improve turn-level, corpus-based metrics which can only evaluate test cases encountered in a corpus and cannot measure system’s ability to sustain multi-turn interactions.

Dialogue Evaluation Task-Oriented Dialogue Systems

Neural Machine Translation Decoding with Terminology Constraints

no code implementations NAACL 2018 Eva Hasler, Adrià De Gispert, Gonzalo Iglesias, Bill Byrne

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem.

Machine Translation NMT +1

Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment

no code implementations NAACL 2018 Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, Bill Byrne

We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers.

NMT

Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation

no code implementations WS 2018 Felix Stahlberg, Danielle Saunders, Gonzalo Iglesias, Bill Byrne

SGNMT is a decoding platform for machine translation which allows paring various modern neural models of translation with different kinds of constraints and symbolic models.

Machine Translation Translation

Unfolding and Shrinking Neural Machine Translation Ensembles

no code implementations EMNLP 2017 Felix Stahlberg, Bill Byrne

Ensembling is a well-known technique in neural machine translation (NMT) to improve system performance.

Machine Translation NMT +1

Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices

no code implementations EACL 2017 Felix Stahlberg, Adrià De Gispert, Eva Hasler, Bill Byrne

This makes our approach much more flexible than $n$-best list or lattice rescoring as the neural decoder is not restricted to the SMT search space.

Machine Translation NMT +1

Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization

no code implementations NAACL 2016 Daniel Beck, Adrià De Gispert, Gonzalo Iglesias, Aurelien Waite, Bill Byrne

We address the problem of automatically finding the parameters of a statistical machine translation system that maximize BLEU scores while ensuring that decoding speed exceeds a minimum value.

Bayesian Optimization Machine Translation +1

The University of Cambridge's Machine Translation Systems for WMT18

no code implementations WS 2018 Felix Stahlberg, Adria de Gispert, Bill Byrne

The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation.

Machine Translation Translation

Domain Adaptive Inference for Neural Machine Translation

no code implementations ACL 2019 Danielle Saunders, Felix Stahlberg, Adria de Gispert, Bill Byrne

We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sacrificing performance on the original domain.

Machine Translation NMT +1

Cued@wmt19:ewc&lms

no code implementations11 Jun 2019 Felix Stahlberg, Danielle Saunders, Adria de Gispert, Bill Byrne

Two techniques provide the fabric of the Cambridge University Engineering Department's (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs).

Language Modelling Sentence

The CUED's Grammatical Error Correction Systems for BEA-2019

no code implementations WS 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.

Grammatical Error Correction Machine Translation +1

CUED@WMT19:EWC\&LMs

no code implementations WS 2019 Felix Stahlberg, Danielle Saunders, Adri{\`a} de Gispert, Bill Byrne

Two techniques provide the fabric of the Cambridge University Engineering Department{'}s (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs).

Language Modelling Sentence

Coached Conversational Preference Elicitation: A Case Study in Understanding Movie Preferences

no code implementations WS 2019 Filip Radlinski, Krisztian Balog, Bill Byrne, Karthik Krishnamoorthi

Studying the dialogues in one domain, we present a brief quantitative analysis of how people describe movie preferences at scale.

Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling

no code implementations IJCNLP 2019 Bo-Hsiang Tseng, Marek Rei, Pawe{\l} Budzianowski, Richard Turner, Bill Byrne, Anna Korhonen

Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels.

Semi-supervised Bootstrapping of Dialogue State Trackers for Task Oriented Modelling

no code implementations26 Nov 2019 Bo-Hsiang Tseng, Marek Rei, Paweł Budzianowski, Richard E. Turner, Bill Byrne, Anna Korhonen

Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels.

Using Context in Neural Machine Translation Training Objectives

no code implementations ACL 2020 Danielle Saunders, Felix Stahlberg, Bill Byrne

We find that each of these lines of research has a clear space in it for the other, and propose merging them with a scheme that allows a document-level evaluation metric to be used in the NMT training objective.

Grammatical Error Correction Machine Translation +3

The Teacher-Student Chatroom Corpus

no code implementations NLP4CALL (COLING) 2020 Andrew Caines, Helen Yannakoudakis, Helena Edmondson, Helen Allen, Pascual Pérez-Paredes, Bill Byrne, Paula Buttery

The Teacher-Student Chatroom Corpus (TSCC) is a collection of written conversations captured during one-to-one lessons between teachers and learners of English.

Descriptive

Transformer-Empowered Content-Aware Collaborative Filtering

no code implementations2 Apr 2022 Weizhe Lin, Linjun Shou, Ming Gong, Pei Jian, Zhilin Wang, Bill Byrne, Daxin Jiang

Knowledge graph (KG) based Collaborative Filtering is an effective approach to personalizing recommendation systems for relatively static domains such as movies and books, by leveraging structured information from KG to enrich both item and user representations.

Collaborative Filtering Contrastive Learning +1

uFACT: Unfaithful Alien-Corpora Training for Semantically Consistent Data-to-Text Generation

no code implementations Findings (ACL) 2022 Tisha Anders, Alexandru Coca, Bill Byrne

Our approach is to augment the training set of a given target corpus with alien corpora which have different semantic representations.

Data-to-Text Generation

Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey

no code implementations5 Aug 2022 Xiaoyu Shen, Svitlana Vakulenko, Marco del Tredici, Gianni Barlacchi, Bill Byrne, Adrià De Gispert

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-answering systems.

Open-Domain Question Answering Retrieval

Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation

1 code implementation29 Jan 2023 Jinghong Chen, Weizhe Lin, Bill Byrne

We show that SGSAcc can be applied to evaluate utterances generated from a wide range of dialogue actions in the Schema Guided Dialogue (SGD) dataset with good agreement with human judgment.

Natural Language Inference Response Generation

FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering

no code implementations19 Mar 2023 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 answer.

Common Sense Reasoning Information Retrieval +4

Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns

no code implementations23 Sep 2023 Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin, Weixuan Zhang, Tisha Anders, Bill Byrne

Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata.

Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques

no code implementations12 Oct 2023 Junxiao Shen, John J. Dudley, Jingyao Zheng, Bill Byrne, Per Ola Kristensson

However, the task of prompting large language models to specialize in specific text prediction tasks can be challenging, particularly for designers without expertise in prompt engineering.

In-Context Learning Language Modelling +2

Improving hateful memes detection via learning hatefulness-aware embedding space through retrieval-guided contrastive learning

no code implementations14 Nov 2023 Jingbiao Mei, Jinghong Chen, Weizhe Lin, Bill Byrne, Marcus Tomalin

Finally, we demonstrate a retrieval-based hateful memes detection system, which is capable of making hatefulness classification based on data unseen in training from a database.

Contrastive Learning Meme Classification +1

Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding

no code implementations14 Nov 2023 Guangyu Yang, Jinghong Chen, Weizhe Lin, Bill Byrne

Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs).

Machine Translation NMT +3

Cannot find the paper you are looking for? You can Submit a new open access paper.