Search Results for author:
Found 68 papers, 20 papers with code
GCDF1: A Goal- and Context- Driven F-Score for Evaluating User Models
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.
Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices
In this paper, we build a benchmark with annotations for both evidence selection and answer generation covering 6 information sources.
Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It
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.
Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation
Building neural machine translation systems to perform well on a specific target domain is a well-studied problem.
uFACT: Unfaithful Alien-Corpora Training for Semantically Consistent Data-to-Text Generation
Our approach is to augment the training set of a given target corpus with alien corpora which have different semantic representations.
The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities
In particular, we observe a decline in the ability to perform formality steering, to produce technical translations through few-shot examples, and to perform document-level translation.
A Preference-driven Paradigm for Enhanced Translation with Large Language Models
Recent research has shown that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) using only a small amount of parallel data.
Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata
The Directed Acyclic Transformer is a fast non-autoregressive (NAR) model that performs well in Neural Machine Translation.
Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches
Two approaches have emerged to input images into large language models (LLMs).
Parameter Efficient Reinforcement Learning from Human Feedback
In this work, we empirically evaluate the setup of Parameter Efficient Reinforcement Learning from Human Feedback (PE-RLHF) that leverages LoRA fine-tuning for Reward Modeling, and Reinforcement Learning.
PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers
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)
Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding
Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs).
Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning
Hateful memes have emerged as a significant concern on the Internet.
Ranked #2 on
Meme Classification
on Hateful Memes
Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques
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.
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
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.
Ranked #1 on
Retrieval
on OK-VQA
Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata.
xPQA: Cross-Lingual Product Question Answering across 12 Languages
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.
FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering
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.
Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation
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.
Retrieval Augmented Visual Question Answering with Outside Knowledge
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.
Ranked #2 on
Retrieval
on OK-VQA
Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey
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.
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation
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.
From Rewriting to Remembering: Common Ground for Conversational QA Models
In conversational QA, models have to leverage information in previous turns to answer upcoming questions.
Transformer-Empowered Content-Aware Collaborative Filtering
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.
Transferable Dialogue Systems and User Simulators
Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents.
First the worst: Finding better gender translations during beam search
Neural machine translation inference procedures like beam search generate the most likely output under the model.
Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances.
Ranked #1 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems
In terms of data, we introduce TicketTalk, a movie ticketing dialog dataset with 23, 789 annotated conversations.
The Teacher-Student Chatroom Corpus
The Teacher-Student Chatroom Corpus (TSCC) is a collection of written conversations captured during one-to-one lessons between teachers and learners of English.
Inference-only sub-character decomposition improves translation of unseen logographic characters
One possible approach to this problem uses sub-character decomposition for training and test sentences.
Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It
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.
Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task
The 2020 WMT Biomedical translation task evaluated Medline abstract translations.
Using Context in Neural Machine Translation Training Objectives
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.
Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem
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.
Semi-supervised Bootstrapping of Dialogue State Trackers for Task Oriented Modelling
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
Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels.
Coached Conversational Preference Elicitation: A Case Study in Understanding Movie Preferences
Studying the dialogues in one domain, we present a brief quantitative analysis of how people describe movie preferences at scale.
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data.
On NMT Search Errors and Model Errors: Cat Got Your Tongue?
We report on search errors and model errors in neural machine translation (NMT).
CUED@WMT19:EWC\&LMs
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).
Neural and FST-based approaches to grammatical error correction
In this paper, we describe our submission to the BEA 2019 shared task on grammatical error correction.
The CUED's Grammatical Error Correction Systems for BEA-2019
We describe two entries from the Cambridge University Engineering Department to the BEA 2019 Shared Task on grammatical error correction.
UCAM Biomedical translation at WMT19: Transfer learning multi-domain ensembles
The 2019 WMT Biomedical translation task involved translating Medline abstracts.
Cued@wmt19:ewc&lms
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).
Domain Adaptive Inference for Neural Machine Translation
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.
Neural Grammatical Error Correction with Finite State Transducers
Language model based GEC (LM-GEC) is a promising alternative which does not rely on annotated training data.
An Operation Sequence Model for Explainable Neural Machine Translation
We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself.
The University of Cambridge's Machine Translation Systems for WMT18
The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation.
Neural Machine Translation Decoding with Terminology Constraints
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.
Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT
We explore strategies for incorporating target syntax into Neural Machine Translation.
Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
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.
Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation
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.
Break it Down for Me: A Study in Automated Lyric Annotation
Comprehending lyrics, as found in songs and poems, can pose a challenge to human and machine readers alike.
A Comparison of Neural Models for Word Ordering
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.
SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
This paper introduces SGNMT, our experimental platform for machine translation research.
Unfolding and Shrinking Neural Machine Translation Ensembles
Ensembling is a well-known technique in neural machine translation (NMT) to improve system performance.
Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices
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.
The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
This paper presents the University of Cambridge submission to WMT16.
Syntactically Guided Neural Machine Translation
We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT).
Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization
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.
