Search Results for author:
Found 28 papers, 12 papers with code
Hierarchical Recurrent Aggregative Generation for Few-Shot NLG
Large pretrained models enable transfer learning to low-resource domains for language generation tasks.
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level
We introduce Agent K v1. 0, an end-to-end autonomous data science agent designed to automate, optimise, and generalise across diverse data science tasks.
Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency
Code Language Models have been trained to generate accurate solutions, typically with no regard for runtime.
HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants
To help accelerate the development of LMs as conversational assistants, we propose a novel automatic evaluation task: HumanRankEval (HRE).
MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation
To build MuLAn, we developed a training free pipeline which decomposes a monocular RGB image into a stack of RGBA layers comprising of background and isolated instances.
Findings of the First Workshop on Simulating Conversational Intelligence in Chat
SCI-CHAT follows previous workshops on open domain dialogue but in contrast the focus of the shared task is simulation of intelligent conversation as judged in a live human evaluation.
Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
The advent of large pre-trained language models in the domain of Code Synthesis has shown remarkable performance on various benchmarks, treating the problem of Code Generation in a fashion similar to Natural Language Generation, trained with a Language Modelling (LM) objective.
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP.
Correct and Optimal: the Regular Expression Inference Challenge
We propose regular expression inference (REI) as a challenge for code/language modelling, and the wider machine learning community.
Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, culturally adapted, and large-scale ToD datasets for multiple languages.
Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access
To alleviate the problem of structured databases' limited coverage, recent task-oriented dialogue systems incorporate external unstructured knowledge to guide the generation of system responses.
Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU
Curriculum Learning (CL) is a technique of training models via ranking examples in a typically increasing difficulty trend with the aim of accelerating convergence and improving generalisability.
Natural Language Understanding
Zero-Shot Cross-Lingual Transfer
EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching
We use Wikidata and English Wikipedia to construct an entity-centric CS corpus by switching entities to their counterparts in other languages.
Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Study
Multihop Question Answering is a complex Natural Language Processing task that requires multiple steps of reasoning to find the correct answer to a given question.
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.
XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking
Dialogue State Tracking (DST), a crucial component of task-oriented dialogue (ToD) systems, keeps track of all important information pertaining to dialogue history: filling slots with the most probable values throughout the conversation.
CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language.
Natural Language Understanding
Zero-Shot Cross-Lingual Transfer
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning
For small Natural Language Inference (NLI) datasets, language modelling is typically followed by pretraining on a large (labelled) NLI dataset before fine-tuning with each NLI subtask.
XeroAlign: Zero-Shot Cross-lingual Transformer Alignment
The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks.
Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation
Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability.
Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management
We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-deterministic agents.
Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA
The results show differences in ability to represent compositional and lexical information between RoBERTa, BERT and DistilBERT.
Show Us the Way: Learning to Manage Dialog from Demonstrations
We present our submission to the End-to-End Multi-Domain Dialog Challenge Track of the Eighth Dialog System Technology Challenge.
LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories
While word embeddings are now a de facto standard representation of words in most NLP tasks, recently the attention has been shifting towards vector representations which capture the different meanings, i. e., senses, of words.
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora.
Semantic Representations of Word Senses and Concepts
Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days.
