Search Results for author:
Found 48 papers, 17 papers with code
RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining
Large-scale pretrained language models have achieved SOTA results on NLP tasks.
MovieChats: Chat like Humans in a Closed Domain
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
semiPQA: A Study on Product Question Answering over Semi-structured Data
To fill in this blank, here we study how to effectively incorporate semi-structured answer sources for PQA and focus on presenting answers in a natural, fluent sentence.
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.
Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?
Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality.
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.
Unraveling the Mystery of Scaling Laws: Part I
However, the original scaling law paper by OpenAI did not disclose the complete details necessary to derive the precise scaling law formulas, and their conclusions are only based on models containing up to 1. 5 billion parameters.
The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis
Compared to work on monolingual (English) in-context learning, multilingual in-context learning is under-explored, and we lack an in-depth understanding of the role of demonstrations in this context.
StableMask: Refining Causal Masking in Decoder-only Transformer
The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling.
A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks
We hope that our findings can provide a deeper understanding of PEFT methods on various PTMs and SE downstream tasks.
Fast calculation of Counterparty Credit exposures and associated sensitivities using fourier series expansion
This paper introduces a novel approach for computing netting--set level and counterparty level exposures, such as Potential Future Exposure (PFE) and Expected Exposure (EE), along with associated sensitivities.
LawBench: Benchmarking Legal Knowledge of Large Language Models
We hope this benchmark provides in-depth understanding of the LLMs' domain-specified capabilities and speed up the development of LLMs in the legal domain.
SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects
Despite the progress we have recorded in the last few years in multilingual natural language processing, evaluation is typically limited to a small set of languages with available datasets which excludes a large number of low-resource languages.
Weaker Than You Think: A Critical Look at Weakly Supervised Learning
In this paper, we revisit the setup of these approaches and find that the benefits brought by these approaches are significantly overestimated.
Is Translation Helpful? An Empirical Analysis of Cross-Lingual Transfer in Low-Resource Dialog Generation
Cross-lingual transfer is important for developing high-quality chatbots in multiple languages due to the strongly imbalanced distribution of language resources.
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.
WeLM: A Well-Read Pre-trained Language Model for Chinese
Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks.
MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages
In this paper, we present mDIA, the first large-scale multilingual benchmark for dialogue generation across low- to high-resource languages.
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.
Meta Self-Refinement for Robust Learning with Weak Supervision
Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost.
A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation
We focus on two questions: 1) How can pre-trained models be used for languages not included in the initial pre-training?
A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges
In this paper, to address the current lack of comprehensive survey of existing LJP tasks, datasets, models and evaluations, (1) we analyze 31 LJP datasets in 6 languages, present their construction process and define a classification method of LJP with 3 different attributes; (2) we summarize 14 evaluation metrics under four categories for different outputs of LJP tasks; (3) we review 12 legal-domain pretrained models in 3 languages and highlight 3 major research directions for LJP; (4) we show the state-of-art results for 8 representative datasets from different court cases and discuss the open challenges.
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.
Deep Latent-Variable Models for Text Generation
Text generation aims to produce human-like natural language output for down-stream tasks.
Logical Fallacy Detection
In this paper, we propose the task of logical fallacy detection, and provide a new dataset (Logic) of logical fallacies generally found in text, together with an additional challenge set for detecting logical fallacies in climate change claims (LogicClimate).
Knowledge-enhanced Session-based Recommendation with Temporal Transformer
We introduce time interval embedding to represent the time pattern between the item that needs to be predicted and historical click, and use it to replace the position embedding in the original transformer (called temporal transformer).
Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer
Given the fact of a case, Legal Judgment Prediction (LJP) involves a series of sub-tasks such as predicting violated law articles, charges and term of penalty.
AST-Transformer: Encoding Abstract Syntax Trees Efficiently for Code Summarization
Code summarization aims to generate brief natural language descriptions for source code.
Preventing Author Profiling through Zero-Shot Multilingual Back-Translation
Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e. g. their gender or ethnicity.
The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation
We propose a shared task on training instance selection for few-shot neural text generation.
On Training Instance Selection for Few-Shot Neural Text Generation
In this work, we present a study on training instance selection in few-shot neural text generation.
Learning Fine-grained Fact-Article Correspondence in Legal Cases
We believe that learning fine-grained correspondence between each single fact and law articles is crucial for an accurate and trustworthy AI system.
Neural Data-to-Text Generation with LM-based Text Augmentation
Our approach automatically augments the data available for training by (i) generating new text samples based on replacing specific values by alternative ones from the same category, (ii) generating new text samples based on GPT-2, and (iii) proposing an automatic method for pairing the new text samples with data samples.
Data Augmentation for Multiclass Utterance Classification -- A Systematic Study
Utterance classification is a key component in many conversational systems.
Cross-Domain Learning for Classifying Propaganda in Online Contents
Prior work has focused on supervised learning with training data from the same domain.
DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool
We present a lightweight annotation tool, the Data AnnotatoR Tool (DART), for the general task of labeling structured data with textual descriptions.
Integrating Image Captioning with Rule-based Entity Masking
Particularly, these image features are subdivided into global and local features, where global features are extracted from the global representation of the image, while local features are extracted from the objects detected locally in an image.
Diversifying Dialogue Generation with Non-Conversational Text
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation.
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
The neural attention model has achieved great success in data-to-text generation tasks.
Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training
In this work, we develop techniques targeted at bridging the gap between Pidgin English and English in the context of natural language generation.
Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator
Pointer Generators have been the de facto standard for modern summarization systems.
Select and Attend: Towards Controllable Content Selection in Text Generation
As a result, the content to be described in the text cannot be explicitly controlled.
Unsupervised Rewriter for Multi-Sentence Compression
First, the word graph approach that simply concatenates fragments from multiple sentences may yield non-fluent or ungrammatical compression.
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network.
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems.
Improving Variational Encoder-Decoders in Dialogue Generation
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation.
DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects.
A Conditional Variational Framework for Dialog Generation
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.
