Search Results for author: Xiaoyu Shen

Found 45 papers, 17 papers with code

MovieChats: Chat like Humans in a Closed Domain

no code implementations EMNLP 2020 Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie zhou

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.

Chatbot Retrieval

semiPQA: A Study on Product Question Answering over Semi-structured Data

no code implementations ECNLP (ACL) 2022 Xiaoyu Shen, Gianni Barlacchi, Marco del Tredici, Weiwei Cheng, Adrià Gispert

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.

Attribute Question Answering +1

The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis

no code implementations20 Feb 2024 Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba O. Alabi, Xiaoyu Shen, Dietrich Klakow, Marius Mosbach

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.

In-Context Learning

StableMask: Refining Causal Masking in Decoder-only Transformer

no code implementations7 Feb 2024 Qingyu Yin, Xuzheng He, Xiang Zhuang, Yu Zhao, Jianhua Yao, Xiaoyu Shen, Qiang Zhang

The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling.

Language Modelling Position

A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks

1 code implementation25 Dec 2023 Wentao Zou, Qi Li, Jidong Ge, Chuanyi Li, Xiaoyu Shen, LiGuo Huang, Bin Luo

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

no code implementations21 Nov 2023 Gijs Mast, Xiaoyu Shen, Fang Fang

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

1 code implementation28 Sep 2023 Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Songyang Zhang, Kai Chen, Zongwen Shen, Jidong Ge

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.

Benchmarking Memorization +1

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

2 code implementations14 Sep 2023 David Ifeoluwa Adelani, Hannah Liu, Xiaoyu Shen, Nikita Vassilyev, Jesujoba O. Alabi, Yanke Mao, Haonan Gao, Annie En-Shiun Lee

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.

Cross-Lingual Transfer Language Modelling +5

Weaker Than You Think: A Critical Look at Weakly Supervised Learning

1 code implementation27 May 2023 Dawei Zhu, Xiaoyu Shen, Marius Mosbach, Andreas Stephan, Dietrich Klakow

In this paper, we revisit the setup of these approaches and find that the benefits brought by these approaches are significantly overestimated.

Weakly-supervised Learning

Is Translation Helpful? An Empirical Analysis of Cross-Lingual Transfer in Low-Resource Dialog Generation

no code implementations21 May 2023 Lei Shen, Shuai Yu, Xiaoyu Shen

Cross-lingual transfer is important for developing high-quality chatbots in multiple languages due to the strongly imbalanced distribution of language resources.

Cross-Lingual Transfer Machine Translation +1

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

WeLM: A Well-Read Pre-trained Language Model for Chinese

no code implementations21 Sep 2022 Hui Su, Xiao Zhou, Houjin Yu, Xiaoyu Shen, YuWen Chen, Zilin Zhu, Yang Yu, Jie zhou

Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks.

Language Modelling Self-Supervised Learning +2

MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages

1 code implementation27 Aug 2022 Qingyu Zhang, Xiaoyu Shen, Ernie Chang, Jidong Ge, Pengke Chen

In this paper, we present mDIA, the first large-scale multilingual benchmark for dialogue generation across low- to high-resource languages.

Dialogue 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

Meta Self-Refinement for Robust Learning with Weak Supervision

1 code implementation15 May 2022 Dawei Zhu, Xiaoyu Shen, Michael A. Hedderich, Dietrich Klakow

Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost.

A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges

no code implementations11 Apr 2022 Junyun Cui, Xiaoyu Shen, Feiping Nie, Zheng Wang, Jinglong Wang, Yulong Chen

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.

Deep Latent-Variable Models for Text Generation

no code implementations3 Mar 2022 Xiaoyu Shen

Text generation aims to produce human-like natural language output for down-stream tasks.

Dialogue Generation Document Summarization +1

Logical Fallacy Detection

2 code implementations28 Feb 2022 Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf

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).

Language Modelling Logical Fallacies +2

Knowledge-enhanced Session-based Recommendation with Temporal Transformer

no code implementations16 Dec 2021 Rongzhi Zhang, Yulong Gu, Xiaoyu Shen, Hui Su

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).

Graph Representation Learning Session-Based Recommendations

Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer

1 code implementation13 Dec 2021 Yunyun huang, Xiaoyu Shen, Chuanyi Li, Jidong Ge, Bin Luo

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.

Preventing Author Profiling through Zero-Shot Multilingual Back-Translation

1 code implementation EMNLP 2021 David Ifeoluwa Adelani, Miaoran Zhang, Xiaoyu Shen, Ali Davody, Thomas Kleinbauer, Dietrich Klakow

Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e. g. their gender or ethnicity.

Sentence Style Transfer +2

Learning Fine-grained Fact-Article Correspondence in Legal Cases

1 code implementation21 Apr 2021 Jidong Ge, Yunyun huang, Xiaoyu Shen, Chuanyi Li, Wei Hu

We believe that learning fine-grained correspondence between each single fact and law articles is crucial for an accurate and trustworthy AI system.

Text Matching

Neural Data-to-Text Generation with LM-based Text Augmentation

no code implementations EACL 2021 Ernie Chang, Xiaoyu Shen, Dawei Zhu, Vera Demberg, Hui Su

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-to-Text Generation Text Augmentation

Cross-Domain Learning for Classifying Propaganda in Online Contents

2 code implementations13 Nov 2020 Liqiang Wang, Xiaoyu Shen, Gerard de Melo, Gerhard Weikum

Prior work has focused on supervised learning with training data from the same domain.

DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool

no code implementations COLING 2020 Ernie Chang, Jeriah Caplinger, Alex Marin, Xiaoyu Shen, Vera Demberg

We present a lightweight annotation tool, the Data AnnotatoR Tool (DART), for the general task of labeling structured data with textual descriptions.

Active Learning text annotation

Integrating Image Captioning with Rule-based Entity Masking

no code implementations22 Jul 2020 Aditya Mogadala, Xiaoyu Shen, Dietrich Klakow

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.

Image Captioning

Diversifying Dialogue Generation with Non-Conversational Text

1 code implementation ACL 2020 Hui Su, Xiaoyu Shen, Sanqiang Zhao, Xiao Zhou, Pengwei Hu, Randy Zhong, Cheng Niu, Jie zhou

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation.

Dialogue Generation Translation

Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training

no code implementations18 Mar 2020 Ernie Chang, David Ifeoluwa Adelani, Xiaoyu Shen, Vera Demberg

In this work, we develop techniques targeted at bridging the gap between Pidgin English and English in the context of natural language generation.

Data-to-Text Generation Machine Translation +1

Unsupervised Rewriter for Multi-Sentence Compression

no code implementations ACL 2019 Yang Zhao, Xiaoyu Shen, Wei Bi, Akiko Aizawa

First, the word graph approach that simply concatenates fragments from multiple sentences may yield non-fluent or ungrammatical compression.

Sentence Sentence Compression

Improving Multi-turn Dialogue Modelling with Utterance ReWriter

1 code implementation ACL 2019 Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, Jie zhou

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.

Coreference Resolution Dialogue Rewriting

NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation

no code implementations EMNLP 2018 Hui Su, Xiaoyu Shen, Wenjie Li, Dietrich Klakow

Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems.

Dialogue Generation

Improving Variational Encoder-Decoders in Dialogue Generation

no code implementations6 Feb 2018 Xiaoyu Shen, Hui Su, Shuzi Niu, Vera Demberg

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation.

Dialogue Generation

DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset

13 code implementations IJCNLP 2017 Yan-ran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, Shuzi Niu

We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects.

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