Revisit Automatic Error Detection for Wrong and Missing Translation -- A Supervised Approach

no code implementations • IJCNLP 2019 • Wenqiang Lei, Weiwen Xu, Ai Ti Aw, Yuanxin Xiang, Tat Seng Chua

While achieving great fluency, current machine translation (MT) techniques are bottle-necked by adequacy issues.

Machine Translation Translation

Addressing the Vulnerability of NMT in Input Perturbations

1 code implementation • NAACL 2021 • Weiwen Xu, Ai Ti Aw, Yang Ding, Kui Wu, Shafiq Joty

Neural Machine Translation (NMT) has achieved significant breakthrough in performance but is known to suffer vulnerability to input perturbations.

Machine Translation NMT +1

Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering

1 code implementation • Findings (ACL) 2021 • Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam

Our framework contains three new ideas: (a) {\tt AMR-SG}, an AMR-based Semantic Graph, constructed by candidate fact AMRs to uncover any hop relations among question, answer and multiple facts.

graph construction Knowledge Graphs +4

Exploiting Reasoning Chains for Multi-hop Science Question Answering

1 code implementation • Findings (EMNLP) 2021 • Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam

We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the reasoning chain for multi-hop Science Question Answering.

Science Question Answering

Improving Lexical Embeddings for Robust Question Answering

no code implementations • 28 Feb 2022 • Weiwen Xu, Bowei Zou, Wai Lam, Ai Ti Aw

Recent techniques in Question Answering (QA) have gained remarkable performance improvement with some QA models even surpassed human performance.

Question Answering

A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems

1 code implementation • 14 Apr 2022 • Yang Deng, Wenxuan Zhang, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam

In this work, we propose a novel Unified MultI-goal conversational recommeNDer system, namely UniMIND.

Multi-Task Learning Recommendation Systems +1

PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks

1 code implementation • 17 Oct 2022 • Weiwen Xu, Xin Li, Yang Deng, Wai Lam, Lidong Bing

Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training.

Data Augmentation Relation

ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction

1 code implementation • 17 Oct 2022 • Weiwen Xu, Yang Deng, Wenqiang Lei, Wenlong Zhao, Tat-Seng Chua, Wai Lam

We study automatic Contract Clause Extraction (CCE) by modeling implicit relations in legal contracts.

Implicit Relations Relation

From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader

1 code implementation • 9 Dec 2022 • Weiwen Xu, Xin Li, Wenxuan Zhang, Meng Zhou, Wai Lam, Luo Si, Lidong Bing

We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data.

Classification Extractive Question-Answering +6

mPMR: A Multilingual Pre-trained Machine Reader at Scale

1 code implementation • 23 May 2023 • Weiwen Xu, Xin Li, Wai Lam, Lidong Bing

mPMR aims to guide multilingual pre-trained language models (mPLMs) to perform natural language understanding (NLU) including both sequence classification and span extraction in multiple languages.

Classification Machine Reading Comprehension +3

Reasons to Reject? Aligning Language Models with Judgments

1 code implementation • 22 Dec 2023 • Weiwen Xu, Deng Cai, Zhisong Zhang, Wai Lam, Shuming Shi

As humans, we consistently engage in interactions with our peers and receive feedback in the form of natural language.