paper-with-me

홈 › Papers

Context-Aware Interaction Network for Question Matching

2021-04-17 · EMNLP 2021 11 · Zhe Hu, Zuohui Fu, Yu Yin, Gerard de Melo

Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links between the two input sequences, neglecting the importance of contextual information. We propose a context-aware interaction network (COIN) to properly align two sequences and infer their semantic relationship. Specifically, each interaction block includes (1) a context-aware cross-attention mechanism to effectively integrate contextual information when aligning two sequences, and (2) a gate fusion layer to flexibly interpolate aligned representations. We apply multiple stacked interaction blocks to produce alignments at different levels and gradually refine the attention results. Experiments on two question matching datasets and detailed analyses demonstrate the effectiveness of our model.

📄 PDF Abstract BibTeX arXiv:2104.08451

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceText Matching

Similar Papers 제목 키워드 기반

PG-GSQL: Pointer-Generator Network with Guide Decoding for Cross-Domain Context-Dependent Text-to-SQL Generation

2020-12-01 · COLING 2020 8 · Huajie Wang, Mei Li, Lei Chen

Text-to-SQL is a task of translating utterances to SQL queries, and most existing neural approaches of text-to-SQL focus on the cross-domain context-independent generation task. We pay close attention to the cross-domain…

DecoderText to SQLText-To-SQL

A Hybrid Approach of Deep Semantic Matching and Deep Rank for Context Aware Question Answer System

2019-10-01 · ROCLING 2019 10 · Shu-Yi Xie, Chia-Hao Chang, Zhi Zhang, Yang Mo 외

DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension

2019-08-30 · Shuailiang Zhang, Hai Zhao, Yuwei Wu, Zhuosheng Zhang 외

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representati…

Reading ComprehensionSentence

Answer-focused and Position-aware Neural Question Generation

2018-10-01 · EMNLP 2018 10 · Xingwu Sun, Jing Liu, Yajuan Lyu, wei he 외

In this paper, we focus on the problem of question generation (QG). Recent neural network-based approaches employ the sequence-to-sequence model which takes an answer and its context as input and generates a relevant que…

Machine Reading ComprehensionPositionQuestion AnsweringQuestion Generation+2

Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring

2019-12-02 · Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li 외

Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and…

DecoderPositionQuestion GenerationQuestion-Generation+1