ntmc-community/awesome-neural-models-for-semantic-match

A curated list of papers dedicated to neural text (semantic) matching.

Awesome Neural Models for Semantic Match

_{A collection of papers maintained by MatchZoo Team.
Checkout our open source toolkit MatchZoo for more information!}

Text matching is a core component in many natural language processing tasks, where many task can be viewed as a matching between two texts input.

Where s and t are source text input and target text input, respectively. The psi and phi are representation function for input s and t, respectively. The f is the interaction function, and g is the aggregation function. More detailed explaination about this formula can be found on A Deep Look into Neural Ranking Models for Information Retrieval. The representative matching tasks are as follows:

Tasks	Source Text	Target Text
Ad-hoc Information Retrieval	query	document (title/content)
Community Question Answering	question	question/answer
Paraphrase Identification	string1	string2
Natural Language Inference	premise	hypothesis
Response Retrieval	context/utterances	response
Long Form Question Answering	question+document	answer

Healthcheck

pip3 install -r requirements.txt
python3 healthcheck.py

awesome-neural-models-for-semantic-match's Issues

End-to-End Retrieval in Continuous Space

https://arxiv.org/pdf/1811.08008.pdf

ESIM model

Enhanced LSTM for Natural Language Inference

new push to response retrieval

add CONV-KNRM

CONV-KNRM is a paper published in WSDM 2018.

NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval

https://arxiv.org/pdf/1810.12936.pdf

Add HiNT from SIGIR 2018

Implement the HiNT model from SIGIR 2018 paper.

Add MIX from KDD 2018

MIX: Multi-Channel Information Crossing for Text Matching
website: http://www.kdd.org/kdd2018/accepted-papers/view/mix-multi-channel-information-crossing-for-text-matching

pdf: http://delivery.acm.org/10.1145/3220000/3219928/p110-chen.pdf?ip=89.146.52.65&id=3219928&acc=OPENTOC&key=4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E054E54E275136550&__acm__=1534239354_8f9980fa3cf636970710270d04a0a46f

Together We Stand: Siamese Networks for Similar Question Retrieval

SCQA

update Response retrieval to add recently published models and datasets

update new models and datasets recently published

Recommandation (unsupervised/low ressource text alignment)

Hey guys,

Good work both on MatchZoo and this list!
I would be interested in quick advices/pointers on something related: I'd like to match related parts of texts.

More formally, I've a document, made of different sections (each with multiple sentences), and I'd like to map it to a similar text (transcription in fact), which is a bit longer, with some noise but talk about the same thing (lot of similarities) and in the same order. I made a dynamic programming algorithms which maximize a cosine similarities between sentence embeddings. Results aren't too bad, but I'd like to experiment other stuff.

Any idea?

Thanks a lot for any clue / references that seems relevant. We could discuss through gitter.im as well.

Paul

---

I've not much gold data (i.e. suitable segments to be training pairs), which is why I mention unsupervised/low ressources).

A Decomposable Attention Model for Natural Language Inference

Here is an important work for NLI task, which can be added:
A Decomposable Attention Model for Natural Language Inference [EMNLP 2016, by Google]
open code
please consider it

Add Siamese-LSTM

for sentence level & character level similarity.

DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval

https://arxiv.org/pdf/1811.00606.pdf

NAACL 2018/2019 relevant papers

NAACL 2018:
DeepAlignment: Unsupervised Ontology Matching With Refined Word Vectors
http://www.dit.unitn.it/~pavel/OM/articles/Kolyvakis_N18.pdf
DR-BILSTM: DEPENDENT READING BIDIRECTIONAL LSTM FOR NATURAL LANGUAGE
https://arxiv.org/pdf/1802.05577.pdf
Learning to Disentangle Interleaved Conversational Threads with a Siamese Hierarchical Network and Similarity Ranking
https://www.aclweb.org/anthology/N18-1164
Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering
https://arxiv.org/pdf/1710.03430.pdf

NAACL 2019:
A Complex-valued Network for Matching
https://arxiv.org/pdf/1904.05298.pdf
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
https://arxiv.org/pdf/1810.08854.pdf

AAAI 2019 relevant papers

“match”

Yang, Xiao, et al. "Adversarial training for community question answer selection based on multi-scale matching."
https://arxiv.org/abs/1804.08058

Kim, Seonhoon, et al. "Semantic sentence matching with densely-connected recurrent and co-attentive information."
https://arxiv.org/abs/1805.11360

Zhao, Boming, et al. "Preference-Aware Task Assignment in On-demand Taxi Dispatching: An Online Stable Matching Approach." (2019).
https://www.tik.ee.ethz.ch/file/5c75a1f030e8d090d46ef165f1805d34/aaai19-zhao.pdf

Tang, Min, Jiaran Cai, and Hankz Hankui Zhuo. "Multi-Matching Network for Multiple Choice Reading Comprehension." (2019).
http://xplan-lab.org/Paper_PDF/AAAI-19.pdf

Lai, Yuxuan, et al. "Lattice CNNs for Matching Based Chinese Question Answering." arXiv preprint arXiv:1902.09087 (2019).
https://arxiv.org/abs/1902.09087

Zhang, Kun, et al. "DRr-Net: Dynamic Re-read Network for Sentence Semantic Matching." (2019).
http://staff.ustc.edu.cn/~cheneh/paper_pdf/2019/Kun-Zhang-AAAI.pdf

“retrieval”

Tang, Zhiwen, and Grace Hui Yang. "Deeptilebars: Visualizing term distribution for neural information retrieval."
https://arxiv.org/abs/1811.00606

“answer”

Hu, Minghao, et al. "Read+ verify: Machine reading comprehension with unanswerable questions."
https://arxiv.org/abs/1808.05759

Yang, Xiao, et al. "Adversarial training for community question answer selection based on multi-scale matching.
https://arxiv.org/abs/1804.08058

Pang, Liang, et al. "HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering." arXiv preprint arXiv:1901.03866 (2019).
https://arxiv.org/abs/1901.03866

(not sure)
Answer Identification from Product Reviews for User Questions by Multi-­‐task Attentive Networks Long Chen (Northwest University of China)*; Ziyu Guan (Northwest University); Wei Zhao (Xidian University); Wanqing
http://web.cse.ohio-state.edu/~sun.397/docs/AAAI19_ProdQA.pdf

For text match problem, what is the different between question-question match and question-answer match?

I know question-question match is a text similarity problem.
What about question-answer match or question-doc match? It is used in information retrieval.
question-question match is indeed text similarity. But how do you define question-answer similarity?
Thank you!!

abcnn

ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs

new push to response retrieval

new push to response retrieval 200811 by wuchen

ACL 2018/2019 and CIKM 2018 relevant papers

ACL2018

• Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network: Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, Hua Wu
• Think Visually: Question Answering through Virtual Imagery: Ankit Goyal, Jian Wang, Jia Deng
• Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce: Minghui Qiu, Liu Yang, Feng Ji, Weipeng Zhao, Wei Zhou, Jun Huang, Haiqing Chen, W. Bruce Croft, Wei Lin

ACL2019

• A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching: Jihun Choi, Taeuk Kim, Sang-goo Lee
• Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction: Kosuke Nishida, Kyosuke Nishida, Masaaki Nagata, Atsushi Otsuka, Itsumi Saito, Hisako Asano, Junji Tomita
• Matching Article Pairs with Graphical Decomposition and Convolutions: Bang Liu, Di Niu, Haojie Wei, Jinghong Lin, Yancheng He, Kunfeng Lai, Yu Xu

CIKM2018

• A Globalization-Semantic Matching Neural Network for Paraphrase Identification: Miao Fan, Wutao Lin, Yue Feng, Mingming Sun, Ping Li
• AQuPR: Attention based Query Passage Retrieval: Parth Pathak, Mithun Das Gupta, Niranjan Nayak, Harsh Kohli
• Retrieve-and-Read: Multi-task Learning of Information: Kyosuke Nishida, Itsumi Saito, Atsushi Otsuka, Hisako Asano, and Junji Tomita
• Attentive Neural Architecture for Ad-hoc Structured Document: Saeid Balaneshinkordan, Alexander Kotov, Fedor Nikolaev

IJCAI 2018/2019 and WWW 2018/2019 relevant papers

IJCAI-2018

• Weakly Learning to Match Experts in Online Community: Yujie Qian, Jie Tang, Kan Wu
• Hermitian Co-Attention Networks for Text Matching in Asymmetrical Domains: Yi Tay, Anh Tuan Luu, Siu Cheung Hui
• Attention-Fused Deep Matching Network for Natural Language Inference, Chaoqun Duan, Lei Cui, Xinchi Chen: Furu Wei, Conghui Zhu, Tiejun Zhao

IJCAI-2019

• A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots: Xueliang Zhao, Chongyang Tao, Wei Wu, Can Xu, Dongyan Zhao, Rui Yan

WWW-2018

• Matching Natural Language Sentences with Hierarchical Sentence Factorization: Bang Liu, Ting Zhang, Fred X. Han, Di Niu, Kunfeng Lai, Yu Xu

• A Neural Network-based Framework for Non-factoid Question Answering: Nam Khanh Tran, Claudia Niederée

WWW-2019

• Semantic Text Matching for Long-Form Documents: Jyun-Yu Jiang, Mingyang Zhang, Cheng Li, Michael Bendersky, Nadav Golbandi, Marc Najork

• Learning Fast Matching Models from Weak Annotations: Xue Li, Zhipeng Luo, Hao Sun, Jianjin Zhang, Weihao Han, Xianqi Chu, Liangjie Zhang, Qi Zhang

• Local Matching Networks for Engineering Diagram Search: Zhuyun Dai, Zhen Fan, Hafeezul Rahman, Jamie Callanx

• Learning Novelty-Aware Ranking of Answers to Complex Questions: Shahar Harel , Sefi Albo , Eugene Agichtein, Kira Radinsky

• HAR: A Hierarchical Attention Retrieval Model for Healthcare Question Answering: Ming Zhu, Aman Ahuja, Wei Wei, Chandan K. Reddy

Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering

https://arxiv.org/pdf/1810.00494.pdf

multi-cast attention network

Multi-Cast Attention Networks for Retrieval-based Question
Answering and Response Prediction: https://arxiv.org/pdf/1806.00778.pdf