Improving AI’s Language Skills at ACL 2018

Share this post:

The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) will be held July 15–20 in Melbourne, Australia. ACL received 1,544 submissions and accepted 384, for an overall acceptance rate of 24.9 percent. IBM Research AI will present multiple papers at ACL 2018 and is proud to be a Gold sponsor. Please plan to attend the sessions below or visit booth #9 in the exhibit hall to learn about our latest advances in natural language processing, including unsupervised text style transfer, coreference resolution, entity linking, mention detection, neural models, adversarial attacks, argumentation mining, and reading comprehension. IBM researchers are also giving a tutorial and co-organizing a workshop at ACL 2018; please see details below.

Accepted papers at ACL 2018

Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer
C. Nogueira dos Santos, I. Melnyk and I. Padhi
Jul 16 12:30 – 14:00

Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking
G. Kundu, A. Sil, R. Florian and W. Hamza
Jul 17 14:00 @ Room 210/211, MCEC

Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering
R. Zhang, C. Nogueira dos Santos, M. Yasunaga, B. Xiang and D. Radev
Jul 16 12:30 – 14:00

Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
J. H. Lau, T. Cohn, T. Baldwin, J. Brooke and A. Hammond
Jul 17 16:20 @ Room 212/213, MCEC

Attacking Visual Language Understanding with Adversarial Examples: A Case Study on Neural Image Captioning
H. Chen, H. Zhang, P.-Y. Chen, J. Yi and C.-J. Hsieh
Jul 18 12:30 – 14:00

Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour
S. Mathias, D. Kanojia, K. Patel, S. Agrawal, A. Mishra and P. Bhattacharyya
Jul 18 12:30 – 14:00

Will it Blend? Weak and Manual Labeled Data in a Neural Network for Argumentation Mining
E. Shnarch, C. Alzate, L. Dankin, M. Gleize, Y. Hou, L. Choshen, R. Aharonov and N. Slonim
Jul 18 12:30 – 14:00

A Co-Matching Model for Multi-choice Reading Comprehension
S. Wang, M. Yu, S. Chang and J. Jiang
Jul 18, 14:00 – 15:00 @ Room 219, MCEC

Learning Thematic Similarity Metric from Article Sections Using Triplet Networks
L. Ein Dor, Y. Mass, A. Halfon, E. Venezian, I. Shnayderman, R. Aharonov and N. Slonim
Jul 16 12:30 – 14:00

Discovering Implicit Knowledge with Unary Relations
M. Glass and A. Gliozzo
Jul 17 12:30 – 14:00

A Graph-to-Sequence Model for AMR-to-Text Generation
L. Song, Y. Zhang, Z. Wang and D. Gildea
Jul 17 12:30 – 14:00

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension
A. Saha, R. Aralikatte, M. M. Khapra and K. Sankaranarayanan
Jul 17 12:30 – 14:00

Exemplar Encoder Decoder for Neural Conversation Generation
G. Pandey, D. Contractor, V. Kumar and S. Joshi
Jul 17 10:30 @ Room 212/213, MCEC

The Influence of Context on Sentence Acceptability Judgements
J.-P. Bernardy, S. Lappin and J. H. Lau
Jul 17 14:30 @ Room 219, MCEC

A Neural Parser as a Direct Classifier for Head-Final Languages
H. Kanayama, M. Muraoka and R. Kohita
Jul 19 13:30 – 14:30, RELNLP Workshop

Towards Cross-Domain Engagement Analysis in Medical Notes
A. Faulkner and S. Rosenthal
Jul 19 16:15 – 18:15, BioNLP Workshop

A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset
M. Boratko, H. Padigela, D. Mikkilineni, P. Yuvraj, R. Das, A. McCallum, M. Chang, A. Fokoue-Nkoutche, P. Kapanipathi, N. Mattei, R. Musa, K. Talamadupula and M. Witbrock
Jul 19, Machine Reading for Question Answering Workshop

ACL 2018 Tutorial

Multi-lingual Entity Discovery and Linking Tutorial
A. Sil, H. Ji, D. Roth and S. Cucerzan
Jul 15

ACL 2018 Workshop

Relevance of Linguistic Structure in Neural NLP
G. Dinu, M. Ballesteros, A. Sil, A. Soggard, T. Naseem, Y. Goldberg, W. Hamza, S. Bowman and R. Florian
Jul 19

More AI stories

More Is Less: Learning Efficient Video Representations

IBM researchers developed a novel low memory footprint and efficient architecture for spatio-temporal analysis of video. The results show strong performance on several benchmarks – and allow training of deeper models using larger sequences of input frames, which will lead to higher accuracy on video action recognition tasks.

Continue reading

Sobolev Independence Criterion

At NeurIPS 2019, IBM Research AI will showcase the “Sobolev Independence Criterion," a novel interpretable dependency measure that provides feature importance scores that can be used for controlling False Discovery Rate.

Continue reading

IBM Research AI at NeurIPS 2019

IBM researchers from our labs around the world will present more than 100 papers across regular sessions and workshops at NeurIPS. They are all focused on different core technologies and use cases of AI. And a number of them will be on display in booth #111 with demos scientists will be presenting throughout the week.

Continue reading