Program 2018


Wednesday, October 31, 2018

Opening remarks

CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Coffee break

CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection


Invited talk by Max Welling: Inductive Bias in Deep Learning

Session 1

Embedded-State Latent Conditional Random Fields for Sequence Labeling
Dung Thai, Sree Harsha Ramesh, Shikhar Murty, Luke Vilnis and Andrew McCallum

Continuous Word Embedding Fusion via Spectral Decomposition
Tianfan Fu, Cheng Zhang and Stephan Mandt

Coffee break

Poster session 1


Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems
Van-Khanh Tran and Le-Minh Nguyen

A Trio Neural Model for Dynamic Entity Relatedness Ranking
Tu Nguyen, Tuan Tran and Wolfgang Nejdl

A Unified Neural Network Model for Geolocating Twitter Users
Mohammad Ebrahimi, Elaheh ShafieiBavani, Raymond Wong and Fang Chen

Corpus-driven Thematic Hierarchy Induction
Ilia Kuznetsov and Iryna Gurevych

Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge
Pasquale Minervini and Sebastian Riedel

From Strings to Other Things: Linking the Neighborhood and Transposition effects in Word Reading
Stéphan Tulkens, Dominiek Sandra and Walter Daelemans

Global Attention for Name Tagging
Boliang Zhang, Spencer Whitehead, Lifu Huang and Heng Ji

Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Maha Elbayad, Laurent Besacier and Jakob Verbeek

Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension
Matthias Blohm, Glorianna Jagfeld, Ekta Sood, Xiang Yu and Ngoc Thang Vu

Uncovering Code-mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering
Deepak Gupta, Pabitra Lenka, Asif Ekbal and Pushpak Bhattacharyya

Learning to Embed Semantic Correspondence for Natural Language Understanding
Sangkeun Jung, Jinsik Lee and Jiwon Kim

Commonsense Knowledge Base Completion and Generation
Itsumi Saito, Kyosuke Nishida, Hisako Asano and Junji Tomita

Active Learning for Interactive Neural Machine Translation of Data Streams
Álvaro Peris and Francisco Casacuberta

Churn Intent Detection in Multilingual Chatbot Conversations and Social Media
Christian Abbet, Meryem M'hamdi, Athanasios Giannakopoulos, Robert West, Andreea Hossmann, Michael Baeriswyl and Claudiu Musat

Learning text representations for 500K classification tasks on Named Entity Disambiguation
Ander Barrena, Aitor Soroa and Eneko Agirre

Hierarchical Attention Based Position-aware Network for Aspect-level Sentiment Analysis
Lishuang Li, Yang Liu and AnQiao Zhou

Bidirectional Generative Adversarial Networks for Neural Machine Translation
Zhirui Zhang, Shujie Liu, Mu Li, Ming Zhou and Enhong Chen

Latent Entities Extraction: How to Extract Entities that Do Not Appear in the Text?
Eylon Shoshan and Kira Radinsky

Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction
Yova Kementchedjhieva, Sebastian Ruder, Ryan Cotterell and Anders Søgaard

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings
Kamil Bennani-Smires, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl and Martin Jaggi

Thursday, November 1, 2018

Session 2 (session chair: Ivan Vulić)

A Temporally Sensitive Submodularity Framework for Timeline Summarization
Sebastian Martschat and Katja Markert
Chinese Poetry Generation with a Salient-Clue Mechanism
Xiaoyuan Yi, Ruoyu Li and Maosong Sun
Multi-modal Sequence Fusion via Recursive Attention for Emotion Recognition
Rory Beard, Ritwik Das, Raymond W. M. Ng, P. G. Keerthana Gopalakrishnan, Luka Eerens, Pawel Swietojanski and Ondrej Miksik
Using sparse semantic embeddings learned from multimodal text and image data to model human conceptual knowledge
Steven Derby, Paul Miller, Brian Murphy and Barry Devereux
Similarity dependent Chinese Restaurant Process for Cognate Identification in Multilingual Wordlists
Taraka Rama
Uncovering Divergent Linguistic Information in Word Embeddings with Lessons for Intrinsic and Extrinsic Evaluation (best paper award)
Mikel Artetxe, Gorka Labaka, Inigo Lopez-Gazpio and Eneko Agirre

Coffee break

Invited talk by Asifa Majid: Semantic spaces across diverse languages

​Session 3 (session chair: Annie Louis)

Comparing Models of Associative Meaning: An Empirical Investigation of Reference in Simple Language Games
Judy Hanwen Shen, Matthias Hofer, Bjarke Felbo and Roger Levy
Sequence Classification with Human Attention (special paper award)
Maria Barrett, Joachim Bingel, Nora Hollenstein, Marek Rei and Anders Søgaard

Lunch, SIGNLL business meeting

Session 4 (session chair: Wilker Aziz)

Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!
​Katharina Kann, Sascha Rothe and Katja Filippova
Predefined Sparseness in Recurrent Sequence Models
Thomas Demeester, Johannes Deleu, Fréderic Godin and Chris Develder
Learning to Actively Learn Neural Machine Translation
Ming Liu, Wray Buntine and Gholamreza Haffari
Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit
Amrith Krishna, Bodhisattwa Prasad Majumder, Rajesh Bhat and Pawan Goyal
Weakly-supervised Neural Semantic Parsing with a Generative Ranker
Jianpeng Cheng and Mirella Lapata
Modeling Composite Labels for Neural Morphological Tagging
Alexander Tkachenko and Kairit Sirts

Coffee break

Poster session 2


Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks
Edward Collins, Nikolai Rozanov and Bingbing Zhang

Vectorial semantic spaces do not encode human judgments of intervention similarity
Paola Merlo and Francesco Ackermann

Lessons learned in multilingual grounded language learning
Ákos Kádár, Desmond Elliott, Marc-Alexandre Côté, Grzegorz Chrupała and Afra Alishahi

Unsupervised Sentence Compression using Denoising Auto-Encoders
Thibault Fevry and Jason Phang

Resources to Examine the Quality of Word Embedding Models Trained on n-Gram Data
Ábel Elekes, Adrian Englhardt, Martin Schäler and Klemens Böhm

Linguistically-based Deep Unstructured Question Answering
Ahmad Aghaebrahimian

DIMSIM: An Accurate Chinese Phonetic Similarity Algorithm based on Learned High Dimensional Encoding
Min Li, Marina Danilevsky, Sara Noeman and Yunyao Li

Challenge or Empower: Revisiting Argumentation Quality in a News Editorial Corpus
Roxanne El Baff, Henning Wachsmuth, Khalid Al Khatib and Benno Stein

Bringing Order to Neural Word Embeddings with Embeddings Augmented by Random Permutations (EARP)
Trevor Cohen and Dominic Widdows

Aggregated Semantic Matching for Short Text Entity Linking
Feng Nie, Shuyan Zhou, Jing Liu, Jinpeng Wang, Chin-Yew Lin and Rong Pan

Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models
Tong Niu and Mohit Bansal

Improving Response Selection in Multi-turn Dialogue Systems by Incorporating Domain Knowledge
Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann and Asja Fischer

The Lifted Matrix-Space Model for Semantic Composition
WooJin Chung, Sheng-Fu Wang and Samuel Bowman

End-to-End Neural Entity Linking
Nikolaos Kolitsas, Octavian-Eugen Ganea and Thomas Hofmann

Modelling Salient Features as Directions in Fine-Tuned Semantic Spaces
Thomas Ager, Ondřej Kuželka and Steven Schockaert

Model Transfer with Explicit Knowledge of the Relation between Class Definitions
Hiyori Yoshikawa and Tomoya Iwakura

Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner
Yury Zemlyanskiy and Fei Sha

Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis
Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao, Weiwei Sun and Xiaojun Wan

From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information
Hengru Xu, Shen Li, Renfen Hu, Si Li and Sheng Gao

Sequence to Sequence Mixture Model for Diverse Machine Translation
Xuanli He, Gholamreza Haffari and Mohammad Norouzi

Continuous Word Embedding Fusion via Spectral Decomposition
Tianfan Fu, Cheng Zhang and Stephan Mandt