Analyzing and interpreting neural networks for NLP

Summary of the program

Time	Program item
09:00-09:10	Opening remarks
09:10-10:00	Invited talk 1: Yoav Goldberg
10:00-11:00	Poster session 1 (10:30-11 tea break)
11:00-12:30	Oral presentation session 1 (6 x 15 minutes)
12:30-14:00	Lunch
14:00-14:50	Invited talk 2: Graham Neubig
14:50-16:00	Poster session 2 (15:30-16 tea break)
16:00-16:50	Invited talk 3: Leila Wehbe
16:50-17:20	Oral presentation session 2 (2 x 15 minutes)
17:20-17:30	Best paper announcement and closing remarks

Oral presentation session 1

11:00-11:15 Interpretable Structure Induction via Sparse Attention. Ben Peters, Vlad Niculae and André F. T. Martins.
11:15-11:30 Understanding Convolutional Neural Networks for Text Classification. Alon Jacovi, Yoav Goldberg and Oren Sar Shalom.
11:30-11:45 Extracting Syntactic Trees from Transformer Encoder Self-Attentions. David Mareček and Rudolf Rosa.
11:45-12:00 Context-Free Transductions with Neural Stacks. Yiding Hao, William Merrill, Dana Angluin, Robert Frank, Noah Amsel, Andrew Benz and Simon Mendelsohn.
12:00-12:15 Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures. Danilo Croce, Daniele Rossini and Roberto Basili.
12:15-12:30 Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell. Pia Sommerauer and Antske Fokkens.

Oral presentation session 2

16:50-17:05 What do RNN Language Models Learn about Filler–Gap Dependencies? Ethan Wilcox, Roger Levy, Takashi Morita and Richard Futrell.
17:05-17:20 Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information. Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes and Willem Zuidema.

Poster session 1

When does deep multi-task learning work for loosely related document classification tasks? Emma Kerinec, Chloé Braud and Anders Søgaard.
Analyzing Learned Representations of a Deep ASR Performance Prediction Model. Zied Elloumi, Laurent Besacier, Olivier Galibert and Benjamin Lecouteux.
Learning Explanations from Language Data. David Harbecke, Robert Schwarzenberg and Christoph Alt.
Nightmare at test time: How punctuation prevents parsers from generalizing. Anders Søgaard, Miryam de Lhoneux and Isabelle Augenstein.
How much should you ask? On the question structure in QA systems. Barbara Rychalska, Dominika Basaj, Anna Wróblewska and Przemyslaw Biecek.
Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System. Barbara Rychalska, Dominika Basaj, Anna Wróblewska and Przemyslaw Biecek.
Interpretable Textual Neuron Representations for NLP. Nina Poerner, Benjamin Roth and Hinrich Schütze.
Evaluating Textual Representations through Image Generation. Graham Spinks and Marie-Francine Moens.
On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis. Jose Camacho-Collados and Mohammad Taher Pilehvar.
Language Models Learn POS First. Naomi Saphra and Adam Lopez.
Jump to better conclusions: SCAN both left and right. Joost Bastings, Marco Baroni, Jason Weston, Kyunghyun Cho and Douwe Kiela.
Linguistic representations in multi-task neural networks for ellipsis resolution. Ola Rønning, Daniel Hardt and Anders Søgaard.
Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models. Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui and Masaaki Nagata.
Rule induction for global explanation of trained models. Madhumita Sushil, Simon Suster and Walter Daelemans.
Predicting and interpreting embeddings for out of vocabulary words in downstream tasks. Nicolas Garneau, Jean-Samuel Leboeuf and Luc Lamontagne.
Can LSTM Learn to Capture Agreement? The Case of Basque. Shauli Ravfogel, Yoav Goldberg and Francis Tyers.
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks. Joao Loula, Marco Baroni and Brenden Lake.
Probing sentence embeddings for structure-dependent tense. Geoff Bacon and Terry Regier.
Evaluating the Ability of LSTMs to Learn Context-Free Grammars. Luzi Sennhauser and Robert Berwick.
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation. Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White and Benjamin Van Durme.
Interpretable Neural Architectures for Attributing an Ad’s Performance to its Writing Style. Reid Pryzant, Sugato Basu and Kazoo Sone.
Interpretable Word Embedding Contextualization. Kyoung-Rok Jang, Sung-Hyon Myaeng and Sang-Bum Kim.
Interpreting Neural Networks with Nearest Neighbors. Eric Wallace, Shi Feng and Jordan Boyd-Graber.
‘Indicatements’ that character language models learn English morpho-syntactic units and regularities. Yova Kementchedjhieva and Adam Lopez.
Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items. Jaap Jumelet and Dieuwke Hupkes.

Poster session 2

State Gradients for RNN Memory Analysis. Lyan Verwimp, Hugo Van hamme, Vincent Renkens and Patrick Wambacq.
LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation. Pankaj Gupta and Hinrich Schütze.
Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue. Dieuwke Hupkes, Sanne Bouwmeester and Raquel Fernández.
An Operation Sequence Model for Explainable Neural Machine Translation. Felix Stahlberg and Bill Byrne.
Introspection for convolutional automatic speech recognition. Andreas Krug and Sebastian Stober.
Portable, layer-wise task performance monitoring for NLP models. Tom Lippincott.
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy and Samuel Bowman.
Explicitly modeling case improves neural dependency parsing. Clara Vania and Adam Lopez.
Learning and Evaluating Sparse Interpretable Sentence Embeddings. Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko and Thomas Hofmann.
Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis. Kelly Zhang and Samuel Bowman.
Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model. Steven Derby, Paul Miller, Brian Murphy and Barry Devereux.
Closing Brackets with Recurrent Neural Networks. Natalia Skachkova, Thomas Trost and Dietrich Klakow.
Iterative Recursive Attention Model for Interpretable Sequence Classification. Martin Tutek and Jan Šnajder.
Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models. Avery Hiebert, Cole Peterson, Alona Fyshe and Nishant Mehta.
Debugging Sequence-to-Sequence Models with Seq2Seq-Vis. Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister and Alexander Rush.
Grammar Induction with Neural Language Models: An Unusual Replication. Phu Mon Htut, Kyunghyun Cho and Samuel Bowman.
Importance of Self-Attention for Sentiment Analysis. Gaël Letarte, Frédérik Paradis, Philippe Giguère and François Laviolette.
Does Syntactic Knowledge in Multilingual Language Models Transfer Across Languages? Prajit Dhar and Arianna Bisazza
Exploiting Attention to Reveal Shortcomings in Memory Models. Kaylee Burns, Aida Nematzadeh, Erin Grant, Alison Gopnik and Tom Griffiths.
An Analysis of Encoder Representations in Transformer-Based Machine Translation. Alessandro Raganato and Jörg Tiedemann.
End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space. Pranava Swaroop Madhyastha, Josiah Wang and Lucia Specia.
Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation. Johnny Wei, Khiem Pham, Brendan O’Connor and Brian Dillon.
Limitations in learning an interpreted language with recurrent models. Denis Paperno.