XplaiNLI: Explainable Natural Language Inference through Visual Analytics

08/12/2020

XplaiNLI: Explainable Natural Language Inference through Visual Analytics

Aikaterini-Lida Kalouli, Rita Sevastjanova, Valeria de Paiva, Richard Crouch, Mennatallah El-Assady

Keywords:

Abstract Paper Similar Papers

Abstract: Advances in Natural Language Inference (NLI) have helped us understand what state-of-the-art models really learn and what their generalization power is. Recent research has revealed some heuristics and biases of these models. However, to date, there is no systematic effort to capitalize on those insights through a system that uses these to explain the NLI decisions. To this end, we propose XplaiNLI, an eXplainable, interactive, visualization interface that computes NLI with different methods and provides explanations for the decisions made by the different approaches.

The video of this talk cannot be embedded. You can watch it here:

https://underline.io/lecture/6435-xplainli-explainable-natural-language-inference-through-visual-analytics

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at COLING Workshops 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

08/12/2020

Reading Comprehension as Natural Language Inference:A Semantic Analysis

Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar and
Xiang Li, Pavan Kapanipathi, Kartik Talamadupula

Keywords Paper

0

0

0

0

7:54

19/04/2021

Exploring transitivity in neural NLI models through veridicality

Hitomi Yanaka, Koji Mineshima, Kentaro Inui

Keywords Paper

0

0

0

0

11:39

05/12/2020

A survey of the state of explainable AI for natural language processing

Marina Danilevsky, Kun Qian, Ranit Aharonov and
Yannis Katsis, Ban Kawas, Prithviraj Sen

Keywords Paper

0

0

0

0

14:13

04/07/2020

MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization

Canwen Xu, Jiaxin Pei, Hongtao Wu and
Yiyu Liu, Chenliang Li

Keywords Paper

Classification, Question Answering, Summarization, Natural Processing

0

0

0

0

7:00

04/07/2020

ERASER: A Benchmark to Evaluate Rationalized NLP Models

Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani and
Eric Lehman, Caiming Xiong, Richard Socher, Byron C. Wallace

Keywords Paper

NLP, Evaluating Reasoning, ERASER, Rationalized Models

0

0

0

0

9:04

04/07/2020

Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data

Emily M. Bender, Alexander Koller

Keywords Paper

NLP tasks, natural understanding, large models, NLU

0

0

0

0

12:35

04/07/2020

Language (Re)modelling: Towards Embodied Language Understanding

Ronen Tamari, Chen Shani, Tom Hope and
Miriam R L Petruck, Omri Abend, Dafna Shahaf

Keywords Paper

Embodied Understanding, natural understanding, representation, NLU systems

0

0

0

0

12:08

06/12/2021

Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning

Christopher Rytting, David Wingate

Keywords Paper

language, transfer learning

0

0

0

0

14:16

04/07/2020

Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences

Yi Tay, Donovan Ong, Jie Fu and
Alvin Chan, Nancy Chen, Anh Tuan Luu, Chris Pal

Keywords Paper

Machine Alignment, Understanding preferences, natural understanding, natural task

0

0

0

0

5:25

26/04/2020

Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction

Taeuk Kim, Jihun Choi, Daniel Edmiston, Sang-goo Lee

Keywords Paper

0

0

0

0

4:59

16/11/2020

Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification

Prithviraj Sen, Marina Danilevsky, Yunyao Li and
Siddhartha Brahma, Matthias Boehm, Laura Chiticariu, Rajasekar Krishnamurthy

Keywords Paper

interpretability models, sentence classification, le, human-machine models

0

0

0

0

9:42

04/07/2020

Uncertain Natural Language Inference

Tongfei Chen, Zhengping Jiang, Adam Poliak and
Keisuke Sakaguchi, Benjamin Van Durme

Keywords Paper

Uncertain Inference, Natural Inference, NLI, UNLI

0

0

0

0

6:41

08/12/2020

Seeing the World through Text: Evaluating Image Descriptions for Commonsense Reasoning in Machine Reading Comprehension

Diana Galvan-Sosa, Jun Suzuki, Kyosuke Nishida and
Koji Matsuda, Kentaro Inui

Keywords Paper

0

0

0

0

14:03

26/04/2020

Learn to Explain Efficiently via Neural Logic Inductive Learning

Yuan Yang, Le Song

Keywords Paper

inductive logic programming, interpretability, attention

0

0

0

0

5:01

08/12/2020

Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data

Ankit Arun, Soumya Batra, Vikas Bhardwaj and
Ashwini Challa, Pinar Donmez, Peyman Heidari, Hakan Inan, Shashank Jain, Anuj Kumar, Shawn Mei, Karthik Mohan, Michael White

Keywords Paper

0

0

0

0

15:01

04/07/2020

Understanding Attention for Text Classification

Xiaobing Sun, Wei Lu

Keywords Paper

Text Classification, natural tasks, NLP tasks, gradient process

0

0

0

0

11:54

14/06/2020

Towards Visually Explaining Variational Autoencoders

Wenqian Liu, Runze Li, Meng Zheng and
Srikrishna Karanam, Ziyan Wu, Bir Bhanu, Richard J. Radke, Octavia Camps

Keywords Paper

explainability, reasoning, attention, vae, anomaly, disentanglement

0

0

0

0

4:56

02/02/2021

Knowledge-driven Natural Language Understanding of English Text and its Applications

Kinjal Basu, Sarat Chandra Varanasi, Farhad Shakerin and
Joaquín Arias, Gopal Gupta

Keywords Paper

0

0

0

0

18:52

02/02/2021

LIREx: Augmenting Language Inference with Relevant Explanations

Xinyan Zhao, V.G.Vinod Vydiswaran

Keywords Paper

0

0

0

0

18:56

04/07/2020

Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses

Erfan Sadeqi Azer, Daniel Khashabi, Ashish Sabharwal, Dan Roth

Keywords Paper

Natural Processing, NLP, NLP research, Bayesian hypotheses

0

0

0

0

11:59

16/11/2020

STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering

Hrituraj Singh, Sumit Shekhar

Keywords Paper

answering questions, natural questions, sequential localization, question encoding

0

0

0

0

12:01

16/11/2020

Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning

Xiaoxiao Guo, Mo Yu, Yupeng Gao and
Chuang Gan, Murray Campbell, Shiyu Chang

Keywords Paper

language techniques, language challenges, action generation, if solving

0

0

0

0

7:31

04/07/2020

(Re)construing Meaning in NLP

Sean Trott, Tiago Timponi Torrent, Nancy Chang, Nathan Schneider

Keywords Paper

NLP, natural understanding, theoretical semantics, construed meaning

0

0

0

0

14:03

04/07/2020

Logical Natural Language Generation from Open-Domain Tables

Wenhu Chen, Jianshu Chen, Yu Su and
Zhiyu Chen, William Yang Wang

Keywords Paper

Logical Generation, neural NLG, surface-level realizations, logical inference

0

0

0

0

11:48

06/12/2020

Network-to-Network Translation with Conditional Invertible Neural Networks

Robin Rombach, Patrick Esser, Bjorn Ommer

Keywords Paper

0

0

0

0

3:25

04/07/2020

Probing Linguistic Systematicity

Emily Goodwin, Koustuv Sinha, Timothy J. O'Donnell

Keywords Paper

Probing Systematicity, probing tasks, generalization, natural inference

0

0

0

0

12:57

04/07/2020

Temporally-Informed Analysis of Named Entity Recognition

Shruti Rijhwani, Daniel Preotiuc-Pietro

Keywords Paper

named recognition, NLP tasks, Natural models, language use

0

0

0

0

11:30

02/02/2021

Neural Analogical Matching

Maxwell Crouse, Constantine Nakos, Ibrahim Abdelaziz, Ken Forbus

Keywords Paper

0

0

0

0

14:02

16/11/2020

Asking without Telling: Exploring Latent Ontologies in Contextual Representations

Julian Michael, Jan A. Botha, Ian Tenney

Keywords Paper

pretrained encoders, elmo, bert, latent learning

0

0

0

0

12:45

03/08/2020

TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP

Nils Rethmeier, Vageesh Kumar Saxena, Isabelle Augenstein

Keywords Paper

0

0

0

0

7:32

08/12/2020

Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs

Zikang Wang, Linjing Li, Daniel Zeng

Keywords Paper

0

0

0

0

12:02

16/11/2020

QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines

Valentina Pyatkin, Ayal Klein, Reut Tsarfaty, Ido Dagan

Keywords Paper

natural understanding, predicting relations, discourse relations, question-and-answer pairs

0

0

0

0

11:22

08/12/2020

Reinforced Multi-task Approach for Multi-hop Question Generation

Deepak Gupta, Hardik Chauhan, Ravi Tej Akella and
Asif Ekbal, Pushpak Bhattacharyya

Keywords Paper

0

0

0

0

11:50

06/12/2021

IRM---when it works and when it doesn't: A test case of natural language inference

Yana Dranker, He He, Yonatan Belinkov

Keywords Paper

robustness, causality, language

0

0

0

0

11:17

06/12/2020

Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge

Alon Talmor, Oyvind Tafjord, Peter Clark and
Yoav Goldberg, Jonathan Berant

Keywords Paper

0

0

0

0

3:28

04/07/2020

NILE : Natural Language Inference with Faithful Natural Language Explanations

Sawan Kumar, Partha Talukdar

Keywords Paper

Natural Inference, NLP tasks, internal making, NLI

0

0

0

1

10:55

01/07/2020

How Self-Attention Improves Rare Class Performance in a Question-Answering Dialogue Agent

Adam Stiff, Qi Song, Eric Fosler-Lussier

Keywords Paper

0

0

0

0

7:55

16/11/2020

End-to-End Slot Alignment and Recognition for Cross-Lingual NLU

Weijia Xu, Batool Haider, Saab Mansour

Keywords Paper

natural understanding, natural, nlu, goal-oriented systems

0

0

0

0

9:46

26/04/2020

Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model

Wenhan Xiong, Jingfei Du, William Yang Wang, Veselin Stoyanov

Keywords Paper

0

0

0

0

5:00

19/04/2021

A study of automatic metrics for the evaluation of natural language explanations

Miruna-Adriana Clinciu, Arash Eshghi, Helen Hastie

Keywords Paper

0

0

0

0

6:10