Канал: Zining Zhu

A State-Vector Framework for Dataset Effects

A State-Vector Framework for Dataset Effects

Situated Natural Language Explanation (ACL NLRSE)

Situated Natural Language Explanation (ACL NLRSE)

Some methods to make NLP interpretable

Some methods to make NLP interpretable

A tale of GPT models

A tale of GPT models

EMNLP 2022: Predicting Fine-tuning Performance with Probing (2-min version)

EMNLP 2022: Predicting Fine-tuning Performance with Probing (2-min version)

OOD-Probe: A Neural Interpretation of Out-of-Domain Generalizations

OOD-Probe: A Neural Interpretation of Out-of-Domain Generalizations

Predicting fine-tuning performance with probing

Predicting fine-tuning performance with probing

On the data requirements of probing

On the data requirements of probing

Talk 7: Datasets

Talk 7: Datasets

Talk 6: Shortcuts and Underspecification

Talk 6: Shortcuts and Underspecification

Talk 5: Behavioral Tests

Talk 5: Behavioral Tests

Talk 4: Probing

Talk 4: Probing

Talk 3: Geometry of representations

Talk 3: Geometry of representations

Talk 2: Some explainable AI methods

Talk 2: Some explainable AI methods

Talk 1: What is NLP; Quick overview on some NLP models

Talk 1: What is NLP; Quick overview on some NLP models

Talk 0: Intro to Interpretable-NLP

Talk 0: Intro to Interpretable-NLP

(Kim et al., 2020) Interpretation of NLP models through input marginalization

(Kim et al., 2020) Interpretation of NLP models through input marginalization

(Sanh et al., 2020) Learning from others' mistakes

(Sanh et al., 2020) Learning from others' mistakes

(Alvarez-Melis and Jaakkola, 2017) black-box explaination for Seq2Seq

(Alvarez-Melis and Jaakkola, 2017) black-box explaination for Seq2Seq

(Carton et al., 2020) Evaluating and characterizing human rationales

(Carton et al., 2020) Evaluating and characterizing human rationales

(Pimentel et al., '20) Speakers Fill Lexical Semantic Gaps with Context

(Pimentel et al., '20) Speakers Fill Lexical Semantic Gaps with Context

(Zhang et al., 2017) Understanding deep learning requires rethinking generalization

(Zhang et al., 2017) Understanding deep learning requires rethinking generalization

(Zhu and Rudzicz '20) An information theoretic view on selecting linguistic probes

(Zhu and Rudzicz '20) An information theoretic view on selecting linguistic probes

Examining the rhetorical capacities of neural language models

Examining the rhetorical capacities of neural language models

(Chrupala and Alishahi '19) Correlating Neural and Symbolic Representations of Language

(Chrupala and Alishahi '19) Correlating Neural and Symbolic Representations of Language

(Bender and Koller '20) Climbing towards NLU

(Bender and Koller '20) Climbing towards NLU

(Glavaš and Vulić, '20) Is Supervised Syntactic Parsing Beneficial for Language Understanding?

(Glavaš and Vulić, '20) Is Supervised Syntactic Parsing Beneficial for Language Understanding?

(Niven and Kao '19) Probing Neural Network Comprehension of Natural Language Arguments

(Niven and Kao '19) Probing Neural Network Comprehension of Natural Language Arguments

(Ethayarajh, 2019) How Contextual are Contextualized Word Representations?

(Ethayarajh, 2019) How Contextual are Contextualized Word Representations?