no code implementations • COLING 2022 • Sagnik Ray Choudhury, Anna Rogers, Isabelle Augenstein
Two of the most fundamental issues in Natural Language Understanding (NLU) at present are: (a) how it can established whether deep learning-based models score highly on NLU benchmarks for the ”right” reasons; and (b) what those reasons would even be.
no code implementations • COLING 2022 • Sagnik Ray Choudhury, Nikita Bhutani, Isabelle Augenstein
We find that EP test results do not change significantly when the fine-tuned model performs well or in adversarial situations where the model is forced to learn wrong correlations.
1 code implementation • 20 Oct 2023 • Sagnik Ray Choudhury, Pepa Atanasova, Isabelle Augenstein
Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI).
1 code implementation • 20 Oct 2023 • Sagnik Ray Choudhury, Jushaan Kalra
However, a large body of research claims that the tests necessarily do not measure the LLM's capacity to encode knowledge, but rather reflect the classifiers' ability to learn the problem.
no code implementations • 15 Sep 2022 • Sagnik Ray Choudhury, Anna Rogers, Isabelle Augenstein
Two of the most fundamental challenges in Natural Language Understanding (NLU) at present are: (a) how to establish whether deep learning-based models score highly on NLU benchmarks for the 'right' reasons; and (b) to understand what those reasons would even be.
no code implementations • 15 Sep 2021 • Sagnik Ray Choudhury, Nikita Bhutani, Isabelle Augenstein
We find that EP test results do not change significantly when the fine-tuned model performs well or in adversarial situations where the model is forced to learn wrong correlations.
1 code implementation • NAACL 2021 • Brian Lester, Sagnik Ray Choudhury, Rashmi Prasad, Srinivas Bangalore
Complex natural language understanding modules in dialog systems have a richer understanding of user utterances, and thus are critical in providing a better user experience.
1 code implementation • 15 Apr 2021 • Karolina Stańczak, Sagnik Ray Choudhury, Tiago Pimentel, Ryan Cotterell, Isabelle Augenstein
Recent research has demonstrated that large pre-trained language models reflect societal biases expressed in natural language.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Brian Lester, Daniel Pressel, Amy Hemmeter, Sagnik Ray Choudhury, Srinivas Bangalore
Current state-of-the-art models for named entity recognition (NER) are neural models with a conditional random field (CRF) as the final layer.
1 code implementation • 30 Sep 2020 • Brian Lester, Daniel Pressel, Amy Hemmeter, Sagnik Ray Choudhury, Srinivas Bangalore
Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.
1 code implementation • 5 Jan 2020 • Brian Lester, Daniel Pressel, Amy Hemmeter, Sagnik Ray Choudhury
The CRF layer is used to facilitate global coherence between labels, and the contextual embeddings provide a better representation of words in context.
1 code implementation • WS 2018 • Daniel Pressel, Sagnik Ray Choudhury, Brian Lester, Yanjie Zhao, Matt Barta
We introduce Baseline: a library for reproducible deep learning research and fast model development for NLP.
no code implementations • 4 Jan 2018 • Agnese Chiatti, Mu Jung Cho, Anupriya Gagneja, Xiao Yang, Miriam Brinberg, Katie Roehrick, Sagnik Ray Choudhury, Nilam Ram, Byron Reeves, C. Lee Giles
Effective and efficient Information Extraction and Retrieval from digital screenshots is a crucial prerequisite to successful use of screen data.
no code implementations • 25 Jan 2014 • Shibamouli Lahiri, Sagnik Ray Choudhury, Cornelia Caragea
Keyword and keyphrase extraction is an important problem in natural language processing, with applications ranging from summarization to semantic search to document clustering.