Portrait de Aishik Chakraborty n'est pas disponible

Aishik Chakraborty

Doctorat - McGill
Superviseur⋅e principal⋅e
Jackie Cheung
Sujets de recherche
Traitement du langage naturel

Publications

Systematic Generalization by Finetuning? Analyzing Pretrained Language Models Using Constituency Tests
Aishik Chakraborty
Jackie Cheung
Timothy O'Donnell
Constituents are groups of words that behave as a syntactic unit. Many linguistic phenomena (e.g., question formation, diathesis alternation… (voir plus)s) require the manipulation and rearrangement of constituents in a sentence. In this paper, we investigate how different finetuning setups affect the ability of pretrained sequence-to-sequence language models such as BART and T5 to replicate constituency tests — transformations that involve manipulating constituents in a sentence. We design multiple evaluation settings by varying the combinations of constituency tests and sentence types that a model is exposed to during finetuning. We show that models can replicate a linguistic transformation on a specific type of sentence that they saw during finetuning, but performance degrades substantially in other settings, showing a lack of systematic generalization. These results suggest that models often learn to manipulate sentences at a surface level unrelated to the constituent-level syntactic structure, for example by copying the first word of a sentence. These results may partially explain the brittleness of pretrained language models in downstream tasks.
2023-12-01
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP (publié)
doi.org
Learning Lexical Subspaces in a Distributional Vector Space
Kushal Arora
Aishik Chakraborty
Jackie Cheung
Abstract In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about… (voir plus) lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relation should hold. Our framework can handle symmetric attract and repel relations (e.g., synonymy and antonymy, respectively), as well as asymmetric relations (e.g., hypernymy and meronomy). In a suite of intrinsic benchmarks, we show that our model outperforms previous approaches on relatedness tasks and on hypernymy classification and detection, while being competitive on word similarity tasks. It also outperforms previous systems on extrinsic classification tasks that benefit from exploiting lexical relational cues. We perform a series of analyses to understand the behaviors of our model.1 Code available at https://github.com/aishikchakraborty/LexSub.
2020-12-01
Transactions of the Association for Computational Linguistics (publié)
doi.org