Papers by A Pranav
Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets (2024.lrec-main)
Copied to clipboard
| Challenge: | Distributional Semantics has undergone significant changes with the introduction of contextualized distributional models. |
| Approach: | They compare static and contextual distributional models for Mandarin Chinese . they find that static models are stronger for some of the classical tasks . |
| Outcome: | The proposed models perform better on some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and categorization of words into abstract semantic classes. |
2kenize: Tying Subword Sequences for Chinese Script Conversion (2020.acl-main)
Copied to clipboard
| Challenge: | Traditional Chinese character conversion is a common step in Chinese NLP but current methods do not take into account that a simplified Chinese character can correspond to multiple traditional characters. |
| Approach: | They propose a model that can disambiguate between mappings and convert between the two scripts by using subword segmentation and two language models. |
| Outcome: | The proposed model outperforms previous Chinese Character conversion approaches by 6 points in accuracy. |
Glitter: A Multi-Sentence, Multi-Reference Benchmark for Gender-Fair German Machine Translation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing MT models are limited in size and often consist of single sentences or single gender-fair formulation types. |
| Approach: | They propose a benchmark for machine translation that features extended passages with professional translations implementing gender-fair alternatives: neutral rewording, typographical solutions and neologistic forms. |
| Outcome: | The proposed benchmark features extended passages with professional translations implementing three gender-fair alternatives: neutral rewording, typographical solutions (gender star), and neologistic forms (-ens forms). |
The Double Bind: Revisiting Preprinting and Peer Review Two Years After the Removal of the ACL Anonymity Period (2026.findings-acl)
Copied to clipboard
| Challenge: | ACL removed the anonymity period for conference submissions in February 2024 . |
| Approach: | They track preprinting trends for 47k publications and analyze 1.9k peer reviews . they suggest improving visibility and investing in diversity initiatives . |
| Outcome: | The proposed anonymity period was removed in 2024, but it was ineffective for underrepresented researchers . the authors suggest addressing D&I issues rather than implementing anonymity policies. |
Alignment Analysis of Sequential Segmentation of Lexicons to Improve Automatic Cognate Detection (P18-3)
Copied to clipboard
| Challenge: | Existing studies on cognate detection only distinguish between a pair of words whether they are cognates or non-cognates. |
| Approach: | They propose to incorporate ranking functions into search engine ranking functions . they also propose to use graphical error modelling to calculate morphological shifts . |
| Outcome: | The proposed methods give better results than competing baselines, the authors show . they show that language modelling based retrieval functions with positional tokenization and error modelling give better outcomes . |