Papers by Olga Zamaraeva

7 papers
More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs (2026.acl-long)

Copied to clipboard

Challenge: a growing number of studies compare LLMs with human-authored text . diversity is unclear, but it is important to understand what makes human and machine writing distinct .
Approach: They compare syntactic properties of AI-generated and human-authored English news texts . they use the Head-Driven Phrase Structure Grammar and the English Resource Grammar .
Outcome: The proposed model differs from human-authored English news text in two years.
Comparing LLM-generated and human-authored news text using formal syntactic theory (2025.acl-long)

Copied to clipboard

Challenge: a systematic comparison of LLM-generated and human-authored texts is a topic of growing interest in the field of natural language processing.
Approach: They compare LLM-generated and human-authored New York Times texts using a formal syntactic theory . they use a broad-coverage English resource grammar to analyze the texts .
Outcome: The proposed comparisons reveal systematic differences between human and LLM-generated texts . the authors hope the results will lead to further discoveries about grammatical properties of LLMs .
Spanish Resource Grammar Version 2023 (2024.lrec-main)

Copied to clipboard

Challenge: Using the Freeling morphological analyzer, we encode a strict notion of grammaticality in the Spanish resource grammar.
Approach: They propose to use the HPSG formalism to encode a Spanish resource grammar with a manually verified treebank of 2,291 sentences.
Outcome: The proposed grammars encode a complex set of hypotheses about syntax and a strict notion of grammaticality making them a resource for natural language processing applications in computer-assisted language learning.
Revisiting Supertagging for faster HPSG parsing (2024.emnlp-main)

Copied to clipboard

Challenge: a new supertagger for HPSG-based treebanks is used to improve parsing speed and accuracy.
Approach: They propose to integrate the best supertagger into an HPSG-based parser and compare it to an existing system.
Outcome: The proposed system achieves 97.26% accuracy on 950 sentences from WSJ23 and 93.88% on the out-of-domain technical essay The Cathedral and the Bazaar.
Improving Feature Extraction for Pathology Reports with Precise Negation Scope Detection (C18-1)

Copied to clipboard

Challenge: a broad coverage, linguistically precise English resource grammar detects negation scope in sentences taken from pathology reports.
Approach: They use a linguistically precise English resource grammar to detect negation scope in pathology reports.
Outcome: The proposed approach improves classification of cancer reports with respect to laterality compared with NegEx.
Visualizing Inferred Morphotactic Systems (N19-4)

Copied to clipboard

Challenge: a web-based system facilitates the exploration of complex morphological patterns found in morphology rich languages.
Approach: They propose a web-based system that facilitates the exploration of complex morphological patterns found in morphology rich languages.
Outcome: The proposed system can be used to explore morphological patterns in morphology rich languages.
Clausal Modifiers in the Grammar Matrix (C18-1)

Copied to clipboard

Challenge: clausal modifiers are a common feature of grammars that are not considered in development.
Approach: They propose to extend the coverage of an existing grammar customization system to clausal modifiers, also referred to as adverbial clauses.
Outcome: The proposed grammars achieve 88.4% coverage and 1.5% overgeneration on five languages not considered in development.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations