Papers by James Martin

7 papers
LiDARR: Linking Document AMRs with Referents Resolvers (2025.acl-demo)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a formalism for semantic representation of natural language text.
Approach: They propose a web tool for semantic annotation at the document level using Abstract Meaning Representation (AMR) it integrates an AMR-to-surface alignment model and a coreference resolution model into the tool .
Outcome: The proposed tool simplifies the creation of knowledge graphs from natural language documents . it integrates an AMR-to-surface alignment model and coreference resolution model .
FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity.
Approach: They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models.
Outcome: The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models.
In Search of the Lost Arch in Dialogue: A Dependency Dialogue Acts Corpus for Multi-Party Dialogues (2025.findings-acl)

Copied to clipboard

Challenge: Understanding speaker intentions remains a challenge in NLP . a number of corpora annotated using theoretical frameworks of dialogue focus on utterance-level labeling of speaker intent, missing wider context, or the rhetorical structure of a dialogue.
Approach: They propose to annotate a corpus of 33 dialogues and over 9,000 utterance units using the Dependency Dialogue Acts framework.
Outcome: The proposed corpus spans four genres of multi-party conversations from different modalities.
Building a Broad Infrastructure for Uniform Meaning Representations (2024.lrec-main)

Copied to clipboard

Challenge: This paper reports the first release of the UMR data set for six languages . it includes annotations for six different languages that vary greatly in terms of their linguistic properties and resource availability.
Approach: They report the first release of the UMR data set for six languages . they describe on-going efforts to enlarge the data set and extend it to other languages - including Navajo, Navájo, and Sanapaná .
Outcome: The first release of the UMR data set includes annotations for six languages . the language dataset is available for free and can be extended to other languages if needed .
Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasing (2024.acl-short)

Copied to clipboard

Challenge: Existing methods for Cross-Document Event Coreference Resolution (CDEC) are biased towards lexical similarities, limiting a crucial avenue of research in event comprehension.
Approach: They propose a lexically rich variant of Event Coref Bank Plus (ECB+) for CDEC on symbolic and metaphoric language.
Outcome: The proposed method avoids the reannotation of expensive coreference links on symbolic and metaphoric language.
Discovering Language Model Behaviors with Model-Written Evaluations (2023.findings-acl)

Copied to clipboard

Challenge: Prior work creates evaluations with crowdwork or existing data sources, which are not always available.
Approach: They generate evaluations automatically with language models (LMs) using crowdwork or existing data sources to find out how they behave .
Outcome: The results show that large LMs repeat back a dialog user’s preferred answer and express greater desire to pursue concerning goals like resource acquisition and goal preservation.
On the Role of Semantic Proto-roles in Semantic Analysis: What do LLMs know about agency? (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on large language models (LLMs) have not explored their capacity to reason over event structure . et al., 2015, 142: e007-e0027; eugene, 1985; Weiner, 1995; saab, 1985) focus on the role of large language model in decision-making .
Approach: They propose to characterize agents via properties such as "instigation" and "volition" they also examine whether incorporating semantic proto-role labeling context improves SRL performance .
Outcome: The proposed model improves in a zero-shot setting by incorporating proto-role labeling context . the results support previous work showing that LLMs underperform human annotators in complex semantic analysis.

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