The coreference under transformation labeling dataset: Entity tracking in procedural texts using event models
We demonstrate that coreference resolution in procedural texts is significantly improved
when performing transformation-based entity linking prior to coreference relation …
when performing transformation-based entity linking prior to coreference relation …
Annotating situated actions in dialogue
C Tam, R Brutti, K Lai, J Pustejovsky - Proceedings of the Fourth …, 2023 - aclanthology.org
Actions are critical for interpreting dialogue: they provide context for demonstratives and
definite descriptions in discourse, and they continually update the common ground. This …
definite descriptions in discourse, and they continually update the common ground. This …
Competence-based question generation
Abstract Models of natural language understanding often rely on question answering and
logical inference benchmark challenges to evaluate the performance of a system. While …
logical inference benchmark challenges to evaluate the performance of a system. While …
Dense Paraphrasing for Textual Enrichment
Understanding inferences and answering questions from text requires more than merely
recovering surface arguments, adjuncts, or strings associated with the query terms. As …
recovering surface arguments, adjuncts, or strings associated with the query terms. As …
Linguistically Conditioned Semantic Textual Similarity
Semantic textual similarity (STS) is a fundamental NLP task that measures the semantic
similarity between a pair of sentences. In order to reduce the inherent ambiguity posed from …
similarity between a pair of sentences. In order to reduce the inherent ambiguity posed from …
Samsung research Poland (SRPOL) at SemEval-2022 task 9: Hybrid question answering using semantic roles
T Dryjański, M Zaleska, B Kuźma… - Proceedings of the …, 2022 - aclanthology.org
In this work we present an overview of our winning system for the R2VQ-Competence-based
Multimodal Question Answering task, with the final exact match score of 92.53%. The task is …
Multimodal Question Answering task, with the final exact match score of 92.53%. The task is …
Hit&qmul at semeval-2022 task 9: Label-enclosed generative question answering (leg-qa)
This paper presents the second place system for the R2VQ: competence-based multimodal
question answering shared task. The purpose of this task is to involve semantic&cooking …
question answering shared task. The purpose of this task is to involve semantic&cooking …
PINGAN_AI at SemEval-2022 Task 9: Recipe knowledge enhanced model applied in Competence-based Multimodal Question Answering
Z Ruan, X Hou, L Jiang - … of the 16th International Workshop on …, 2022 - aclanthology.org
This paper describes our system used in the SemEval-2022 Task 09: R2VQ-Competence-
based Multimodal Question Answering. We propose a knowledge-enhanced model for …
based Multimodal Question Answering. We propose a knowledge-enhanced model for …