@inproceedings{zhang-etal-2022-label-definitions,
    title = "Label Definitions Improve Semantic Role Labeling",
    author = "Zhang, Li  and
      Jindal, Ishan  and
      Li, Yunyao",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.411",
    pages = "5613--5620",
    abstract = "Argument classification is at the core of Semantic Role Labeling. Given a sentence and the predicate, a semantic role label is assigned to each argument of the predicate. While semantic roles come with meaningful definitions, existing work has treated them as symbolic. Learning symbolic labels usually requires ample training data, which is frequently unavailable due to the cost of annotation. We instead propose to retrieve and leverage the definitions of these labels from the annotation guidelines. For example, the verb predicate {``}work{''} has arguments defined as {``}worker{''}, {``}job{''}, {``}employer{''}, etc. Our model achieves state-of-the-art performance on the CoNLL09 dataset injected with label definitions given the predicate senses. The performance improvement is even more pronounced in low-resource settings when training data is scarce.",
}
          

@inproceedings{lyu-etal-2022-favorite,
    title = "Is {``}My Favorite New Movie{''} My Favorite Movie? Probing the Understanding of Recursive Noun Phrases",
    author = "Lyu, Qing  and
      Hua, Zheng  and
      Li, Daoxin  and
      Zhang, Li  and
      Apidianaki, Marianna  and
      Callison-Burch, Chris",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.388",
    pages = "5286--5302",
    abstract = "Recursive noun phrases (NPs) have interesting semantic properties. For example, {``}my favorite new movie{''} is not necessarily my favorite movie, whereas {``}my new favorite movie{''} is. This is common sense to humans, yet it is unknown whether language models have such knowledge. We introduce the Recursive Noun Phrase Challenge (RNPC), a dataset of three textual inference tasks involving textual entailment and event plausibility comparison, precisely targeting the understanding of recursive NPs. When evaluated on RNPC, state-of-the-art Transformer models only perform around chance. Still, we show that such knowledge is learnable with appropriate data. We further probe the models for relevant linguistic features that can be learned from our tasks, including modifier semantic category and modifier scope. Finally, models trained on RNPC achieve strong zero-shot performance on an extrinsic Harm Detection evaluation task, showing the usefulness of the understanding of recursive NPs in downstream applications.",
}
        

@inproceedings{zhang-etal-2020-small,
title = "Small but Mighty: New Benchmarks for Split and Rephrase",
author = "Zhang, Li  and
  Zhu, Huaiyu  and
  Brahma, Siddhartha  and
  Li, Yunyao",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.91",
pages = "1198--1205",
}      
        

@inproceedings{zhang-etal-2019-multi,
title = "Multi-Label Transfer Learning for Multi-Relational Semantic Similarity",
author = "Zhang, Li  and
  Wilson, Steven  and
  Mihalcea, Rada",
booktitle = "Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*{SEM} 2019)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/S19-1005",
pages = "44--50",
abstract = "Multi-relational semantic similarity datasets define the semantic relations between two short texts in multiple ways, e.g., similarity, relatedness, and so on. Yet, all the systems to date designed to capture such relations target one relation at a time. We propose a multi-label transfer learning approach based on LSTM to make predictions for several relations simultaneously and aggregate the losses to update the parameters. This multi-label regression approach jointly learns the information provided by the multiple relations, rather than treating them as separate tasks. Not only does this approach outperform the single-task approach and the traditional multi-task learning approach, but it also achieves state-of-the-art performance on all but one relation of the Human Activity Phrase dataset.",
}
        

@misc{zhang2018direct,
title={Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity},
author={Li Zhang and Steven R. Wilson and Rada Mihalcea},
year={2018},
eprint={1804.07835},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
        

@InProceedings{acl18sql,
  author    = {Catherine Finegan-Dollak\*  and  Jonathan K. Kummerfeld\*  and  Li Zhang  and  Karthik Ramanathan  and  Sesh Sadasivam  and  Rui Zhang  and  Dragomir Radev},
  title     = {Improving Text-to-SQL Evaluation Methodology},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  shortvenue = {ACL},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Victoria, Australia},
  pages     = {351--360},
  abstract  = {To be informative, an evaluation must measure how well systems generalize to realistic unseen data. We identify limitations of and propose improvements to current evaluations of text-to-SQL systems. First, we compare human-generated and automatically generated questions, characterizing properties of queries necessary for real-world applications. To facilitate evaluation on multiple datasets, we release standardized and improved versions of seven existing datasets and one new text-to-SQL dataset. Second, we show that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries; therefore, we propose a complementary dataset split for evaluation of future work. Finally, we demonstrate how the common practice of anonymizing variables during evaluation removes an important challenge of the task. Our observations highlight key difficulties, and our methodology enables effective measurement of future development.},
  url       = {http://aclweb.org/anthology/P18-1033},
  software  = {https://github.com/jkkummerfeld/text2sql-data},
  data      = {https://github.com/jkkummerfeld/text2sql-data},
}
          

@article{Burdick2018EntityAE,
title={Entity and Event Extraction from Scratch Using Minimal Training Data},
author={Laura Burdick and Steven R. Wilson and Oana Ignat and Charles F Welch and Li Zhang and Mingzhe Wang and Jia Deng and Rada Mihalcea},
journal={Theory and Applications of Categories},
year={2018}
}