Publications

Filter by type:

. Unipelt: A unified framework for parameter-efficient language model tuning. ACL 2022, 2022.

PDF

. Quantifying Adaptability in Pre-trained Language Models with 500 Tasks. arXiv preprint arXiv:2112.03204, 2021.

PDF

. Sparse Distillation: Speeding Up Text Classification by Using Bigger Models. arXiv preprint arXiv:2110.08536, 2021.

PDF

. A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision. arXiv preprint arXiv:2112.13884, 2021.

PDF

. On the influence of masking policies in intermediate pre-training. EMNLP 2021, 2021.

PDF

. Towards few-shot fact-checking via perplexity. NAACL 2021, 2021.

PDF

. On unifying misinformation detection. NAACL 2021, 2021.

PDF

. Linformer: Self-Attention with Linear Complexity. arXiv preprint arXiv:2006.04768, 2020.

PDF

. To Pretrain or Not to Pretrain: Examining the Benefits of Pretrainng on Resource Rich Tasks. The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 2020.

PDF

. Language Models as Fact Checkers?. Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER), 2020.

PDF

. Keeping Notes: Conditional Natural Language Generation with a Scratchpad Encoder. The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), 2019.

PDF

. Adversarial Training for Community Question Answer Selection Based on Multi-scale Matching. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 2019.

PDF

. Characterizing and Supporting Question Answering in Human-to-Human Communication. The 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2018.

PDF

. Identifying Task Boundaries in Digital Assistants. WWW 2018 (The Web Conference), 2018.

PDF

. Actionable Email Intent Modeling with Reparametrized RNNs. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2018.

PDF

. Building Natural Language Interfaces to Web APIs. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM), 2017.

PDF

. User Interaction Sequences for Search Satisfaction Prediction. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017.

PDF

. Identifying Earmarks in Congressional Bills. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016.

PDF

. Learning to Account for Good Abandonment in Search Success Metrics. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 2016.

PDF

. Learning to identify relevant studies for systematic reviews using random forest and external information. Machine Learning 102.3 (2016): 465-482, 2016.

PDF

. Chemical entity extraction using CRF and an ensemble of extractors. Journal of cheminformatics 7 (1), S12, 2015.

PDF

. The number of scholarly documents on the public web. PloS one 9 (5), e93949, 2014.

PDF