Summarization
- LQSum, document summarization with latent queries, described in Xu and Lapata (TACL, 2022)
- Multimodal movie summarization, described in Papalampidi et al., (AAAI, 2021)
- SUMMER, CSI episodes summarizer, described in Papalampidi et al., (ACL 2020)
- Crosslingual Summarizer, described in Perez and Lapata (EMNLP, 2021)
- Multidocument Summarizer, described in Perez and Lapata (JAIR, 2021)
- MARGE, query-focused summarizer, described in Xu and Lapata (ACL-IJCNLP, 2021)
- AceSum, aspect controllable opinion summarizer, described in Amplayo et al. (EMNLP 2021).
- PlanSum, unsupervised opinion summarizer with content planning, described in Amplayo et al. (AAAI 2021)
- QuerySum, coarse-to-fine multidocument summarizer, described in Xu and Lapata (EMNLP 2020).
- DenoiseSum, unsupervised opinion summarizer with noising and denoising, described in Amplayo and Lapata (ACL 2020)
- Opinion summarization system with quantized transformers described in Angelidis et al. (TACL, 2020).
- BertSum summarization system, described in Liu and Lapata (EMNLP, 2019).
- Hierarchical Transformer-based multidocument summarizer described in Liu and Lapata (ACL, 2019).
- Template-based multidocument summarizer described in Perez-Beltrachini et al. (ACL, 2019).
- PACSum, unsupervised summarizer described in Zheng and Lapata (ACL, 2019).
- Weakly supervised opinion summarizer in Angelidis and Lapata (EMNLP, 2018).
- XSum, Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization, (EMNLP, 2018).
- Refresh, Ranking Sentences for Extractive Summarisation with Reinforcement Learning (NAACL, 2018).
- Neural Summarizer, code for summarization system described in Cheng and Lapata (ACL, 2016).
Generation
- Data-to-text Generator with Variational Sequential Planning, described in Puduppully et al. (TACL, 2022)
- HRQ-VAE, hierarchical sketch induction for paraphrase generation, described in Hosking et al. (ACL 2022)
- Data-to-text Generator with macro-planning, described in Puduppully and Lapata (TACL, 2021)
- Separator, paraphrase generator, described in Hosking and Lapata (ACL, 2021)
- Data-to-text Generator with entity modeling (RotoWire, ACL, 2019).
- RotoWire Generator, described in Puduppully et al. (AAAI, 2019).
- Data-to-text Generator, described in Perez-Beltrachini and Mirella Lapata (WikiBio, NAACL, 2018)
- Dress, sentence simplification model trained with reinforcement learning (EMNLP, 2017)
- Chinese Poem Generator, described in Zhang and Lapata (EMNLP, 2014).
- Concept-to-text Generator, described in Konstas and Lapata (JAIR, 2013).
- T3 Tree Transducer toolkit, described in Cohn and Lapata (ACM Transactions on Intelligent Systems and Technology, 2013).
Semantic Parsing
- Dangle, semantic parser for compositional generalization described in Zheng and Lapata (ACL 2022).
- ZX-Parse, zero-shot cross-lingual parser described in Serborne and Lapata (ACL 2022).
- Cross-lingual semantic parser described in Sherborne et al., (Findings of the EMNLP 2020).
- TreeDRS parser, described in Liu et al. (ACL, 2019).
- Discourse Representation Theory (DRT) parser described in Liu et al. (ACL, 2018).
- MATE, MultiSeed Aspect Extractor Model (EMNLP, 2018)
- SCANNER, neural semantic parser described in Cheng et al (ACL, 2017).
- UDepLambda, framework to convert universal dependencies to logical form (EMNLP, 2017).
- DepLambda, code for transforming dependency structures to logical form (TACL, 2016).
- Lang2Logic, semantic parsers descibed in Dong and Lapata (ACL, 2016).
- GraphParser, (ungrounded) semantic parser described in Reddy et al. (TACL, 2014).
Semantic Role Labeling
- Semi-supervised SRL with cross-view training in Cai and Lapata (EMNLP, 2019).
- Syntax-aware semantic role labeler in Cai and Lapata (TACL, 2019).
- PathLSTM, semantic role labeling model described in Roth and Lapata (ACL, 2016).
- Mateplus, semantic role labeling model described in Roth and Lapata (TACL, 2015).
Representation Learning
- Weakly supervised domain detection in Xu and Lapata (TACL, 2019).
- MILNET, multiple instance learning networks for fine-grained sentiment analysis, described in Angelidis and Lapata (TACL, 2018).
- Generative parser, described in Cheng et al (ACL, 2017).
- DenSe parser, code for neural dependency parser described in Zhang et al. (EACL, 2017).
- Long short term memory networks, code for LSTMN described in Cheng et al. (EMNLP, 2016).
- TreeLSTM, code for models described in Zhang et al. (NAACL, 2016).
- Dependency Vectors, software for semantic spaces described in Pado and Lapata (CL, 2007).