Share This Author
Social Bias Frames: Reasoning about Social and Power Implications of Language
- Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah A. Smith, Yejin Choi
- PsychologyAnnual Meeting of the Association for…
- 10 November 2019
It is found that while state-of-the-art neural models are effective at high-level categorization of whether a given statement projects unwanted social bias, they are not effective at spelling out more detailed explanations in terms of Social Bias Frames.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.
Automatic Article Commenting: the Task and Dataset
A large-scale Chinese dataset with millions of real comments and a human-annotated subset characterizing the comments’ varying quality is introduced, and automatic metrics that generalize a broad set of popular reference-based metrics and exhibit greatly improved correlations with human evaluations are developed.
Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
- Lianhui Qin, Michel Galley, Jianfeng Gao
- Computer ScienceAnnual Meeting of the Association for…
- 1 June 2019
A new end-to-end approach to contentful neural conversation that jointly models response generation and on-demand machine reading is presented, allowing for more focused integration of external knowledge than has been possible in prior approaches.
Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification
This work develops an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator, and achieves state-of-the-art performance on the PDTB benchmark.
Counterfactual Story Reasoning and Generation
- Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin Choi
- Computer ScienceEMNLP
- 9 September 2019
This paper proposes Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given counterfactually event.
A Stacking Gated Neural Architecture for Implicit Discourse Relation Classification
A stacking neural network model is proposed to solve the classification problem in which a convolutional neural network is utilized for sentence modeling and a collaborative gated neural network (CGNN) is proposed for feature transformation.
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
- Lianhui Qin, Vered Shwartz, Yejin Choi
- Computer ScienceConference on Empirical Methods in Natural…
- 12 October 2020
This paper proposes DeLorean, a new unsupervised decoding algorithm that can flexibly incorporate both the past and future contexts using only off-the-shelf, left-to-right language models and no supervision.
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
This paper presents Energy-based Constrained Decoding with Langevin Dynamics (C OLD), a decoding framework which describes constrained generation as specifying constraints through an energy function, then performing differentiable reasoning over the constraints through gradient-based sampling.
Implicit Discourse Relation Recognition with Context-aware Character-enhanced Embeddings
This paper proposes a neural model utilizing context-aware character-enhanced embeddings to alleviate the drawbacks of the current word level representation and obtains state-of-the-art results.