Guided Generation of Cause and Effect

By Zhongyang Li, Xiao Ding, Ting-Wei Liu, J. Edward Hu, Benjamin Van Durme. 2020

89 citations recorded by the source corpus.

We present a conditional text generation framework that posits sentential expressions of possible causes and effects. This framework depends on two novel resources we develop in the course of this work: a very large-scale collection of English sentences expressing causal patterns (CausalBank); and a refinement over previous work on constructing large lexical causal knowledge graphs (Cause Effect Graph). Further, we extend prior work in lexically-constrained decoding to support disjunctive positive constraints. Human assessment conﬁrms that our approach gives high-quality and diverse outputs. Finally, we use CausalBank to perform continued training of an encoder supporting a recent state-of-the-art model for causal reasoning, leading to a 3-point improvement on the COPA challenge set, with no change in model architecture.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models (2021, methodology): “Most prior art for automatic knowledge graph construction extracts knowledge from raw text (Bhakthavatsalam et al., 2020; Zhang et al., 2020a; Zhou et al., 2020; Zhang et al., 2020b; Li et al., 2020).”
Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, methodology): “Some other commonsense knowledge graphs, such as TransOMCS [75] and CausalBanK [76] are automatically constructed to provide commonsense knowledge.”
COD3S: Diverse Generation with Discrete Semantic Signatures (2020, methodology): “Table 4 shows results of automatic diversity evaluation on the in-distribution training sample from CausalBank following Li et al. (2020).”