Natural Language Inference from Multiple Premises
By Alice Lai, Yonatan Bisk, Julia Hockenmaier. 2017
63 citations recorded by the source corpus.
We define a novel textual entailment task that requires inference over multiple premise sentences. We present a new dataset for this task that minimizes trivial lexical inferences, emphasizes knowledge of everyday events, and presents a more challenging setting for textual entailment. We evaluate several strong neural baselines and analyze how the multiple premise task differs from standard textual entailment.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Artificial Intelligence
- Yejin Choi
- Ashish Sabharwal
- Mohit Bansal
- Peter Clark
- Hannaneh Hajishirzi
- Tushar Khot
- Kyle Richardson
- Luke S. Zettlemoyer
In Computer Vision and Pattern Recognition
- Yejin Choi
- Peter Clark
- Ashish Sabharwal
- Mohit Bansal
- Tushar Khot
- Hannaneh Hajishirzi
- Luc Van Gool
- Rowan Zellers
In Natural Language Processing
- Yejin Choi
- Ashish Sabharwal
- Peter Clark
- Mohit Bansal
- Tushar Khot
- Kyle Richardson
- Jonathan Berant
- Hannaneh Hajishirzi
Citations in the corpus
- SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (2018, background): “Entailment NLI There has been a long history of NLI benchmarks focusing on linguistic entailment (Cooper et al., 1996; Dagan et al., 2006; Marelli et al., 2014; Bowman et al., 2015; Lai et al., 2017; Williams et al., 2018).”
- Hypothesis Only Baselines in Natural Language Inference (2018, background): “In contrast, in MPE, scores are much closer to a uniform distribution of p ( l | w ) across labels.”
- Explaining Answers with Entailment Trees (2021, methodology): “Our approach is to generate explanations in the form of multistep entailment trees , such as shown in Figure 1, made up of individual, multi-premise textual entailment (TE) steps (Dagan et al., 2013; Lai et al., 2017).”
- Transforming Question Answering Datasets Into Natural Language Inference Datasets (2018, background): “The questions vary greatly in terms of their type and difficulty: questions in QAMR hinge on selecting the right arguments within a single sentence, while questions in RACE, written for middle-and high-schoolers, require holistic reasoning about the text (e.g.”
- Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (2018, background): “A plethora of new natural language inference (NLI)1 datasets has been created in recent years (Bowman et al., 2015; Williams et al., 2017; Lai et al., 2017; Khot et al., 2018).”
- Temporal Reasoning on Implicit Events from Distant Supervision (2020, background): “Such tests in TRACIE take the form of multi-premise textual entailment (TE) (Lai et al., 2017).”
- Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text Summarization (2021, background): “The QuestionAnswering (QA) task can easily be cast into the NLI form, and QA datasets (Rajpurkar et al., 2016; Lai et al., 2017b; Khashabi et al., 2018; Sun et al., 2019; Huang et al., 2019) encompass a variety of semantic phenomena that only occur in longer (con)texts.”
- Natural Language Inference in Context - Investigating Contextual Reasoning over Long Texts (2020, methodology): “The multiple premise entailment (MPE) task (Lai, Bisk, and Hockenmaier 2017) is a variant of the entailment task where each hypothesis is paired with a set of independently written premise sentences.”
- Robustness Gym: Unifying the NLP Evaluation Landscape (2021, unknown): “, 2018), MPE (Lai et al., 2017), EQUATE (Ravichander et al.”