Natural language inference.

By Yorick Wilks. 1973

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

A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference (2017, background): “These syntactic differences suggest that alignment-based NLI models (like, for example, that of MacCartney, 2009) are unlikely to succeed.”
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference (2019, background): “MacCartney and Manning (2009) also discuss the implicational behavior of these various types of words within NLI.”
Revealing the Importance of Semantic Retrieval for Machine Reading at Scale (2019, methodology): “Fact Veriﬁcation: Following Thorne et al. (2018), we formulate downstream fact veriﬁcation as the 3-way natural language inference (NLI) classiﬁcation problem (MacCartney and Manning, 2009; Bowman et al., 2015) and train the model with 3-way cross entropy loss.”
ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, background): “Figure 7 shows three instances of incorrect proofs from ProoFVer, which highlight some of the well known limitations in natural logic (Karttunen, 2015; MacCartney, 2009).”
Transformers as Soft Reasoners over Language (2020, background): “In particular, NLI allows for unsupported inferences that “a person would typically infer” [Dagan et al. , 2013], while we have used a precise model of inference in which all of a rule’s conditions need to be proven true in order for the conclusion to follow.”
Hypothesis Only Baselines in Natural Language Inference (2018, methodology): “For example, MacCartney (2009) used a simple bag-of-words model to evaluate early iterations of Recognizing Textual En-tailment (RTE) challenge sets.”
Enhanced LSTM for Natural Language Inference (2016, methodology): “…is concerned with determining whether a natural-language hypothesis h can be inferred from a premise p , as depicted in the following example from MacCartney (2009), where the hypothesis is regarded to be entailed from the premise. p: Several airlines polled saw costs grow more than expected,…”
Stress Test Evaluation for Natural Language Inference (2018, methodology): “…methods (Glickman et al., 2005; Harabagiu and Hickl, 2006; Romano et al., 2006; Dagan et al., 2006; Giampiccolo et al., 2007; Dagan et al., 2010; MacCartney, 2009; Zanzotto et al., 2006; Malakasiotis and Androutsopoulos, 2007; Haghighi et al., 2005; Angeli and Manning, 2014). de Marneffe et al.…”
Learning Natural Language Inference with LSTM (2015, methodology): “Because inference is essentially a logic problem, methods based on formal logic (Clark and Harrison, 2009) or natural logic (MacCartney, 2009) have also been proposed.”
Natural Language Inference by Tree-Based Convolution and Heuristic Matching (2015, background): “Recognizing entailment and contradiction be-tween two sentences (called a premise and a hypothesis ) is known as natural language inference (NLI) in MacCartney (2009).”
Evaluating Compositionality in Sentence Embeddings (2018, background): “In this paper, we explore minimal cases in a “natural language inference” (NLI, MacCartney (2009); Dagan et al. (2006)) task that cannot be solved without taking compositional information into account and thus develop a stringent test for compositionality.”
Question Answering via Integer Programming over Semi-Structured Knowledge (2016, background): “Recent work on Natural Logic [ Angeli and Manning, 2014; MacCartney, 2009 ] has extended RTE to account for the logical structure within language.”
NaturalLI: Natural Logic Inference for Common Sense Reasoning (2014, methodology): “A similar observation is noted in MacCartney (2009), where prematurely collapsing to # occasionally misses inferences.”
The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations (2017, background): “For related discussion of entailment and natural language understanding see Chier-chia and McConnell-Ginet (1991), Dagan et al. (2006), and MacCartney (2009).”
PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification (2015, methodology): “We automatically annotate each paraphrase rule in PPDB with an explicit entailment relation based on natural logic (MacCartney, 2009).”
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters (2021, background): “The task of natural language inference is to determine the logical relationship between two text sequences (MacCartney, 2009).”
Detecting hallucinations in large language models using semantic entropy (2024, unknown): “We measure entailment using both general-purpose LLMs and natural language inference (NLI) tools developed specifically for detecting entailment for which we show direct evaluations in Supplementary Tables 2 and 3 and Supplementary Fig.”