Fact verification requires validating a claim in the context of evidence. We show, however, that in the popular FEVER dataset this might not necessarily be the case. Claim-only classifiers perform competitively with top evidenceaware models. In this paper, we investigate the cause of this phenomenon, identifying strong cues for predicting labels solely based on the claim, without considering any evidence. We create an evaluation set that avoids those idiosyncrasies. The performance of FEVERtrained models significantly drops when evaluated on this test set. Therefore, we introduce a regularization method which alleviates the effect of bias in the training data, obtaining improvements on the newly created test set. This work is a step towards a more sound evaluation of reasoning capabilities in fact verification models. 1

In this paper, we introduce SLQS, a new entropy-based measure for the unsupervised identification of hypernymy and its directionality in Distributional Semantic Models (DSMs). SLQS is assessed through two tasks: (i.) identifying the hypernym in hyponym-hypernym pairs, and (ii.) discriminating hypernymy among various semantic relations. In both tasks, SLQS outperforms other state-of-the-art measures.

The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution. We investigate an extensive number of such unsupervised measures, using several distributional semantic models that differ by context type and feature weighting. We analyze the performance of the different methods based on their linguistic motivation. Comparison to the state-of-the-art supervised methods shows that while supervised methods generally outperform the unsupervised ones, the former are sensitive to the distribution of training instances, hurting their reliability. Being based on general linguistic hypotheses and independent from training data, unsupervised measures are more robust, and therefore are still useful artillery for hypernymy detection.

In this paper, we introduce EVALution 1.0, a dataset designed for the training and the evaluation of Distributional Semantic Models (DSMs). This version consists of almost 7.5K tuples, instantiating several semantic relations between word pairs (including hypernymy, synonymy, antonymy, meronymy). The dataset is enriched with a large amount of additional information (i.e. relation domain, word frequency, word POS, word semantic field, etc.) that can be used for either filtering the pairs or performing an in-depth analysis of the results. The tuples were extracted from a combination of ConceptNet 5.0 and Word-Net 4.0, and subsequently filtered through automatic methods and crowdsourcing in order to ensure their quality. The dataset is freely downloadable 1. An extension in RDF format, including also scripts for data processing, is under development.

Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel data. Existing approaches try to explicitly disentangle content and attribute information, but this is difficult and often results in poor content-preservation and ungrammaticality. In contrast, we propose a simpler approach, Iterative Matching and Translation (IMaT), which: (1) constructs a pseudoparallel corpus by aligning a subset of semantically similar sentences from the source and the target corpora; (2) applies a standard sequence-to-sequence model to learn the attribute transfer; (3) iteratively improves the learned transfer function by refining imperfections in the alignment. In sentiment modification and formality transfer tasks, our method outperforms complex state-of-the-art systems by a large margin. As an auxiliary contribution, we produce a publicly-available test set with human-generated transfer references. 1 . * Equal Contribution 1 The enriched test set is available at https:// github.com/zhijing-jin/IMaT

Cheese production is increasing in many countries, and a desire toward genetic selection for milk coagulation properties in dairy cattle breeding exists. However, measurements of individual cheesemaking properties are hampered by high costs and labor, whereas traditional single-point milk coagulation properties (MCP) are sometimes criticized. Nevertheless, new modeling of the entire curd firmness and syneresis process (CFt equation) offers new insight into the cheesemaking process. Moreover, identification of genomic regions regulating milk cheesemaking properties might enhance direct selection of individuals in breeding programs based on cheese ability rather than related milk components. Therefore, the objective of this study was to perform genome-wide association studies to identify genomic regions linked to traditional MCP and new CFt parameters, milk acidity (pH), and milk protein percentage. Milk and DNA samples from 1,043 Italian Brown Swiss cows were used. Milk pH and 3 MCP traits were grouped together to represent the MCP set. Four CFt equation parameters, 2 derived traits, and protein percentage were considered as the second group of traits (CFt set). Animals were genotyped with the Illumina SNP50 BeadChip v.2 (Illumina Inc., San Diego, CA). Multitrait animal models were used to estimate variance components. For genome-wide association studies, the genome-wide association using mixed model and regression-genomic control approach was used. In total, 106 significant marker traits associations and 66 single nucleotide polymorphisms were identified on 12 chromosomes (1, 6, 9, 11, 13, 15, 16, 19, 20, 23, 26, and 28). Sharp peaks were detected at 84 to 88 Mbp on Bos taurus autosome (BTA) 6, with a peak at 87.4 Mbp in the region harboring the casein genes. Evidence of quantitative trait loci at 82.6 and 88.4 Mbp on the same chromosome was found. All chromosomes but BTA6, BTA11, and BTA28 were associated with only one trait. Only BTA6 was in common between MCP and CFt sets. The new CFt traits reinforced the support of MCP signals and provided with additional information on genomic regions that might be involved in regulation of the coagulation process of bovine milk.

No abstract

Bovine Progressive Degenerative Myeloencephalopathy (Weaver Syndrome) is a recessive neurological disease that has been observed in the Brown Swiss cattle breed since the 1970’s in North America and Europe. Bilateral hind leg weakness and ataxia appear in afflicted animals at 6 to 18 months of age, and slowly progresses to total loss of hind limb control by 3 to 4 years of age. While Weaver has previously been mapped to Bos taurus autosome (BTA) 4∶46–56 Mb and a diagnostic test based on the 6 microsatellite (MS) markers is commercially available, neither the causative gene nor mutation has been identified; therefore misdiagnosis can occur due to recombination between the diagnostic MS markers and the causative mutation. Analysis of 34,980 BTA 4 SNPs genotypes derived from the Illumina BovineHD assay for 20 Brown Swiss Weaver carriers and 49 homozygous normal bulls refined the Weaver locus to 48–53 Mb. Genotyping of 153 SNPs, identified from whole genome sequencing of 10 normal and 10 carrier animals, across a validation set of 841 animals resulted in the identification of 41 diagnostic SNPs that were concordant with the disease. Except for one intergenic SNP all are associated with genes expressed in nervous tissues: 37 distal to NRCAM, one non-synonymous (serine to asparagine) in PNPLA8, one synonymous and one non-synonymous (lysine to glutamic acid) in CTTNBP2. Haplotype and imputation analyses of 7,458 Brown Swiss animals with Illumina BovineSNP50 data and the 41 diagnostic SNPs resulted in the identification of only one haplotype concordant with the Weaver phenotype. Use of this haplotype and the diagnostic SNPs more accurately identifies Weaver carriers in both Brown Swiss purebred and influenced herds.