No abstract

No abstract

Corresponding author … … … … source target Figure 1: Schematic representation of seq2seq NMT, where x 1 , . .. , x T and h 1 , . . . , h T represent source-side word embeddings and hidden states respectively, c t represents a source-side context vector, s t a target-side decoder RNN hidden state, and y t a predicted word. Seeking to shorten the distance between source and target word embeddings, in what we term bridging, is the key insight for the advances presented in this paper.improve quality of both sentence translation, in general, and alignment and translation of individual source words with target words, in particular.

Semantic networks and semantic spaces have been two prominent approaches to represent lexical semantics. While a unified account of the lexical meaning relies on one being able to convert between these representations, in both directions, the conversion direction from semantic networks into semantic spaces started to attract more attention recently. In this paper we present a methodology for this conversion and assess it with a case study. When it is applied over WordNet, the performance of the resulting embeddings in a mainstream semantic similarity task is very good, substantially superior to the performance of word embeddings based on very large collections of texts like word2vec.

Commonsense is a quintessential human capacity that has been a core challenge to Artificial Intelligence since its inception. Impressive results in Natural Language Processing tasks, including in commonsense reasoning, have consistently been achieved with Transformer neural language models, even matching or surpassing human performance in some benchmarks. Recently, some of these advances have been called into question: so called data artifacts in the training data have been made evident as spurious correlations and shallow shortcuts that in some cases are leveraging these outstanding results.In this paper we seek to further pursue this analysis into the realm of commonsense related language processing tasks. We undertake a study on different prominent benchmarks that involve commonsense reasoning, along a number of key stress experiments, thus seeking to gain insight on whether the models are learning transferable generalizations intrinsic to the problem at stake or just taking advantage of incidental shortcuts in the data items.The results obtained indicate that most datasets experimented with are problematic, with models resorting to non-robust features and appearing not to be learning and generalizing towards the overall tasks intended to be conveyed or exemplified by the datasets.