For many NLP applications of online reviews, comparison of two opinion-bearing sentences is key. We argue that, while general purpose text similarity metrics have been applied for this purpose, there has been limited exploration of their applicabilit
y to opinion texts. We address this gap in the literature, studying: (1) how humans judge the similarity of pairs of opinion-bearing sentences; and, (2) the degree to which existing text similarity metrics, particularly embedding-based ones, correspond to human judgments. We crowdsourced annotations for opinion sentence pairs and our main findings are: (1) annotators tend to agree on whether or not opinion sentences are similar or different; and (2) embedding-based metrics capture human judgments of opinion similarity'' but not opinion difference''. Based on our analysis, we identify areas where the current metrics should be improved. We further propose to learn a similarity metric for opinion similarity via fine-tuning the Sentence-BERT sentence-embedding network based on review text and weak supervision by review ratings. Experiments show that our learned metric outperforms existing text similarity metrics and especially show significantly higher correlations with human annotations for differing opinions.
Document alignment techniques based on multilingual sentence representations have recently shown state of the art results. However, these techniques rely on unsupervised distance measurement techniques, which cannot be fined-tuned to the task at hand
. In this paper, instead of these unsupervised distance measurement techniques, we employ Metric Learning to derive task-specific distance measurements. These measurements are supervised, meaning that the distance measurement metric is trained using a parallel dataset. Using a dataset belonging to English, Sinhala, and Tamil, which belong to three different language families, we show that these task-specific supervised distance learning metrics outperform their unsupervised counterparts, for document alignment.
Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain adaptatio
n. This paper models adaptation success and selection of the most suitable source domains among several candidates in text similarity. We use descriptive domain information and cross-domain similarity metrics as predictive features. While mostly positive, the results also point to some domains where adaptation success was difficult to predict.
Van Tijm and Victor Gremonsky, in their comparative monetary work, have
established two closely related, largely divergent approaches and research methods. The
first to follow the approach of EvelFeilmann to look at international literary relations
is a
certain historical causation (historical theory). And the second approach to the theory of
typology, influenced by the writings of A. Vesilowski monetary, influenced by German
philosophers, starting in the second half of the eighteenth century. The term similarities
and differences between literatures is presented as a result of similarity or difference in the
movement of the development of societies and their conditions.
However, their divergence in principle did not override their agreement on some
partial issues and their divergence in other matters. This is what the research will try to
look at, using extrapolation as a means to elucidate judgments, which were ignored by
scholars and interested parties, in the hope of giving each person the right, both impartially
and objectively, to adopt their texts.
