FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning

Despite the success of neural dialogue systems in achieving high performance on the leader-board, they cannot meet users' requirements in practice, due to their poor reasoning skills. The underlying reason is that most neural dialogue models only capture the syntactic and semantic information, but fail to model the logical consistency between the dialogue history and the generated response. Recently, a new multi-turn dialogue reasoning task has been proposed, to facilitate dialogue reasoning research. However, this task is challenging, because there are only slight differences between the illogical response and the dialogue history. How to effectively solve this challenge is still worth exploring. This paper proposes a Fine-grained Comparison Model (FCM) to tackle this problem. Inspired by human's behavior in reading comprehension, a comparison mechanism is proposed to focus on the fine-grained differences in the representation of each response candidate. Specifically, each candidate representation is compared with the whole history to obtain a history consistency representation. Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model prefer a candidate that is logically consistent with the speaker's history logic. Finally, the above consistency representations are employed to output a ranking list of the candidate responses for multi-turn dialogue reasoning. Experimental results on two public dialogue datasets show that our method obtains higher ranking scores than the baseline models.

Comparing Text Representations: A Theory-Driven Approach

Much of the progress in contemporary NLP has come from learning representations, such as masked language model (MLM) contextual embeddings, that turn challenging problems into simple classification tasks. But how do we quantify and explain this effect? We adapt general tools from computational learning theory to fit the specific characteristics of text datasets and present a method to evaluate the compatibility between representations and tasks. Even though many tasks can be easily solved with simple bag-of-words (BOW) representations, BOW does poorly on hard natural language inference tasks. For one such task we find that BOW cannot distinguish between real and randomized labelings, while pre-trained MLM representations show 72x greater distinction between real and random labelings than BOW. This method provides a calibrated, quantitative measure of the difficulty of a classification-based NLP task, enabling comparisons between representations without requiring empirical evaluations that may be sensitive to initializations and hyperparameters. The method provides a fresh perspective on the patterns in a dataset and the alignment of those patterns with specific labels.

Comparing Grammatical Theories of Code-Mixing

Code-mixed text generation systems have found applications in many downstream tasks, including speech recognition, translation and dialogue. A paradigm of these generation systems relies on well-defined grammatical theories of code-mixing, and there is a lack of comparison of these theories. We present a large-scale human evaluation of two popular grammatical theories, Matrix-Embedded Language (ML) and Equivalence Constraint (EC). We compare them against three heuristic-based models and quantitatively demonstrate the effectiveness of the two grammatical theories.

A Comparison of Sentence-Weighting Techniques for NMT

Sentence weighting is a simple and powerful domain adaptation technique. We carry out domain classification for computing sentence weights with 1) language model cross entropy difference 2) a convolutional neural network 3) a Recursive Neural Tensor Network. We compare these approaches with regard to domain classification accuracy and and study the posterior probability distributions. Then we carry out NMT experiments in the scenario where we have no in-domain parallel corpora and and only very limited in-domain monolingual corpora. Here and we use the domain classifier to reweight the sentences of our out-of-domain training corpus. This leads to improvements of up to 2.1 BLEU for German to English translation.

Comparing Span Extraction Methods for Semantic Role Labeling

In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL). While recent progress incorporating pre-trained contextualized representations into neural encoders has greatly improved SRL F1 performance on popular benchmarks, the potential costs and benefits of structured decoding in these models have become less clear. With extensive experiments on PropBank SRL datasets, we find that more structured decoding methods outperform BIO-tagging when using static (word type) embeddings across all experimental settings. However, when used in conjunction with pre-trained contextualized word representations, the benefits are diminished. We also experiment in cross-genre and cross-lingual settings and find similar trends. We further perform speed comparisons and provide analysis on the accuracy-efficiency trade-offs among different decoding methods.

How Vision Affects Language: Comparing Masked Self-Attention in Uni-Modal and Multi-Modal Transformer

The problem of interpretation of knowledge learned by multi-head self-attention in transformers has been one of the central questions in NLP. However, a lot of work mainly focused on models trained for uni-modal tasks, e.g. machine translation. In this paper, we examine masked self-attention in a multi-modal transformer trained for the task of image captioning. In particular, we test whether the multi-modality of the task objective affects the learned attention patterns. Our visualisations of masked self-attention demonstrate that (i) it can learn general linguistic knowledge of the textual input, and (ii) its attention patterns incorporate artefacts from visual modality even though it has never accessed it directly. We compare our transformer's attention patterns with masked attention in distilgpt-2 tested for uni-modal text generation of image captions. Based on the maps of extracted attention weights, we argue that masked self-attention in image captioning transformer seems to be enhanced with semantic knowledge from images, exemplifying joint language-and-vision information in its attention patterns.

Comparing Approaches to Dravidian Language Identification

This paper describes the submissions by team HWR to the Dravidian Language Identification (DLI) shared task organized at VarDial 2021 workshop. The DLI training set includes 16,674 YouTube comments written in Roman script containing code-mixed text with English and one of the three South Dravidian languages: Kannada, Malayalam, and Tamil. We submitted results generated using two models, a Naive Bayes classifier with adaptive language models, which has shown to obtain competitive performance in many language and dialect identification tasks, and a transformer-based model which is widely regarded as the state-of-the-art in a number of NLP tasks. Our first submission was sent in the closed submission track using only the training set provided by the shared task organisers, whereas the second submission is considered to be open as it used a pretrained model trained with external data. Our team attained shared second position in the shared task with the submission based on Naive Bayes. Our results reinforce the idea that deep learning methods are not as competitive in language identification related tasks as they are in many other text classification tasks.

A Comparative Study of the Digestive System Mucosa in Three Types of Lower Vertebrates

The present study aimed to compare the epithelium tissue of mucosa layer of gastrointestinal tract in three types of lower vertebrates: Scyliorhinus canicula, Sparus aurata, Salamandra infraimmaculata. The results of the histological and comparative study showed that the majority of digestion system parts were lined with simple epithelium tissue while others were lined by pseudostratified epithelium tissue. Goblet cells were distributed in all studied parts of digestion systems with density in some locations. Esophagus was characterized by ciliated epithelium tissue, and the tubular glands were presents in the stomach mucosa. Concerning the Lumina properia, it was visible in all digestive system parts with some differences according to the animal species studied.

Acomparative interpretation of friendship concept in Haidars Hijret Al-Sonono, Huckleberry Finn Adventures by Mark Twain, The Mother by Gorky

Friendship is not a positive social relationship full of moral values .Rather ,it is an essential existential component that has to do with the human soul on all levels starting from the significance of a friend in understanding the other, who represents the major characters in the handled novels of research .The research aims at representing a socialphilosophical compromise of friendship from a comparative perspective dealing with three novels different in time and theme to get the relation which exceeds being an embodiment with which the friend lives with his friend to the self and the other in the major characters which its special world shaped by blending the life experience with the reality portrayed shaped by this relation.In conclusion ,it aims that friendship is a vital active discourse .The most rational part derivate the self of the social weak part , to show his opinion toward self and world.

Comparative Study of Chemical Properties Between Woman's Milk and Cow's Milk

A study of chemical composition of woman's milk has been made and compared with cow's milk in the province of Homs. The findings of this study show that The total value of the solid material in cow's milk is (12.26 ± 1.2%). It is approximately equal to woman 's milk content of the total solid material which is (12.11 ± 0.09%). The woman 's milk content of mineral elements is (02% ± 001%), while the cow's milk content is (0.71 ± 0.14%). For the value of fatty material in the mother's milk, it is (3.5 ± 0.02%) and this is almost equal to cow's milk content of the same material which is (3.4 ± 0.05%). The cow's milk content of protein is equivalent to (2.92 ± 0.019%), whereas cow's milk content is equivalent to ( 1.25 ± 0.009%). The value of calcium in the mother's milk is (32 ± 4.3 mg), and this is significantly lower than the value of the calcium in cow's milk, which is (118 ± 8.2 Mg/ kg).