Automatic soccer commentary generation aims to bridge the gap between raw visual content and professional, tactical commentary.However, existing datasets tend to produce incomplete commentary that lacks semantic richness and fails to convey the full visual information present in standard video clips.To address these limitations, we propose two manually curated datasets: SN-Short, which enhances scene-level semantic descriptions, and SN-Long, which captures event continuity for context-aware commentary.Based on these, we design a commentary augmentation pipeline that transforms incomplete annotations into MatchText, a semantically complete and structurally standardized dataset.Leveraging this supervision, we introduce MatchAware, a generation model that incorporates contextual cues from previous events to produce coherent commentary aligned with the visual flow of the game.Experimental results show that proposed approach significantly outperforms existing baselines on the constructed datasets.~45: 03 ~42: 14 SN-Caption (Mkhallati et al.2023): Dwight Gayle (Crystal Palace) launches a cross from the corner, but David Ospina is alert to thwart the effort.SN-Short (ours): Dwight Gayle (Crystal Palace) launches a cross from the corner, but David Ospina is alert to thwart the effort.The cross was aimed at the far post, but the keeper stood firm and cleared the danger.SN-Long (ours): ・・・・・・ SN-Caption (Mkhallati et al.2023): Goal! Olivier Giroud (Arsenal) fires the rebound inside the right post after the ball breaks to him in the box.The score is 0:2.SN-Short (ours): Goal! Olivier Giroud (Arsenal) fires the rebound inside the right post after the ball breaks to him in the box.The score is 0:2.The away fans erupt in joy, celebrating the crucial goal just before halftime.SN-Long (ours): SN-Short + Both sides have been creating scoring opportunities, with the keepers making key saves at both ends.But it'

This paper proposes a method to develop a machine translation (MT) system from Myanmar Sign Language (MSL) to Myanmar Written Language (MWL) and vice versa for the deaf community. Translation of MSL is a difficult task since only a small amount of a parallel corpus between MSL and MWL is available. To address the challenge for MT of the low-resource language, transfer learning is applied. An MT model is trained first for a high-resource language pair, American Sign Language (ASL) and English, then it is used as an initial model to train an MT model between MSL and MWL. The mT5 model is used as a base MT model in this transfer learning. Additionally, a self-training technique is applied to generate synthetic translation pairs of MSL and MWL from a large monolingual MWL corpus. Furthermore, since the segmentation of a sentence is required as preprocessing of MT for the Myanmar language, several segmentation schemes are empirically compared. Results of experiments show that both transfer learning and self-training can enhance the performance of the translation between MSL and MWL compared with a baseline model fine-tuned from a small MSL-MWL parallel corpus only.

Seeking an efficient solution for the problem of dynamic user preferences on social networks is challenging because the input data areshort textsand user preferences usuallychangeover time. This work proposes a novel framework that tackles these challenges based on deep neural networks and the Dempster-Shafer theory of evidence. The framework consists of three primary phases: (1) learning the hidden space of user texts; (2) word generation and mass inference; and (3) mass combination and keyword extraction. In the first phase, user texts are grouped into small batches according to timestamps. Each batch is used for separately training two types of neural networks, the Variational Autoencoder (VAE) and the Generative Adversarial Network (GAN). In the second phase, the generators in the trained VAE and GAN work independently as twoexpertsto generate bunches of tokens for modeling user preferences. Each bunch is considered as one piece of evidence, and is transformed into the so-called mass function in Dempster-Shafer theory by maximum a posterior estimation. In the final phase, Dempster’s rule of combination is utilized for fusing the two independent pieces of evidence into an overall mass. This mass is used for extracting top keywords to form the user preferences within a specific time span. The experiments on short text datasets verified that the proposed method outperforms baseline models on many evaluation metrics. Additionally, the output of the proposed framework could be used for visualization, which is useful in many practical applications.

Aspect-based sentiment analysis (ABSA) is a task that involves classifying the polarity of aspects of the products or services described in users’ reviews. Most previous work on ABSA has focused on explicit aspects, which appear as explicit words or phrases in the sentences of the review. However, users often express their opinions toward the aspects indirectly or implicitly, in which case the specific name of an aspect does not appear in the review. The current datasets used for ABSA are mainly annotated with explicit aspects. This paper proposes a novel method for constructing a corpus that is automatically annotated with implicit aspects. The main idea is that sentences containing explicit and implicit aspects share a similar context. First, labeled sentences with explicit aspects and unlabeled sentences that include implicit aspects are collected. Next, clustering is performed on these sentences so that similar sentences are merged into the same cluster. Finally, the explicit aspects are propagated to the unlabeled sentences in the same cluster, in order to construct a labeled dataset containing implicit aspects. The results of our experiments on mobile phone reviews show that our method of identifying the labels of implicit aspects achieves a maximum accuracy of 82%.

In this paper, we introduce BART2S a novel framework based on BART pretrained models to generate terms of service in high quality. The framework contains two parts: a generator finetuned with multiple tasks and a discriminator fine-tuned to distinguish the fair and unfair terms. Besides the novelty in design and the implementation contributions, the proposed framework can support drafting terms of service, a growing need in the digital age. Our proposed approach allows the system to reach a balance between automation and the will expression of the service provider. Through experiments, we demonstrate the effectiveness of the method and discuss potential future directions.

Thien Hai Nguyen, Kiyoaki Shirai. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

This paper presents a new method to identify sentiment of an aspect of an entity. It is an extension of RNN (Recursive Neural Network) that takes both dependency and constituent trees of a sentence into account. Results of an experiment show that our method significantly outperforms previous methods.

Our goal is to develop a support-sentence retrieval system that retrieves sentences relevant to a given theme and then, classifies them into relevant types, such as agreement, contradiction, refinement, and supplement. This paper focuses on the first step, a sentence retrieval module. Lexical and typed dependency matching are used to compute the similarity between two sentences. A new query term weighting scheme based on the specificity of the terms is proposed and combined with ordinary IDF weighting for a better performance. Experimental results indicate that our method achieves 34% higher precision than the traditional TF-ISF method

In Japanese constructions of the form [N1 no Adj N2], the adjective Adj modifies either N1 or N2. Determing the semantic dependencies of adjective in such phrase is an important task for machine translation. This paper describes a method for determining the adjective dependency in such constructions using decision lists, and inducing decision lists from training contexts with correct semantic dependencies and without. Based on evaluation, our method is able to determine adjective dependency with an precision of about 94%. We further analyze rules in the induced decision lists and examine effective features to determine the semantic dependencies of adjectives.