We introduce XMEANT-a new cross-lingual version of the semantic frame based MT evaluation metric MEANT-which can correlate even more closely with human adequacy judgments than monolingual MEANT and eliminates the need for expensive human references. Previous work established that MEANT reflects translation adequacy with state-of-the-art accuracy, and optimizing MT systems against MEANT robustly improves translation quality. However, to go beyond tuning weights in the loglinear SMT model, a cross-lingual objective function that can deeply integrate semantic frame criteria into the MT training pipeline is needed. We show that cross-lingual XMEANT outperforms monolingual MEANT by (1) replacing the monolingual context vector model in MEANT with simple translation probabilities, and (2) incorporating bracketing ITG constraints.

No abstract

Technologies for argument mining and argumentation processing are maturing continuously, giving rise to the idea of retrieving arguments in search scenarios. We introduce Touché, the first lab on Argument Retrieval featuring two subtasks: (1) the retrieval of arguments from a focused debate collection to support argumentative conversations, and (2) the retrieval of arguments from a generic web crawl to answer comparative questions with argumentative results. The goal of this lab is to perform an evaluation of various strategies to retrieve argumentative information from the web content. In this paper, we describe the setting of each subtask: the motivation, the data, and the evaluation methodology.

We present the first Africentric SemEval Shared task, Sentiment Analysis for African Languages (AfriSenti-SemEval) 1 . AfriSenti-SemEval is a sentiment classification challenge in 14 African languages (Amharic, Algerian Arabic, Hausa, Igbo, Kinyarwanda, Moroccan Arabic, Mozambican Portuguese, Nigerian Pidgin, Oromo, Swahili, Tigrinya, Twi, Xitsonga, and Yorùbá) (Muhammad et al., 2023), using data labeled with 3 sentiment classes. We present three subtasks: (1) Task A: monolingual classification, which received 44 submissions; (2) Task B: multilingual classification, which received 32 submissions; and (3) Task C: zero-shot classification, which received 34 submissions. The best performance for tasks A and B was achieved by NLNDE team with 71.31 and 75.06 weighted F1, respectively. UCAS-IIE-NLP achieved the best average score for task C with 58.15 weighted F1. We describe the various approaches adopted by the top 10 systems and their approaches.

No abstract