Figure 1: Example images of animated trading card .

Recently, Large language models (LLMs) with in-context learning have demonstrated remarkable potential in handling neural machine translation. However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply the fixed prompt to any input for downstream machine translation tasks. To address this issue, we propose an adaptive few-shot prompting (AFSP) framework to automatically select suitable translation demonstrations for various source input sentences to further elicit the translation capability of an LLM for better machine translation. First, we build a translation demonstration retrieval module based on LLM's embedding to retrieve top-k semantic-similar translation demonstrations from aligned parallel translation corpus. Rather than using other embedding models for semantic demonstration retrieval, we build a hybrid demonstration retrieval module based on the embedding layer of the deployed LLM to build better input representation for retrieving more semantic-related translation demonstrations. Then, to ensure better semantic consistency between source inputs and target outputs, we force the deployed LLM itself to generate multiple output candidates in the target language with the help of translation demonstrations and rerank these candidates. Besides, to better evaluate the effectiveness of our AFSP framework on the latest language and extend the research boundary of neural machine translation, we construct a high-quality diplomatic Chinese-English parallel dataset that consists of 5,528 parallel Chinese-English sentences. Finally, extensive experiments on the proposed diplomatic Chinese-English parallel dataset and the United Nations Parallel Corpus (Chinese-English part) show the effectiveness and superiority of our proposed AFSP.

Efficiently exploring complex loss landscapes is key to the performance of deep neural networks. While momentum-based optimizers are widely used in stateof-the-art setups, classical momentum can still struggle with large, misaligned gradients, leading to oscillations. To address this, we propose Torque-Aware Momentum (TAM), which introduces a damping factor based on the angle between the new gradients and previous momentum, stabilizing the update direction during training. Empirical results show that TAM, which can be combined with both SGD and Adam, enhances exploration, handles distribution shifts more effectively, and improves generalization performance across various tasks, including image classification and large language model fine-tuning, when compared to classical momentum-based optimizers. Despite the wide range of optimization methods available in the literature, stochastic gradient descent (SGD), typically augmented with momentum (Kingma & Ba, 2015; Nesterov, 1983; Qian, 1999), remains the go-to approach for practitioners. Momentum accelerates convergence, particularly in the presence of high curvature (Cutkosky & Mehta, 2020b), small but consistent gradients, or noisy gradients. It also helps the optimizer navigate the loss landscape and escape local minima or saddle points by maintaining consistent updates directions (Jin et al., 2018). While SGD with momentum (SGDM) has shown remarkable success in various scenarios, particularly in computer vision (Sutskever et al., 2013), it remains vulnerable to In this work, we propose that minimizing the influence of misaligned gradients during momentum updates can preserve valuable information and improve the exploration Figure 1: Comparing momentum updates capabilities of momentum-based methods. To enable more obtained using SGDM and TAM consistent exploration of the loss landscape, particularly in for a given SGD trajectory.

Human understanding of language is robust to different word choices as far as they represent similar semantic concepts. To what extent does our human intuition transfer to language models, which represent all subwords as distinct embeddings? In this work, we take an initial step on measuring the role of shared semantics among subwords in the encoder-only multilingual language models (mLMs). To this end, we form "semantic tokens" by merging the semantically similar subwords and their embeddings, and evaluate the updated mLMs on 5 heterogeneous multilingual downstream tasks. Results show that the general shared semantics could get the models a long way in making the predictions on mLMs with different tokenizers and model sizes. Inspections on the grouped subwords show that they exhibit a wide range of semantic similarities, including synonyms and translations across many languages and scripts. Lastly, we found the zero-shot results with semantic tokens are on par or even better than the original models on certain classification tasks, suggesting that the shared subword-level semantics may serve as the anchors for cross-lingual transferring.

Text embedding models play a pivotal role in natural language processing and machine learning. By encoding texts into structured numerical representations, known as text embeddings, these models encapsulate semantic and contextual information of words, phrases, or entire documents within a dense, lowdimensional vector space [27]. Such embeddings are indispensable for various downstream NLP tasks, including classification, clustering, retrieval, and sentence similarity. Contrastive learning stands out as the most effective technique for training text embedding models [6]. It presents text semantic representations by minimizing the distance between positive pairs and maximizing the distance between negative pairs. Beyond its application in natural language processing (NLP), contrastive learning also proves pivotal in visual [8] [5] and multi-modal [25] representation learning. Recent advanced text embedding works [36] [33] [18] primarily rely on a two-stage pretrain-finetune pipeline to acquire general text embedding models. Pre-training utilizes weakly supervised data sourced from large-scale crawling efforts, while fine-tuning involves refining the model with high-quality text pairs obtained through data mining or manual annotation.

Large language models (LLMs) have demonstrated impressive capabilities in general scenarios, exhibiting a level of aptitude that approaches, in some aspects even surpasses, human-level intelligence. Among their numerous skills, the translation abilities of LLMs have received considerable attention. Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process which might take preparatory steps to ensure high-quality translation. This work explores this possibility by proposing the MAPS framework, which stands for Multi-Aspect Prompting and Selection. Specifically, we enable LLMs first to analyze the given source sentence and induce three aspects of translation-related knowledge: keywords, topics, and relevant demonstrations to guide the final translation process. Moreover, we employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge. Both automatic (3 LLMs x 11 directions x 2 automatic metrics) and human evaluation (preference study and MQM) demonstrate the effectiveness of MAPS. Further analysis shows that by mimicking the human translation process, MAPS reduces various translation errors such as hallucination, ambiguity, mistranslation, awkward style, untranslated text, and omission. Source code is available at https://github.com/zwhe99/MAPS-mt.

We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes based on the similarity of contextualised and decontextualised word embeddings, i.e. the average contextual representation of a word in multiple contexts. We conduct experiments in English and Italian, and show that our method substantially outperforms strong baselines and establishes a new state-of-the-art without any explicit supervision or fine-tuning. We further show that our method performs particularly well at predicting low-frequency substitutes, and also generates a diverse list of substitute candidates, reducing morphophonetic or morphosyntactic biases induced by article-noun agreement.

Current open-domain question answering (QA) systems often follow a Retriever-Reader (R2) architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple and effective passage reranking method, Reader-guIDEd Reranker (Rider), which does not involve any training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. We show that Rider, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) score gains without refining the retriever or reader. In particular, Rider achieves 48.3 EM on the Natural Questions dataset and 66.4 on the TriviaQA dataset when only 1,024 tokens (7.8 passages on average) are used as the reader input.

This paper presents our system details and results of participation in the RDoC Tasks of BioNLP-OST 2019. Research Domain Criteria (RDoC) construct is a multi-dimensional and broad framework to describe mental health disorders by combining knowledge from genomics to behaviour. Non-availability of RDoC labelled dataset and tedious labelling process hinders the use of RDoC framework to reach its full potential in Biomedical research community and Healthcare industry. Therefore, Task-1 aims at retrieval and ranking of PubMed abstracts relevant to a given RDoC construct and Task-2 aims at extraction of the most relevant sentence from a given PubMed abstract. We investigate (1) attention based supervised neural topic model and SVM for retrieval and ranking of PubMed abstracts and, further utilize BM25 and other relevance measures for re-ranking, (2) supervised and unsupervised sentence ranking models utilizing multi-view representations comprising of query-aware attention-based sentence representation (QAR), bag-of-words (BoW) and TF-IDF. Our best systems achieved 1st rank and scored 0.86 mean average precision (mAP) and 0.58 macro average accuracy (MAA) in Task-1 and Task-2 respectively.