Жіңішке баптау

We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vec- tors for sentence-level classification tasks. We show that a simple CNN …...

Neural machine translation is a recently proposed approach which has shown competitive re- sults to traditional MT approaches. Similar to other neural network based methods, NMT also suffers from low …...

In recent years, machine learning methods beyond the confines of conventional super- vised learning have been used along with deep learning methods and intensively investigated. Fine-tuning, which improves the performance …...

AbstractWhile target-side monolingual data has been proven to be very useful to improve neural machine translation (briefly, NMT) through back translation, source-side monolingual data is not well investigated. In this …...

AbstractDespite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most …...

AbstractLanguage model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different …...

AbstractFine-tuning pretrained model has achieved promising performance on standard NER benchmarks. Generally, these benchmarks are blessed with strong name regularity, high mention coverage and sufficient context diversity. Unfortunately, when scaling …...

AbstractBERT, a neural network-based language model pre-trained on large corpora, is a breakthrough in natural language processing, significantly outperforming previous state-of-the-art models in numerous tasks. However, there have been few …...

AbstractA major challenge in modern neural networks is the utilization of previous knowledge for new tasks in an effective manner, otherwise known as transfer learning. Fine-tuning, the most widely used …...

AbstractLow-resource machine translation suffers from the scarcity of training data and the unavailability of standard evaluation sets. While a number of research efforts target the former, the unavailability of evaluation …...

AbstractFine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations. In this paper we show that concatenating the embeddings from the pre-trained model with those …...

AbstractIn this paper, we describe an approach for modelling causal reasoning in natural language by detecting counterfactuals in text using multi-head self-attention weights. We use pre-trained transformer models to extract …...

AbstractHuman-generated non-literal translations reflect the richness of human languages and are sometimes indispensable to ensure adequacy and fluency. Non-literal translations are difficult to produce even for human translators, especially for …...

AbstractIntermediate-task training—fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task—often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate …...

AbstractFine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which …...

AbstractRecently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research …...

Word embeddings are used in various fields of natural language processing. The use of word embeddings and concept or word sense em- beddings demonstrated effectiveness in many tasks, such as …...

AbstractSentiment analysis for code-mixed social media text continues to be an under-explored area. This work adds two common approaches: fine-tuning large transformer models and sample efficient methods like ULMFiT. Prior …...

AbstractThis paper shows our system for SemEval-2020 task 10, Emphasis Selection for Written Text in Visual Media. Our strategy is two-fold. First, we propose fine-tuning many pre-trained language models, predicting …...

AbstractRecent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. We constructed a …...

AbstractIn this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several …...

AbstractText classification tends to be difficult when data are inadequate considering the amount of manually labeled text corpora. For low-resource agglutinative languages including Uyghur, Kazakh, and Kyrgyz (UKK languages), in …...

AbstractFine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured …...

AbstractLarge scale pre-trained language models have shown groundbreaking performance improvements for transfer learning in the domain of natural language processing. In our paper, we study a pre-trained multilingual BERT model …...

AbstractThis paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, …...

AbstractAppTek and RWTH Aachen University team together to participate in the offline and simultaneous speech translation tracks of IWSLT 2020. For the offline task, we create both cascaded and end-to-end …...

AbstractThis paper describes the DeepMind submission to the Chinese→English constrained data track of the WMT2020 Shared Task on News Translation. The submission employs a noisy channel factorization as the backbone …...

AbstractThis paper describes the participation of the NLP research team of the IPN Computer Research center in the WMT 2020 Similar Language Translation Task. We have submitted systems for the …...

AbstractRecently, BERT has become an essential ingredient of various NLP deep models due to its effectiveness and universal-usability. However, the online deployment of BERT is often blocked by its large-scale …...

AbstractRecently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the fine-tuning stage …...

AbstractThe training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small …...

AbstractThis paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA). Our work is motivated by the recent progress in BERT-based language …...

AbstractIn online domain-specific customer service applications, many companies struggle to deploy advanced NLP models successfully, due to the limited availability of and noise in their datasets. While prior research demonstrated …...

AbstractThe performance of fine-tuning pre-trained language models largely depends on the hyperparameter configuration. In this paper, we investigate the performance of modern hyperparameter optimization methods (HPO) on fine-tuning pre-trained language …...

AbstractIn this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for …...

AbstractRecent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem. In this work, we demonstrate that, despite …...

The major paradigm of applying a pre-trained language model to downstream tasks is to fine- tune it on labeled task data, which often suf- fers instability and low performance when …...

AbstractThe rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, …...

AbstractThis paper describes our submission to the SemEval-2021 shared task on Lexical Complexity Prediction. We approached it as a regression problem and present an ensemble combining four systems, one feature-based …...

AbstractFine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we use …...

Recently, quite a few studies have been progressive for temporal relation extraction, which is an important work used in sev- eral natural language processing applications. However, less concentration has been …...

AbstractLoading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove …...

AbstractThe rise of pre-trained language models has yielded substantial progress in the vast majority of Natural Language Processing (NLP) tasks. However, a generic approach towards the pre-training procedure can naturally …...

AbstractIt has been shown for English that discrete and soft prompting perform strongly in few-shot learning with pretrained language models (PLMs). In this paper, we show that discrete and soft …...

AbstractFine-tuning pre-trained language models for downstream tasks has become a norm for NLP. Recently it is found that intermediate training can improve performance for fine-tuning language models for target tasks, …...

AbstractRecent progress in pretraining language models on large corpora has resulted in significant performance gains on many NLP tasks. These large models acquire linguistic knowledge during pretraining, which helps to …...

AbstractFinetuning deep pre-trained language models has shown state-of-the-art performances on a wide range of Natural Language Processing (NLP) applications. Nevertheless, their generalization performance drops under domain shift. In the case …...

AbstractLexical semantic change detection is a new and innovative research field. The optimal fine-tuning of models including pre- and post-processing is largely unclear. We optimize existing models by (i) pre-training …...

AbstractCommonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained …...

AbstractIn several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where …...

AbstractThe task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art …...

AbstractIn this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by …...

AbstractTo obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While …...

AbstractWe propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed-attention mechanism, and employ …...

AbstractFine-tuning a large language model on downstream tasks has become a commonly adopted process in the Natural Language Processing (NLP) (CITATION). However, such a process, when associated with the current …...

AbstractFine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and …...

In this research, we investigate techniques to detect hate speech in movies. We introduce a new dataset collected from the subtitles of six movies, where each utterance is annotated ei- …...

AbstractWhen fine-tuning pretrained models for classification, researchers either use a generic model head or a task-specific prompt for prediction. Proponents of prompting have argued that prompts provide a method for …...

AbstractThis paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use …...

AbstractWhile large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored. We leverage advances in language …...

AbstractIn this paper, we propose a knowledge infusion mechanism to incorporate domain knowledge into language transformers. Weakly supervised data is regarded as the main source for knowledge acquisition. We pre-train …...

AbstractNeural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the …...

AbstractAlthough pretrained language models can be fine-tuned to produce state-of-the-art results for a very wide range of language understanding tasks, the dynamics of this process are not well understood, especially …...

AbstractLow-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper …...

AbstractTransformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model …...

AbstractLanguage modeling with BERT consists of two phases of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. We present a method that leverages the …...

AbstractIn the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of …...

AbstractFine-tuning pre-trained language models suchas BERT has become a common practice dom-inating leaderboards across various NLP tasks. Despite its recent success and wide adoption,this process is unstable when there are …...

AbstractAdapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter …...

AbstractRecent studies on neural networks with pre-trained weights (i.e., BERT) have mainly focused on a low-dimensional subspace, where the embedding vectors computed from input words (or their contexts) are located. …...

Frequent usage of complex expressions with numbers and of the terms that require domain knowledge makes it more difficult to com- prehend and summarize financial news arti- cles than that …...

AbstractFine-tuning is the de facto way of leveraging large pretrained language models for downstream tasks. However, fine-tuning modifies all the language model parameters and therefore necessitates storing a full copy …...

AbstractFor task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for …...

AbstractThere has been recent success in pre-training on monolingual data and fine-tuning on Machine Translation (MT), but it remains unclear how to best leverage a pre-trained model for a given …...

AbstractIn this paper, we investigate what types of stereotypical information are captured by pretrained language models. We present the first dataset comprising stereotypical attributes of a range of social groups …...

AbstractLarge pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important for …...

AbstractLarge datasets are essential for neural modeling of many NLP tasks. Current publicly available open-domain dialogue datasets offer a trade-off between quality (e.g., DailyDialog) and size (e.g., Opensubtitles). We narrow …...

AbstractThis paper describes Mininglamp neural machine translation systems of the WMT2021 news translation tasks. We have participated in eight directions translation tasks for news text including Chinese to/from English, Hausa …...

AbstractWe propose TuringAdvice, a new challenge task and dataset for language understanding models. Given a written situation that a real person is currently facing, a model must generate helpful advice …...

AbstractWe describe the Uppsala NLP submission to SemEval-2021 Task 2 on multilingual and cross-lingual word-in-context disambiguation. We explore the usefulness of three pre-trained multilingual language models, XLM-RoBERTa (XLMR), Multilingual BERT …...

AbstractNLP is currently dominated by language models like RoBERTa which are pretrained on billions of words. But what exact knowledge or skills do Transformer LMs learn from large-scale pretraining that …...

AbstractIn this paper, we describe our system used for SemEval 2021 Task 7: HaHackathon: Detecting and Rating Humor and Offense. We used a simple fine-tuning approach using different Pre-trained Language …...

AbstractGiven the prevalence of pre-trained contextualized representations in today’s NLP, there have been many efforts to understand what information they contain, and why they seem to be universally successful. The …...

AbstractNamed entity recognition has become an increasingly useful tool for digital humanities research, specially when it comes to historical texts. However, historical texts pose a wide range of challenges to …...

AbstractRecent advances in the pre-training for language models leverage large-scale datasets to create multilingual models. However, low-resource languages are mostly left out in these datasets. This is primarily because many …...

AbstractLarge language models are shown to present privacy risks through memorization of training data, andseveral recent works have studied such risks for the pre-training phase. Little attention, however, has been …...

AbstractRecently, fine-tuning the pre-trained language model (PrLM) on labeled sentiment datasets demonstrates impressive performance. However, collecting labeled sentiment dataset is time-consuming, and fine-tuning the whole PrLM brings about much computation …...

AbstractWe address the task of automatically distinguishing between human-translated (HT) and machine translated (MT) texts. Following recent work, we fine-tune pre-trained language models (LMs) to perform this task. Our work …...

AbstractNominalization re-writes a clause as a noun phrase. It requires the transformation of the head verb of the clause into a deverbal noun, and the verb’s modifiers into nominal modifiers. …...

AbstractThis paper introduces the joint submission of the Beijing Jiaotong University and WeChat AI to the WMT’22 chat translation task for English-German. Based on the Transformer, we apply several effective …...

AbstractThere have been many efforts to try to understand what grammatical knowledge (e.g., ability to understand the part of speech of a token) is encoded in large pre-trained language models …...

AbstractIn real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as …...

AbstractIn this paper we describe our work towards building a generic framework for both multi-modal embedding and multi-label binary classification tasks, while participating in task 5 (Multimedia Automatic Misogyny Identification) …...

AbstractThere have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision …...

AbstractFine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques …...

AbstractThe finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, …...

AbstractPrompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in …...

AbstractIn this paper, we describe a system that we built to participate in the SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition, specifically the track Mono-lingual in English. …...

AbstractHate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection models in hundreds …...

AbstractWe study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for MLMs, and find that there exists only a weak correlation between these two types of …...

AbstractFine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. …...

AbstractSince empathy plays a crucial role in increasing social bonding between people, many studies have designed their own dialogue agents to be empathetic using the well-established method of fine-tuning. However, …...

AbstractFAQs are important resources to find information. However, especially if a FAQ concerns many question-answer pairs, it can be a difficult and time-consuming job to find the answer you are …...

AbstractMasked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used …...

AbstractDespite their strong performance on many tasks, pre-trained language models have been shown to struggle on out-of-distribution compositional generalization. Meanwhile, recent work has shown considerable improvements on many NLP tasks …...

AbstractWe present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. …...

AbstractPrior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that …...

AbstractFine-tuning general-purpose pre-trained models has become a de-facto standard, also for Vision and Language tasks such as Visual Question Answering (VQA). In this paper, we take a step back and …...

AbstractCurrent approaches for fixing systematic problems in NLP models (e.g., regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide …...

AbstractGTCOM participates in five directions: English to/from Ukrainian, Ukrainian to/from Czech, English to Chinese and English to Croatian. Our submitted systems are unconstrained and focus on backtranslation, multilingual translation model …...

AbstractPretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase …...

AbstractThis paper describes the translation systems trained by Huawei translation services center (HW-TSC) for the WMT22 biomedical translation task in five language pairs: English↔German (en↔de), English↔French (en↔fr), English↔Chinese (en↔zh), English↔Russian …...

AbstractThis work presents a standard Igbo named entity recognition (IgboNER) dataset as well as the results from training and fine-tuning state-of-the-art transformer IgboNER models. We discuss the process of our …...

AbstractFine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks …...

AbstractThough some recent works focus on injecting sentiment knowledge into pre-trained language models, they usually design mask and reconstruction tasks in the post-training phase. This paper aims to integrate sentiment …...

AbstractGrasping the commonsense properties of everyday concepts is an important prerequisite to language understanding. While contextualised language models are reportedly capable of predicting such commonsense properties with human-level accuracy, we …...

AbstractCommonsense reasoning tasks follow a standard paradigm of finetuning pretrained language models on the target task data, where samples are introduced to the model in a random order during training. …...

AbstractBorrowing ideas from Production functions in micro-economics, in this paper we introduce a framework to systematically evaluate the performance and cost trade-offs between machine-translated and manually-created labelled data for task-specific …...

AbstractSeveral studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset …...

AbstractThis paper describes the method we utilized in the SemEval-2022 Task 6 iSarcasmEval: Intended Sarcasm Detection In English and Arabic. Our system has achieved 1st in SubtaskB, which is to …...

AbstractThis paper describes the submissions of the UPC Machine Translation group to the IWSLT 2022 Offline Speech Translation and Speech-to-Speech Translation tracks. The offline task involves translating English speech to …...

AbstractCode-switched (CS) data is ubiquitous in today’s globalized world, but the dearth of annotated datasets in code-switching poses a significant challenge for learning diverse tasks across different language pairs. Parameter-efficient …...

AbstractAs manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as data augmentation (DA). …...

AbstractKnowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and …...

AbstractSentiment analysis is a useful problem which could serve a variety of fields from business intelligence to social studies and even health studies. Using SemEval 2022 Task 10 formulation of …...

AbstractWhile fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two …...

AbstractWe introduce the task of microblog opinion summarization (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain. The dataset contains summaries of tweets …...

AbstractThis paper describes AISP-SJTU’s participation in WMT 2022 shared general MT task. In this shared task, we participated in four translation directions: English-Chinese, Chinese-English, English-Japanese and Japanese-English. Our systems are …...

AbstractThe ARC-NKUA (“Athena” Research Center - National and Kapodistrian University of Athens) submission to the WMT22 General Machine Translation shared task concerns the unconstrained tracks of the English-Ukrainian and Ukrainian-English …...

Abstract“Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a …...

AbstractRecently, finetuning a pretrained language model to capture the similarity between sentence embeddings has shown the state-of-the-art performance on the semantic textual similarity (STS) task. However, the absence of an …...

AbstractToxic language detection systems often falsely flag text that contains minority group mentions as toxic, as those groups are often the targets of online hate. Such over-reliance on spurious correlations …...

AbstractRecent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers …...

AbstractIn French, the placement of the adjective within a noun phrase is subject to variation: it can appear either before or after the noun. We conduct experiments to assess whether …...

AbstractUsing Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language …...

AbstractWe explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of the training dataset. We evaluate the models using automatic …...

AbstractIn the article, we present the CodeNLP submission to the SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition. Our approach is based on data augmentation by combining various …...

AbstractPretraining has been shown to scale well with compute, data size and data diversity. Multitask learning trains on a mixture of supervised datasets and produces improved performance compared to self-supervised …...

AbstractResponse generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm …...

AbstractState-of-the-art Automatic Speech Recognition (ASR) systems are known to exhibit disparate performance on varying speech accents. To improve performance on a specific target accent, a commonly adopted solution is to …...

AbstractFor most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains …...

AbstractLarge language models (LLMs) have been widely employed for graph-to-text generation tasks. However, the process of finetuning LLMs requires significant training resources and annotation work. In this paper, we explore …...

AbstractDiscrete prompts have been used for fine-tuning Pre-trained Language Models for diverse NLP tasks. In particular, automatic methods that generate discrete prompts from a small set of training instances have …...

AbstractPre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs. Motivated by the observation, in this paper, …...

AbstractDomain robustness is a key challenge for Neural Machine Translation (NMT). Translating text from a different distribution than the training set requires the NMT models to generalize well to unseen …...

AbstractThis paper presents the best-performing solution to the SemEval 2023 Task 3 on the subtask 3 dedicated to persuasion techniques detection. Due to a high multilingual character of the input …...

AbstractWe present the system proposed by the MilaNLP team for the Explainable Detection of Online Sexism (EDOS) shared task. We propose an ensemble modeling approach to combine different classifiers trained …...

AbstractFine-tuning pre-trained language models for multiple tasks can be expensive in terms of storage. Parameter-efficient transfer learning (PETL) methods have been proposed to address this issue, but they still require …...

AbstractPrompt tuning is an efficient method for adapting large language models, and Soft Prompt Transfer (SPoT) further narrows the gap between prompt tuning and full model tuning by transferring prompts …...

AbstractAs social media platforms grow, so too does the volume of hate speech and negative sentiment expressed towards particular social groups. In this paper, we describe our approach to SemEval-2023 …...

AbstractOur contribution to the 2023 AfriSenti-SemEval shared task 12: Sentiment Analysis for African Languages, provides insight into how a multilingual large language model can be a resource for sentiment analysis …...

AbstractLong-form question answering (LFQA) aims at answering complex, open-ended questions with detailed, paragraph-length responses. The de facto paradigm of LFQA necessitates two procedures: information retrieval, which searches for relevant supporting …...